# The Best Model For — full catalogue Checked: 2026-11-20T14:30:49.602Z Source: https://openrouter.ai/api/v1/models?output_modalities=all Rows: 290 OpenRouter documents every pricing value as USD per token, request, or unit. A published 0 means that field is free. The Best Model For multiplies only pricing.prompt and pricing.completion by 1,000,000 so those two fields read as USD per million tokens. Other fields are shown raw, because the unit can be a token, a request, or an image. ## GPT-3.5 Turbo (older v0613) Platform: OpenAI Id: openai/gpt-3.5-turbo-0613 URL: https://thebestmodelfor.com/models/openai--gpt-3.5-turbo-0613 OpenRouter: https://openrouter.ai/openai/gpt-3.5-turbo-0613 Kind: chat Listed: 2024-01-25 Context tokens: 4095 Max output tokens: 3685 Input USD per million: 1 Output USD per million: 2 Input per token (published): 0.000001 Output per token (published): 0.000002 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: 2021-09-30 Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks. Training data up to Sep 2021. Checked: 20 Nov 2026 ## GPT-3.5 Turbo 16k Platform: OpenAI Id: openai/gpt-3.5-turbo-16k URL: https://thebestmodelfor.com/models/openai--gpt-3.5-turbo-16k OpenRouter: https://openrouter.ai/openai/gpt-3.5-turbo-16k Kind: chat Listed: 2023-08-28 Context tokens: 16385 Max output tokens: 4096 Input USD per million: 3 Output USD per million: 4 Input per token (published): 0.000003 Output per token (published): 0.000004 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: 2021-09-30 Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: This model offers four times the context length of gpt-3.5-turbo, allowing it to support approximately 20 pages of text in a single request at a higher cost. Training data: up... Checked: 20 Nov 2026 ## GPT-4 Platform: OpenAI Id: openai/gpt-4 URL: https://thebestmodelfor.com/models/openai--gpt-4 OpenRouter: https://openrouter.ai/openai/gpt-4 Kind: chat Listed: 2023-05-28 Context tokens: 8191 Max output tokens: 4096 Input USD per million: 30 Output USD per million: 60 Input per token (published): 0.00003 Output per token (published): 0.00006 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: 2021-09-30 Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: OpenAI's flagship model, GPT-4 is a large-scale multimodal language model capable of solving difficult problems with greater accuracy than previous models due to its broader general knowledge and advanced reasoning... Checked: 20 Nov 2026 ## GPT-4.1 Platform: OpenAI Id: openai/gpt-4.1 URL: https://thebestmodelfor.com/models/openai--gpt-4.1 OpenRouter: https://openrouter.ai/openai/gpt-4.1 Kind: chat Listed: 2025-04-14 Context tokens: 1047576 Max output tokens: 32768 Input USD per million: 2 Output USD per million: 8 Input per token (published): 0.000002 Output per token (published): 0.000008 Batch input USD per million: 1 Batch output USD per million: 4 Other raw prices: web_search=0.01, input_cache_read=0.0000005 Input modalities: file, image, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: 2024-06-30 Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and... Checked: 20 Nov 2026 ## GPT-4.1 Mini Platform: OpenAI Id: openai/gpt-4.1-mini URL: https://thebestmodelfor.com/models/openai--gpt-4.1-mini OpenRouter: https://openrouter.ai/openai/gpt-4.1-mini Kind: chat Listed: 2025-04-14 Context tokens: 1047576 Max output tokens: 32768 Input USD per million: 0.4 Output USD per million: 1.6 Input per token (published): 0.0000004 Output per token (published): 0.0000016 Batch input USD per million: 0.2 Batch output USD per million: 0.8 Other raw prices: web_search=0.01, input_cache_read=0.0000001 Input modalities: file, image, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: 2024-06-30 Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.1% on hard... Checked: 20 Nov 2026 ## GPT-4.1 Nano Platform: OpenAI Id: openai/gpt-4.1-nano URL: https://thebestmodelfor.com/models/openai--gpt-4.1-nano OpenRouter: https://openrouter.ai/openai/gpt-4.1-nano Kind: chat Listed: 2025-04-14 Context tokens: 1047576 Max output tokens: 942818 Input USD per million: 0.1 Output USD per million: 0.4 Input per token (published): 0.0000001 Output per token (published): 0.0000004 Batch input USD per million: 0.05 Batch output USD per million: 0.2 Other raw prices: web_search=0.01, input_cache_read=0.00000003 Input modalities: file, image, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: 2024-06-30 Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million... Checked: 20 Nov 2026 ## GPT-4o Platform: OpenAI Id: openai/gpt-4o URL: https://thebestmodelfor.com/models/openai--gpt-4o OpenRouter: https://openrouter.ai/openai/gpt-4o Kind: chat Listed: 2024-05-13 Context tokens: 128000 Max output tokens: 16384 Input USD per million: 2.5 Output USD per million: 10 Input per token (published): 0.0000025 Output per token (published): 0.00001 Batch input USD per million: 1.25 Batch output USD per million: 5 Other raw prices: input_cache_read=0.00000125 Input modalities: file, image, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: 2023-10-31 Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: GPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of GPT-4 Turbo while being twice as... Checked: 20 Nov 2026 ## GPT-4o (2024-05-13) Platform: OpenAI Id: openai/gpt-4o-2024-05-13 URL: https://thebestmodelfor.com/models/openai--gpt-4o-2024-05-13 OpenRouter: https://openrouter.ai/openai/gpt-4o-2024-05-13 Kind: chat Listed: 2024-05-13 Context tokens: 128000 Max output tokens: 4096 Input USD per million: 5 Output USD per million: 15 Input per token (published): 0.000005 Output per token (published): 0.000015 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: file, image, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: 2023-10-31 Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: GPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of GPT-4 Turbo while being twice as... Checked: 20 Nov 2026 ## GPT-4o (2024-08-06) Platform: OpenAI Id: openai/gpt-4o-2024-08-06 URL: https://thebestmodelfor.com/models/openai--gpt-4o-2024-08-06 OpenRouter: https://openrouter.ai/openai/gpt-4o-2024-08-06 Kind: chat Listed: 2024-08-06 Context tokens: 128000 Max output tokens: 16384 Input USD per million: 2.5 Output USD per million: 10 Input per token (published): 0.0000025 Output per token (published): 0.00001 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: input_cache_read=0.00000125 Input modalities: file, image, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: 2023-10-31 Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: The 2024-08-06 version of GPT-4o offers improved performance in structured outputs, with the ability to supply a JSON schema in the responeformat. Read more here. GPT-4o ("o" for "omni") is... Checked: 20 Nov 2026 ## GPT-4o (2024-11-20) Platform: OpenAI Id: openai/gpt-4o-2024-11-20 URL: https://thebestmodelfor.com/models/openai--gpt-4o-2024-11-20 OpenRouter: https://openrouter.ai/openai/gpt-4o-2024-11-20 Kind: chat Listed: 2024-11-20 Context tokens: 128000 Max output tokens: 16384 Input USD per million: 2.5 Output USD per million: 10 Input per token (published): 0.0000025 Output per token (published): 0.00001 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: input_cache_read=0.00000125 Input modalities: file, image, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: 2023-10-31 Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: The 2024-11-20 version of GPT-4o offers a leveled-up creative writing ability with more natural, engaging, and tailored writing to improve relevance & readability. It’s also better at working with uploaded... Checked: 20 Nov 2026 ## GPT-4o-mini Platform: OpenAI Id: openai/gpt-4o-mini URL: https://thebestmodelfor.com/models/openai--gpt-4o-mini OpenRouter: https://openrouter.ai/openai/gpt-4o-mini Kind: chat Listed: 2024-07-18 Context tokens: 128000 Max output tokens: 16384 Input USD per million: 0.15 Output USD per million: 0.6 Input per token (published): 0.00000015 Output per token (published): 0.0000006 Batch input USD per million: 0.075 Batch output USD per million: 0.3 Other raw prices: input_cache_read=0.000000075 Input modalities: file, image, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: 2023-10-31 Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: GPT-4o mini is OpenAI's newest model after GPT-4 Omni, supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable... Checked: 20 Nov 2026 ## GPT-4o-mini (2024-07-18) Platform: OpenAI Id: openai/gpt-4o-mini-2024-07-18 URL: https://thebestmodelfor.com/models/openai--gpt-4o-mini-2024-07-18 OpenRouter: https://openrouter.ai/openai/gpt-4o-mini-2024-07-18 Kind: chat Listed: 2024-07-18 Context tokens: 128000 Max output tokens: 16384 Input USD per million: 0.15 Output USD per million: 0.6 Input per token (published): 0.00000015 Output per token (published): 0.0000006 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: input_cache_read=0.000000075 Input modalities: file, image, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: 2023-10-31 Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: GPT-4o mini is OpenAI's newest model after GPT-4 Omni, supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable... Checked: 20 Nov 2026 ## GPT-4o Mini Transcribe Platform: OpenAI Id: openai/gpt-4o-mini-transcribe URL: https://thebestmodelfor.com/models/openai--gpt-4o-mini-transcribe OpenRouter: https://openrouter.ai/openai/gpt-4o-mini-transcribe Kind: transcription Listed: 2026-05-01 Context tokens: 128000 Max output tokens: 115200 Input USD per million: 1.25 Output USD per million: 5 Input per token (published): 0.00000125 Output per token (published): 0.000005 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: audio Output modalities: transcription Tools: Not listed Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: GPT-4o Mini Transcribe is OpenAI's smaller, cost-efficient speech-to-text model built on GPT-4o Mini audio capabilities. It's priced per token (input and output), making it suitable for high-volume transcription workflows that... Checked: 20 Nov 2026 ## GPT-4o Transcribe Platform: OpenAI Id: openai/gpt-4o-transcribe URL: https://thebestmodelfor.com/models/openai--gpt-4o-transcribe OpenRouter: https://openrouter.ai/openai/gpt-4o-transcribe Kind: transcription Listed: 2026-04-27 Context tokens: 128000 Max output tokens: 115200 Input USD per million: 2.5 Output USD per million: 10 Input per token (published): 0.0000025 Output per token (published): 0.00001 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: audio Output modalities: transcription Tools: Not listed Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: GPT-4o Transcribe is OpenAI's high-quality speech-to-text model built on GPT-4o audio capabilities. It's priced per token (input and output), making it suitable for workflows that benefit from token-level billing transparency. Checked: 20 Nov 2026 ## GPT-5 Platform: OpenAI Id: openai/gpt-5 URL: https://thebestmodelfor.com/models/openai--gpt-5 OpenRouter: https://openrouter.ai/openai/gpt-5 Kind: chat Listed: 2025-08-07 Context tokens: 400000 Max output tokens: 128000 Input USD per million: 1.25 Output USD per million: 10 Input per token (published): 0.00000125 Output per token (published): 0.00001 Batch input USD per million: 0.625 Batch output USD per million: 5 Other raw prices: web_search=0.01, input_cache_read=0.000000125 Input modalities: file, image, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: 2024-09-30 Reasoning: required Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy... Checked: 20 Nov 2026 ## GPT-5 Image Platform: OpenAI Id: openai/gpt-5-image URL: https://thebestmodelfor.com/models/openai--gpt-5-image OpenRouter: https://openrouter.ai/openai/gpt-5-image Kind: image Listed: 2025-10-14 Context tokens: 400000 Max output tokens: 128000 Input USD per million: 10 Output USD per million: 10 Input per token (published): 0.00001 Output per token (published): 0.00001 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: image_output=0.00004, web_search=0.01, input_cache_read=0.00000125 Input modalities: file, image, text Output modalities: image, text Tools: Not listed Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: required Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: GPT-5 Image combines OpenAI's GPT-5 model with state-of-the-art image generation capabilities. It offers major improvements in reasoning, code quality, and user experience while incorporating GPT Image 1's superior instruction following,... Checked: 20 Nov 2026 ## GPT-5 Image Mini Platform: OpenAI Id: openai/gpt-5-image-mini URL: https://thebestmodelfor.com/models/openai--gpt-5-image-mini OpenRouter: https://openrouter.ai/openai/gpt-5-image-mini Kind: image Listed: 2025-10-16 Context tokens: 400000 Max output tokens: 128000 Input USD per million: 2.5 Output USD per million: 2 Input per token (published): 0.0000025 Output per token (published): 0.000002 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: image_output=0.000008, web_search=0.01, input_cache_read=0.00000025 Input modalities: file, image, text Output modalities: image, text Tools: Not listed Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: required Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: GPT-5 Image Mini combines OpenAI's advanced language capabilities, powered by GPT-5 Mini, with GPT Image 1 Mini for efficient image generation. This natively multimodal model features superior instruction following, text... Checked: 20 Nov 2026 ## GPT-5 Mini Platform: OpenAI Id: openai/gpt-5-mini URL: https://thebestmodelfor.com/models/openai--gpt-5-mini OpenRouter: https://openrouter.ai/openai/gpt-5-mini Kind: chat Listed: 2025-08-07 Context tokens: 400000 Max output tokens: 128000 Input USD per million: 0.25 Output USD per million: 2 Input per token (published): 0.00000025 Output per token (published): 0.000002 Batch input USD per million: 0.125 Batch output USD per million: 1 Other raw prices: web_search=0.01, input_cache_read=0.000000025 Input modalities: file, image, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: 2024-05-31 Reasoning: required Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost.... Checked: 20 Nov 2026 ## GPT-5 Nano Platform: OpenAI Id: openai/gpt-5-nano URL: https://thebestmodelfor.com/models/openai--gpt-5-nano OpenRouter: https://openrouter.ai/openai/gpt-5-nano Kind: chat Listed: 2025-08-07 Context tokens: 400000 Max output tokens: 128000 Input USD per million: 0.05 Output USD per million: 0.4 Input per token (published): 0.00000005 Output per token (published): 0.0000004 Batch input USD per million: 0.025 Batch output USD per million: 0.2 Other raw prices: web_search=0.01, input_cache_read=0.000000005 Input modalities: file, image, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: 2024-05-31 Reasoning: required Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments. While limited in reasoning depth compared to its larger... Checked: 20 Nov 2026 ## GPT-5 Pro Platform: OpenAI Id: openai/gpt-5-pro URL: https://thebestmodelfor.com/models/openai--gpt-5-pro OpenRouter: https://openrouter.ai/openai/gpt-5-pro Kind: chat Listed: 2025-10-06 Context tokens: 400000 Max output tokens: 128000 Input USD per million: 15 Output USD per million: 120 Input per token (published): 0.000015 Output per token (published): 0.00012 Batch input USD per million: 7.5 Batch output USD per million: 60 Other raw prices: web_search=0.01 Input modalities: file, image, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: 2024-09-30 Reasoning: required Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: GPT-5 Pro is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and... Checked: 20 Nov 2026 ## GPT-5.1 Platform: OpenAI Id: openai/gpt-5.1 URL: https://thebestmodelfor.com/models/openai--gpt-5.1 OpenRouter: https://openrouter.ai/openai/gpt-5.1 Kind: chat Listed: 2025-11-13 Context tokens: 400000 Max output tokens: 128000 Input USD per million: 1.25 Output USD per million: 10 Input per token (published): 0.00000125 Output per token (published): 0.00001 Batch input USD per million: 0.625 Batch output USD per million: 5 Other raw prices: web_search=0.01, input_cache_read=0.000000125 Input modalities: file, image, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: optional Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style compared to GPT-5. It uses adaptive reasoning... Checked: 20 Nov 2026 ## GPT-5.1-Codex Platform: OpenAI Id: openai/gpt-5.1-codex URL: https://thebestmodelfor.com/models/openai--gpt-5.1-codex OpenRouter: https://openrouter.ai/openai/gpt-5.1-codex Kind: chat Listed: 2025-11-13 Context tokens: 400000 Max output tokens: 128000 Input USD per million: 1.25 Output USD per million: 10 Input per token (published): 0.00000125 Output per token (published): 0.00001 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: web_search=0.01, input_cache_read=0.00000013 Input modalities: image, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: required Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: GPT-5.1-Codex is a specialized version of GPT-5.1 optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks.... Checked: 20 Nov 2026 ## GPT-5.1-Codex-Max Platform: OpenAI Id: openai/gpt-5.1-codex-max URL: https://thebestmodelfor.com/models/openai--gpt-5.1-codex-max OpenRouter: https://openrouter.ai/openai/gpt-5.1-codex-max Kind: chat Listed: 2025-12-04 Context tokens: 400000 Max output tokens: 128000 Input USD per million: 1.25 Output USD per million: 10 Input per token (published): 0.00000125 Output per token (published): 0.00001 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: web_search=0.01, input_cache_read=0.000000125 Input modalities: image, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: required Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: GPT-5.1-Codex-Max is OpenAI’s latest agentic coding model, designed for long-running, high-context software development tasks. It is based on an updated version of the 5.1 reasoning stack and trained on agentic... Checked: 20 Nov 2026 ## GPT-5.1-Codex-Mini Platform: OpenAI Id: openai/gpt-5.1-codex-mini URL: https://thebestmodelfor.com/models/openai--gpt-5.1-codex-mini OpenRouter: https://openrouter.ai/openai/gpt-5.1-codex-mini Kind: chat Listed: 2025-11-13 Context tokens: 400000 Max output tokens: 128000 Input USD per million: 0.25 Output USD per million: 2 Input per token (published): 0.00000025 Output per token (published): 0.000002 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: web_search=0.01, input_cache_read=0.00000003 Input modalities: image, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: required Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: GPT-5.1-Codex-Mini is a smaller and faster version of GPT-5.1-Codex Checked: 20 Nov 2026 ## GPT-5.2 Platform: OpenAI Id: openai/gpt-5.2 URL: https://thebestmodelfor.com/models/openai--gpt-5.2 OpenRouter: https://openrouter.ai/openai/gpt-5.2 Kind: chat Listed: 2025-12-10 Context tokens: 400000 Max output tokens: 128000 Input USD per million: 1.75 Output USD per million: 14 Input per token (published): 0.00000175 Output per token (published): 0.000014 Batch input USD per million: 0.875 Batch output USD per million: 7 Other raw prices: web_search=0.01, input_cache_read=0.000000175 Input modalities: file, image, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: optional Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1. It uses adaptive reasoning to allocate computation dynamically, responding quickly... Checked: 20 Nov 2026 ## GPT-5.2 Chat Platform: OpenAI Id: openai/gpt-5.2-chat URL: https://thebestmodelfor.com/models/openai--gpt-5.2-chat OpenRouter: https://openrouter.ai/openai/gpt-5.2-chat Kind: chat Listed: 2025-12-10 Context tokens: 128000 Max output tokens: 32000 Input USD per million: 1.75 Output USD per million: 14 Input per token (published): 0.00000175 Output per token (published): 0.000014 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: web_search=0.01, input_cache_read=0.000000175 Input modalities: file, image, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: GPT-5.2 Chat (AKA Instant) is the fast, lightweight member of the 5.2 family, optimized for low-latency chat while retaining strong general intelligence. It uses adaptive reasoning to selectively “think” on... Checked: 20 Nov 2026 ## GPT-5.2-Codex Platform: OpenAI Id: openai/gpt-5.2-codex URL: https://thebestmodelfor.com/models/openai--gpt-5.2-codex OpenRouter: https://openrouter.ai/openai/gpt-5.2-codex Kind: chat Listed: 2026-01-14 Context tokens: 400000 Max output tokens: 128000 Input USD per million: 1.75 Output USD per million: 14 Input per token (published): 0.00000175 Output per token (published): 0.000014 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: web_search=0.01, input_cache_read=0.000000175 Input modalities: image, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: required Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: GPT-5.2-Codex is an upgraded version of GPT-5.1-Codex optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks.... Checked: 20 Nov 2026 ## GPT-5.2 Pro Platform: OpenAI Id: openai/gpt-5.2-pro URL: https://thebestmodelfor.com/models/openai--gpt-5.2-pro OpenRouter: https://openrouter.ai/openai/gpt-5.2-pro Kind: chat Listed: 2025-12-10 Context tokens: 400000 Max output tokens: 128000 Input USD per million: 21 Output USD per million: 168 Input per token (published): 0.000021 Output per token (published): 0.000168 Batch input USD per million: 10.5 Batch output USD per million: 84 Other raw prices: web_search=0.01 Input modalities: file, image, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: required Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: GPT-5.2 Pro is OpenAI’s most advanced model, offering major improvements in agentic coding and long context performance over GPT-5 Pro. It is optimized for complex tasks that require step-by-step reasoning,... Checked: 20 Nov 2026 ## GPT-5.3-Codex Platform: OpenAI Id: openai/gpt-5.3-codex URL: https://thebestmodelfor.com/models/openai--gpt-5.3-codex OpenRouter: https://openrouter.ai/openai/gpt-5.3-codex Kind: chat Listed: 2026-02-24 Context tokens: 400000 Max output tokens: 128000 Input USD per million: 1.75 Output USD per million: 14 Input per token (published): 0.00000175 Output per token (published): 0.000014 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: web_search=0.01, input_cache_read=0.000000175 Input modalities: file, image, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: optional Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: GPT-5.3-Codex is OpenAI’s most advanced agentic coding model, combining the frontier software engineering performance of GPT-5.2-Codex with the broader reasoning and professional knowledge capabilities of GPT-5.2. It achieves state-of-the-art results... Checked: 20 Nov 2026 ## GPT-5.4 Platform: OpenAI Id: openai/gpt-5.4 URL: https://thebestmodelfor.com/models/openai--gpt-5.4 OpenRouter: https://openrouter.ai/openai/gpt-5.4 Kind: chat Listed: 2026-03-05 Context tokens: 1050000 Max output tokens: 128000 Input USD per million: 2.5 Output USD per million: 15 Input per token (published): 0.0000025 Output per token (published): 0.000015 Batch input USD per million: 1.25 Batch output USD per million: 7.5 Other raw prices: web_search=0.01, input_cache_read=0.00000025 Input modalities: file, image, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: optional Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for... Checked: 20 Nov 2026 ## GPT-5.4 Image 2 Platform: OpenAI Id: openai/gpt-5.4-image-2 URL: https://thebestmodelfor.com/models/openai--gpt-5.4-image-2 OpenRouter: https://openrouter.ai/openai/gpt-5.4-image-2 Kind: image Listed: 2026-04-21 Context tokens: 272000 Max output tokens: 128000 Input USD per million: 8 Output USD per million: 15 Input per token (published): 0.000008 Output per token (published): 0.000015 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: image_output=0.00003, web_search=0.01, input_cache_read=0.000002 Input modalities: file, image, text Output modalities: image, text Tools: Not listed Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: optional Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: GPT-5.4 Image 2 combines OpenAI's GPT-5.4 model with state-of-the-art image generation capabilities from GPT Image 2. It enables rich multimodal workflows, allowing users to seamlessly move between reasoning, coding, and... Checked: 20 Nov 2026 ## GPT-5.4 Mini Platform: OpenAI Id: openai/gpt-5.4-mini URL: https://thebestmodelfor.com/models/openai--gpt-5.4-mini OpenRouter: https://openrouter.ai/openai/gpt-5.4-mini Kind: chat Listed: 2026-03-17 Context tokens: 400000 Max output tokens: 128000 Input USD per million: 0.75 Output USD per million: 4.5 Input per token (published): 0.00000075 Output per token (published): 0.0000045 Batch input USD per million: 0.375 Batch output USD per million: 2.25 Other raw prices: web_search=0.01, input_cache_read=0.000000075 Input modalities: file, image, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: 2025-08-31 Reasoning: optional Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong performance across reasoning, coding,... Checked: 20 Nov 2026 ## GPT-5.4 Nano Platform: OpenAI Id: openai/gpt-5.4-nano URL: https://thebestmodelfor.com/models/openai--gpt-5.4-nano OpenRouter: https://openrouter.ai/openai/gpt-5.4-nano Kind: chat Listed: 2026-03-17 Context tokens: 400000 Max output tokens: 128000 Input USD per million: 0.2 Output USD per million: 1.25 Input per token (published): 0.0000002 Output per token (published): 0.00000125 Batch input USD per million: 0.1 Batch output USD per million: 0.625 Other raw prices: web_search=0.01, input_cache_read=0.00000002 Input modalities: file, image, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: 2025-08-31 Reasoning: optional Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks. It supports text and image inputs and is designed for low-latency... Checked: 20 Nov 2026 ## GPT-5.4 Pro Platform: OpenAI Id: openai/gpt-5.4-pro URL: https://thebestmodelfor.com/models/openai--gpt-5.4-pro OpenRouter: https://openrouter.ai/openai/gpt-5.4-pro Kind: chat Listed: 2026-03-05 Context tokens: 1050000 Max output tokens: 128000 Input USD per million: 30 Output USD per million: 180 Input per token (published): 0.00003 Output per token (published): 0.00018 Batch input USD per million: 15 Batch output USD per million: 90 Other raw prices: web_search=0.01 Input modalities: file, image, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: required Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: GPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified architecture with enhanced reasoning capabilities for complex, high-stakes tasks. It features a 1M+ token context window (922K input, 128K... Checked: 20 Nov 2026 ## GPT-5.5 Platform: OpenAI Id: openai/gpt-5.5 URL: https://thebestmodelfor.com/models/openai--gpt-5.5 OpenRouter: https://openrouter.ai/openai/gpt-5.5 Kind: chat Listed: 2026-04-24 Context tokens: 1050000 Max output tokens: 128000 Input USD per million: 5 Output USD per million: 30 Input per token (published): 0.000005 Output per token (published): 0.00003 Batch input USD per million: 2.5 Batch output USD per million: 15 Other raw prices: web_search=0.01, input_cache_read=0.0000005 Input modalities: file, image, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: 2025-12-01 Reasoning: optional Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token... Checked: 20 Nov 2026 ## GPT-5.5 Pro Platform: OpenAI Id: openai/gpt-5.5-pro URL: https://thebestmodelfor.com/models/openai--gpt-5.5-pro OpenRouter: https://openrouter.ai/openai/gpt-5.5-pro Kind: chat Listed: 2026-04-24 Context tokens: 1050000 Max output tokens: 128000 Input USD per million: 30 Output USD per million: 180 Input per token (published): 0.00003 Output per token (published): 0.00018 Batch input USD per million: 15 Batch output USD per million: 90 Other raw prices: web_search=0.01 Input modalities: file, image, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: 2025-12-01 Reasoning: required Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: GPT-5.5 Pro is OpenAI’s high-capability model optimized for deep reasoning and accuracy on complex, high-stakes workloads. It features a 1M+ token context window (922K input, 128K output) with support for... Checked: 20 Nov 2026 ## GPT-5.6 Luna Platform: OpenAI Id: openai/gpt-5.6-luna URL: https://thebestmodelfor.com/models/openai--gpt-5.6-luna OpenRouter: https://openrouter.ai/openai/gpt-5.6-luna Kind: chat Listed: 2026-07-09 Context tokens: 1050000 Max output tokens: 128000 Input USD per million: 0.2 Output USD per million: 1.2 Input per token (published): 0.0000002 Output per token (published): 0.0000012 Batch input USD per million: 0.1 Batch output USD per million: 0.6 Other raw prices: web_search=0.01, input_cache_read=0.00000002, input_cache_write=0.00000025 Input modalities: file, image, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: 2026-02-16 Reasoning: optional Third-party intelligence index: 23.8 Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for... Checked: 20 Nov 2026 ## GPT-5.6 Luna Pro Platform: OpenAI Id: openai/gpt-5.6-luna-pro URL: https://thebestmodelfor.com/models/openai--gpt-5.6-luna-pro OpenRouter: https://openrouter.ai/openai/gpt-5.6-luna-pro Kind: chat Listed: 2026-07-09 Context tokens: 1050000 Max output tokens: 128000 Input USD per million: 0.2 Output USD per million: 1.2 Input per token (published): 0.0000002 Output per token (published): 0.0000012 Batch input USD per million: 0.1 Batch output USD per million: 0.6 Other raw prices: web_search=0.01, input_cache_read=0.00000002, input_cache_write=0.00000025 Input modalities: file, image, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: 2026-02-16 Reasoning: optional Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: GPT-5.6 Luna Pro is the same underlying model as GPT-5.6 Luna, served with reasoning.mode set to pro for higher-quality responses on complex tasks. Cost note: pro mode spends far more... Checked: 20 Nov 2026 ## GPT-5.6 Sol Platform: OpenAI Id: openai/gpt-5.6-sol URL: https://thebestmodelfor.com/models/openai--gpt-5.6-sol OpenRouter: https://openrouter.ai/openai/gpt-5.6-sol Kind: chat Listed: 2026-07-09 Context tokens: 1050000 Max output tokens: 128000 Input USD per million: 4 Output USD per million: 20 Input per token (published): 0.000004 Output per token (published): 0.00002 Batch input USD per million: 2 Batch output USD per million: 10 Other raw prices: web_search=0.01, input_cache_read=0.0000004, input_cache_write=0.000005 Input modalities: file, image, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: 2026-02-16 Reasoning: optional Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks... Checked: 20 Nov 2026 ## GPT-5.6 Sol Pro Platform: OpenAI Id: openai/gpt-5.6-sol-pro URL: https://thebestmodelfor.com/models/openai--gpt-5.6-sol-pro OpenRouter: https://openrouter.ai/openai/gpt-5.6-sol-pro Kind: chat Listed: 2026-07-09 Context tokens: 1050000 Max output tokens: 128000 Input USD per million: 4 Output USD per million: 20 Input per token (published): 0.000004 Output per token (published): 0.00002 Batch input USD per million: 2 Batch output USD per million: 10 Other raw prices: web_search=0.01, input_cache_read=0.0000004, input_cache_write=0.000005 Input modalities: file, image, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: 2026-02-16 Reasoning: optional Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: GPT-5.6 Sol Pro is the same underlying model as GPT-5.6 Sol, served with reasoning.mode set to pro for higher-quality responses on complex tasks. Cost note: pro mode spends far more... Checked: 20 Nov 2026 ## GPT-5.6 Terra Platform: OpenAI Id: openai/gpt-5.6-terra URL: https://thebestmodelfor.com/models/openai--gpt-5.6-terra OpenRouter: https://openrouter.ai/openai/gpt-5.6-terra Kind: chat Listed: 2026-07-09 Context tokens: 1050000 Max output tokens: 128000 Input USD per million: 2 Output USD per million: 12 Input per token (published): 0.000002 Output per token (published): 0.000012 Batch input USD per million: 1 Batch output USD per million: 6 Other raw prices: web_search=0.01, input_cache_read=0.0000002, input_cache_write=0.0000025 Input modalities: file, image, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: 2026-02-16 Reasoning: optional Third-party intelligence index: 32.3 Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and agentic... Checked: 20 Nov 2026 ## GPT-5.6 Terra Pro Platform: OpenAI Id: openai/gpt-5.6-terra-pro URL: https://thebestmodelfor.com/models/openai--gpt-5.6-terra-pro OpenRouter: https://openrouter.ai/openai/gpt-5.6-terra-pro Kind: chat Listed: 2026-07-09 Context tokens: 1050000 Max output tokens: 128000 Input USD per million: 2 Output USD per million: 12 Input per token (published): 0.000002 Output per token (published): 0.000012 Batch input USD per million: 1 Batch output USD per million: 6 Other raw prices: web_search=0.01, input_cache_read=0.0000002, input_cache_write=0.0000025 Input modalities: file, image, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: 2026-02-16 Reasoning: optional Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: GPT-5.6 Terra Pro is the same underlying model as GPT-5.6 Terra, served with reasoning.mode set to pro for higher-quality responses on complex tasks. Cost note: pro mode spends far more... Checked: 20 Nov 2026 ## GPT-6 Astra Platform: OpenAI Id: openai/gpt-6-astra URL: https://thebestmodelfor.com/models/openai--gpt-6-astra OpenRouter: https://openrouter.ai/openai/gpt-6-astra Kind: chat Listed: 2026-09-04 Context tokens: 1050000 Max output tokens: 128000 Input USD per million: 10 Output USD per million: 50 Input per token (published): 0.00001 Output per token (published): 0.00005 Batch input USD per million: 5 Batch output USD per million: 25 Other raw prices: web_search=0.01, input_cache_read=0.000001, input_cache_write=0.0000125 Input modalities: file, image, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: required Third-party intelligence index: 56.9 Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: GPT-6 Astra is OpenAI's flagship model for demanding end-to-end work. It is suited for advanced analysis, software engineering, deep research, scientific work, and document creation, with particular strengths in long-horizon... Checked: 20 Nov 2026 ## GPT-6 Astra Pro Platform: OpenAI Id: openai/gpt-6-astra-pro URL: https://thebestmodelfor.com/models/openai--gpt-6-astra-pro OpenRouter: https://openrouter.ai/openai/gpt-6-astra-pro Kind: chat Listed: 2026-09-04 Context tokens: 1050000 Max output tokens: 128000 Input USD per million: 10 Output USD per million: 50 Input per token (published): 0.00001 Output per token (published): 0.00005 Batch input USD per million: 5 Batch output USD per million: 25 Other raw prices: web_search=0.01, input_cache_read=0.000001, input_cache_write=0.0000125 Input modalities: file, image, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: required Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: GPT-6 Astra Pro is the same underlying model as GPT-6 Astra, served with reasoning.mode set to pro for higher-quality responses on complex tasks. Cost note: pro mode spends far more... Checked: 20 Nov 2026 ## GPT-6 Luna Platform: OpenAI Id: openai/gpt-6-luna URL: https://thebestmodelfor.com/models/openai--gpt-6-luna OpenRouter: https://openrouter.ai/openai/gpt-6-luna Kind: chat Listed: 2026-09-22 Context tokens: 1050000 Max output tokens: 128000 Input USD per million: 0.1 Output USD per million: 0.5 Input per token (published): 0.0000001 Output per token (published): 0.0000005 Batch input USD per million: 0.05 Batch output USD per million: 0.25 Other raw prices: web_search=0.01, input_cache_read=0.00000001, input_cache_write=0.000000125 Input modalities: file, image, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: optional Third-party intelligence index: 27.9 Third-party coding index: unknown Guide: reviewed 2026-11-19 — OpenRouter describes GPT-6 Luna as the fast, cost-efficient GPT-6 model for high-volume work such as chat, classification, and light agent steps. It is the reviewed cheap OpenAI option. Listing blurb: GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic... Checked: 20 Nov 2026 ## GPT-6 Luna Decisions Platform: OpenAI Id: openai/gpt-6-luna-decisions URL: https://thebestmodelfor.com/models/openai--gpt-6-luna-decisions OpenRouter: https://openrouter.ai/openai/gpt-6-luna-decisions Kind: decisions Listed: 2026-10-06 Context tokens: 1050000 Max output tokens: 945000 Input USD per million: 0.1 Output USD per million: 0 Input per token (published): 0.0000001 Output per token (published): 0 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: web_search=0.01, input_cache_read=0, input_cache_write=0 Input modalities: image, text Output modalities: decisions Tools: Not listed Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: GPT-6 Luna Decisions is GPT-6 Luna served through OpenAI's Decisions API. Instead of generating text, it reads the content passed as state (text, JSON, or images) and returns typed, probabilistic... Checked: 20 Nov 2026 ## GPT-6 Luna Pro Platform: OpenAI Id: openai/gpt-6-luna-pro URL: https://thebestmodelfor.com/models/openai--gpt-6-luna-pro OpenRouter: https://openrouter.ai/openai/gpt-6-luna-pro Kind: chat Listed: 2026-09-22 Context tokens: 1050000 Max output tokens: 128000 Input USD per million: 0.1 Output USD per million: 0.5 Input per token (published): 0.0000001 Output per token (published): 0.0000005 Batch input USD per million: 0.05 Batch output USD per million: 0.25 Other raw prices: web_search=0.01, input_cache_read=0.00000001, input_cache_write=0.000000125 Input modalities: file, image, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: optional Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: GPT-6 Luna Pro is the same underlying model as GPT-6 Luna, served with reasoning.mode set to pro for higher-quality responses on complex tasks. Cost note: pro mode spends far more... Checked: 20 Nov 2026 ## GPT-6 Sol Platform: OpenAI Id: openai/gpt-6-sol URL: https://thebestmodelfor.com/models/openai--gpt-6-sol OpenRouter: https://openrouter.ai/openai/gpt-6-sol Kind: chat Listed: 2026-09-22 Context tokens: 1050000 Max output tokens: 128000 Input USD per million: 2 Output USD per million: 10 Input per token (published): 0.000002 Output per token (published): 0.00001 Batch input USD per million: 1 Batch output USD per million: 5 Other raw prices: web_search=0.01, input_cache_read=0.0000002, input_cache_write=0.0000025 Input modalities: file, image, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: optional Third-party intelligence index: 44.2 Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier. It is suited for demanding professional... Checked: 20 Nov 2026 ## GPT-6 Sol Pro Platform: OpenAI Id: openai/gpt-6-sol-pro URL: https://thebestmodelfor.com/models/openai--gpt-6-sol-pro OpenRouter: https://openrouter.ai/openai/gpt-6-sol-pro Kind: chat Listed: 2026-09-22 Context tokens: 1050000 Max output tokens: 128000 Input USD per million: 2 Output USD per million: 10 Input per token (published): 0.000002 Output per token (published): 0.00001 Batch input USD per million: 1 Batch output USD per million: 5 Other raw prices: web_search=0.01, input_cache_read=0.0000002, input_cache_write=0.0000025 Input modalities: file, image, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: optional Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: GPT-6 Sol Pro is the same underlying model as GPT-6 Sol, served with reasoning.mode set to pro for higher-quality responses on complex tasks. Cost note: pro mode spends far more... Checked: 20 Nov 2026 ## GPT-6.1 Sol Platform: OpenAI Id: openai/gpt-6.1-sol URL: https://thebestmodelfor.com/models/openai--gpt-6.1-sol OpenRouter: https://openrouter.ai/openai/gpt-6.1-sol Kind: chat Listed: 2026-09-29 Context tokens: 1050000 Max output tokens: 128000 Input USD per million: 2 Output USD per million: 10 Input per token (published): 0.000002 Output per token (published): 0.00001 Batch input USD per million: 1 Batch output USD per million: 5 Other raw prices: web_search=0.01, input_cache_read=0.0000001, input_cache_write=0.0000025 Input modalities: file, image, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: required Third-party intelligence index: 54.6 Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series. It is suited for agentic coding, computer use, document-heavy professional... Checked: 20 Nov 2026 ## GPT-6.1 Sol Pro Platform: OpenAI Id: openai/gpt-6.1-sol-pro URL: https://thebestmodelfor.com/models/openai--gpt-6.1-sol-pro OpenRouter: https://openrouter.ai/openai/gpt-6.1-sol-pro Kind: chat Listed: 2026-09-29 Context tokens: 1050000 Max output tokens: 128000 Input USD per million: 2 Output USD per million: 10 Input per token (published): 0.000002 Output per token (published): 0.00001 Batch input USD per million: 1 Batch output USD per million: 5 Other raw prices: web_search=0.01, input_cache_read=0.0000001, input_cache_write=0.0000025 Input modalities: file, image, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: required Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: GPT-6.1 Sol Pro is the same underlying model as GPT-6.1 Sol, served with reasoning.mode set to pro for higher-quality responses on complex tasks. Cost note: pro mode spends far more... Checked: 20 Nov 2026 ## GPT-6.1 Terra Platform: OpenAI Id: openai/gpt-6.1-terra URL: https://thebestmodelfor.com/models/openai--gpt-6.1-terra OpenRouter: https://openrouter.ai/openai/gpt-6.1-terra Kind: chat Listed: 2026-10-26 Context tokens: 1050000 Max output tokens: 128000 Input USD per million: 1 Output USD per million: 5 Input per token (published): 0.000001 Output per token (published): 0.000005 Batch input USD per million: 0.5 Batch output USD per million: 2.5 Other raw prices: web_search=0.01, input_cache_read=0.00000005, input_cache_write=0.00000125 Input modalities: file, image, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: optional Third-party intelligence index: 51.3 Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: GPT-6.1 Terra is the mid-tier model in OpenAI's GPT-6.1 series, priced below GPT-6.1 Sol. It is suited for everyday agentic, coding, and writing work, is particularly strong at understanding screenshots... Checked: 20 Nov 2026 ## GPT-6.1 Terra Pro Platform: OpenAI Id: openai/gpt-6.1-terra-pro URL: https://thebestmodelfor.com/models/openai--gpt-6.1-terra-pro OpenRouter: https://openrouter.ai/openai/gpt-6.1-terra-pro Kind: chat Listed: 2026-10-26 Context tokens: 1050000 Max output tokens: 128000 Input USD per million: 1 Output USD per million: 5 Input per token (published): 0.000001 Output per token (published): 0.000005 Batch input USD per million: 0.5 Batch output USD per million: 2.5 Other raw prices: web_search=0.01, input_cache_read=0.00000005, input_cache_write=0.00000125 Input modalities: file, image, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: required Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: GPT-6.1 Terra Pro is the same underlying model as GPT-6.1 Terra, served with reasoning.mode set to pro for higher-quality responses on complex tasks. Cost note: pro mode spends far more... Checked: 20 Nov 2026 ## GPT-6.2 Astra Platform: OpenAI Id: openai/gpt-6.2-astra URL: https://thebestmodelfor.com/models/openai--gpt-6.2-astra OpenRouter: https://openrouter.ai/openai/gpt-6.2-astra Kind: chat Listed: 2026-11-17 Context tokens: 1050000 Max output tokens: 128000 Input USD per million: 8 Output USD per million: 40 Input per token (published): 0.000008 Output per token (published): 0.00004 Batch input USD per million: 4 Batch output USD per million: 20 Other raw prices: web_search=0.01, input_cache_read=0.0000004, input_cache_write=0.00001 Input modalities: file, image, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: required Third-party intelligence index: 62.1 Third-party coding index: unknown Guide: reviewed 2026-11-19 — OpenRouter describes GPT-6.2 Astra as OpenAI's flagship for the hardest projects, including engineering and scientific research. Use it when a wrong answer is expensive to redo. The feed lists Astra Pro as the same model with a higher reasoning mode, and warns that pro mode spends more, even though the published per-token rates match. Listing blurb: GPT-6.2 Astra is the flagship model in the GPT-6.2 series from OpenAI, built for the hardest projects. It is suited for real-world engineering, professional work and scientific research, with stronger... Checked: 20 Nov 2026 ## GPT-6.2 Astra Pro Platform: OpenAI Id: openai/gpt-6.2-astra-pro URL: https://thebestmodelfor.com/models/openai--gpt-6.2-astra-pro OpenRouter: https://openrouter.ai/openai/gpt-6.2-astra-pro Kind: chat Listed: 2026-11-17 Context tokens: 1050000 Max output tokens: 128000 Input USD per million: 8 Output USD per million: 40 Input per token (published): 0.000008 Output per token (published): 0.00004 Batch input USD per million: 4 Batch output USD per million: 20 Other raw prices: web_search=0.01, input_cache_read=0.0000004, input_cache_write=0.00001 Input modalities: file, image, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: required Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: GPT-6.2 Astra Pro is the same underlying model as GPT-6.2 Astra, served with reasoning.mode set to pro for higher-quality responses on complex tasks. Cost note: pro mode spends far more... Checked: 20 Nov 2026 ## GPT-6.2 Sol Platform: OpenAI Id: openai/gpt-6.2-sol URL: https://thebestmodelfor.com/models/openai--gpt-6.2-sol OpenRouter: https://openrouter.ai/openai/gpt-6.2-sol Kind: chat Listed: 2026-11-17 Context tokens: 1050000 Max output tokens: 128000 Input USD per million: 2 Output USD per million: 10 Input per token (published): 0.000002 Output per token (published): 0.00001 Batch input USD per million: 1 Batch output USD per million: 5 Other raw prices: web_search=0.01, input_cache_read=0.0000001, input_cache_write=0.0000025 Input modalities: file, image, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: required Third-party intelligence index: 57.3 Third-party coding index: unknown Guide: reviewed 2026-11-19 — OpenRouter positions GPT-6.2 Sol under Astra as the efficient model for everyday work. It is the reviewed default when you want a strong general model and do not need the flagship. Listing blurb: GPT-6.2 Sol is an upgrade to GPT-6.1 Sol from OpenAI, positioned below the flagship GPT-6.2 Astra in the GPT-6.2 series. It is an efficient, versatile model for everyday work, suited... Checked: 20 Nov 2026 ## GPT-6.2 Sol Pro Platform: OpenAI Id: openai/gpt-6.2-sol-pro URL: https://thebestmodelfor.com/models/openai--gpt-6.2-sol-pro OpenRouter: https://openrouter.ai/openai/gpt-6.2-sol-pro Kind: chat Listed: 2026-11-17 Context tokens: 1050000 Max output tokens: 128000 Input USD per million: 2 Output USD per million: 10 Input per token (published): 0.000002 Output per token (published): 0.00001 Batch input USD per million: 1 Batch output USD per million: 5 Other raw prices: web_search=0.01, input_cache_read=0.0000001, input_cache_write=0.0000025 Input modalities: file, image, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: required Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: GPT-6.2 Sol Pro is the same underlying model as GPT-6.2 Sol, served with reasoning.mode set to pro for higher-quality responses on complex tasks. Cost note: pro mode spends far more... Checked: 20 Nov 2026 ## GPT Audio Platform: OpenAI Id: openai/gpt-audio URL: https://thebestmodelfor.com/models/openai--gpt-audio OpenRouter: https://openrouter.ai/openai/gpt-audio Kind: speech Listed: 2026-01-19 Context tokens: 128000 Max output tokens: 16384 Input USD per million: 2.5 Output USD per million: 10 Input per token (published): 0.0000025 Output per token (published): 0.00001 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: audio=0.000032, audio_output=0.000064 Input modalities: audio, text Output modalities: audio, text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: reviewed 2026-11-19 — The feed lists audio in and audio out. OpenRouter describes GPT Audio as OpenAI's generally available audio model, with a decoder aimed at more natural speech. Use it when the product has to talk back, not only transcribe. Listing blurb: The gpt-audio model is OpenAI's first generally available audio model. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Audio is priced... Checked: 20 Nov 2026 ## GPT Audio Mini Platform: OpenAI Id: openai/gpt-audio-mini URL: https://thebestmodelfor.com/models/openai--gpt-audio-mini OpenRouter: https://openrouter.ai/openai/gpt-audio-mini Kind: speech Listed: 2026-01-19 Context tokens: 128000 Max output tokens: 16384 Input USD per million: 0.6 Output USD per million: 2.4 Input per token (published): 0.0000006 Output per token (published): 0.0000024 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: audio=0.0000006, audio_output=0.0000024 Input modalities: audio, text Output modalities: audio, text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: reviewed 2026-11-19 — GPT Audio Mini has the same listed shape as GPT Audio — text and audio in, text and audio out — at a lower published token rate. It is the budget pick when the model must speak. Listing blurb: A cost-efficient version of GPT Audio. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Input is priced at $0.60 per million... Checked: 20 Nov 2026 ## GPT Chat Latest Platform: OpenAI Id: openai/gpt-chat-latest URL: https://thebestmodelfor.com/models/openai--gpt-chat-latest OpenRouter: https://openrouter.ai/openai/gpt-chat-latest Kind: chat Listed: 2026-05-05 Context tokens: 400000 Max output tokens: 128000 Input USD per million: 5 Output USD per million: 30 Input per token (published): 0.000005 Output per token (published): 0.00003 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: web_search=0.01, input_cache_read=0.0000005 Input modalities: file, image, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: GPT Chat Latest points to OpenAI's stable API alias chat-latest that always resolves to the latest Instant chat model used in ChatGPT. As OpenAI rolls out new Instant model updates... Checked: 20 Nov 2026 ## GPT Image 1 Platform: OpenAI Id: openai/gpt-image-1 URL: https://thebestmodelfor.com/models/openai--gpt-image-1 OpenRouter: https://openrouter.ai/openai/gpt-image-1 Kind: image Listed: 2026-06-24 Context tokens: 400000 Max output tokens: 360000 Input USD per million: 10 Output USD per million: 10 Input per token (published): 0.00001 Output per token (published): 0.00001 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: image_output=0.00004, web_search=0.01, input_cache_read=0.00000125 Input modalities: image, text Output modalities: image Tools: Not listed Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: OpenAI's GPT Image 1 generates and edits images via the dedicated Images API. Features accurate text rendering, transparent backgrounds, and up to 16 reference images for edits. Checked: 20 Nov 2026 ## GPT Image 1 Mini Platform: OpenAI Id: openai/gpt-image-1-mini URL: https://thebestmodelfor.com/models/openai--gpt-image-1-mini OpenRouter: https://openrouter.ai/openai/gpt-image-1-mini Kind: image Listed: 2026-06-24 Context tokens: 400000 Max output tokens: 360000 Input USD per million: 2.5 Output USD per million: 2.5 Input per token (published): 0.0000025 Output per token (published): 0.0000025 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: image_output=0.000008, web_search=0.01, input_cache_read=0.00000025 Input modalities: image, text Output modalities: image Tools: Not listed Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: A cost-efficient variant of GPT Image 1 for high-quality image generation at reduced latency and cost via OpenAI's dedicated Images API. Checked: 20 Nov 2026 ## GPT Image 2 Platform: OpenAI Id: openai/gpt-image-2 URL: https://thebestmodelfor.com/models/openai--gpt-image-2 OpenRouter: https://openrouter.ai/openai/gpt-image-2 Kind: image Listed: 2026-06-24 Context tokens: 400000 Max output tokens: 360000 Input USD per million: 8 Output USD per million: 8 Input per token (published): 0.000008 Output per token (published): 0.000008 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: image_output=0.00003, web_search=0.01, input_cache_read=0.000002 Input modalities: image, text Output modalities: image Tools: Not listed Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: OpenAI's latest image generation model. Supports high-fidelity image generation and editing via the dedicated Images API. Checked: 20 Nov 2026 ## GPT Image 2.5 Flare Platform: OpenAI Id: openai/gpt-image-2.5-flare URL: https://thebestmodelfor.com/models/openai--gpt-image-2.5-flare OpenRouter: https://openrouter.ai/openai/gpt-image-2.5-flare Kind: image Listed: 2026-09-09 Context tokens: 400000 Max output tokens: 360000 Input USD per million: 8 Output USD per million: 8 Input per token (published): 0.000008 Output per token (published): 0.000008 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: image_output=0.00003, web_search=0.01, input_cache_read=0.000002 Input modalities: image, text Output modalities: image Tools: Not listed Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: GPT Image 2.5 Flare is an image generation and editing model from OpenAI, positioned as the speed-oriented tier of the GPT Image 2.5 series. It is suited to high-volume everyday... Checked: 20 Nov 2026 ## GPT Image 2.5 Sunburst Platform: OpenAI Id: openai/gpt-image-2.5-sunburst URL: https://thebestmodelfor.com/models/openai--gpt-image-2.5-sunburst OpenRouter: https://openrouter.ai/openai/gpt-image-2.5-sunburst Kind: image Listed: 2026-09-09 Context tokens: 400000 Max output tokens: 360000 Input USD per million: 8 Output USD per million: 8 Input per token (published): 0.000008 Output per token (published): 0.000008 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: image_output=0.00003, web_search=0.01, input_cache_read=0.000002 Input modalities: image, text Output modalities: image Tools: Not listed Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: GPT Image 2.5 Sunburst is an image generation and editing model from OpenAI, positioned as the precision-oriented tier of the GPT Image 2.5 series. It is suited to detailed creative... Checked: 20 Nov 2026 ## GPT Image 2.6 Flare Platform: OpenAI Id: openai/gpt-image-2.6-flare URL: https://thebestmodelfor.com/models/openai--gpt-image-2.6-flare OpenRouter: https://openrouter.ai/openai/gpt-image-2.6-flare Kind: image Listed: 2026-11-04 Context tokens: 400000 Max output tokens: 360000 Input USD per million: 8 Output USD per million: 8 Input per token (published): 0.000008 Output per token (published): 0.000008 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: image_output=0.00003, web_search=0.01, input_cache_read=0.000002, input_cache_write=0.00001 Input modalities: image, text Output modalities: image Tools: Not listed Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: GPT Image 2.6 Flare is OpenAI's image generation and editing model optimized for speed: fast iteration and interactive text-to-image and image-to-image workflows, generating about 50% faster than GPT Image 2.5.... Checked: 20 Nov 2026 ## GPT Image 2.6 Sunburst Platform: OpenAI Id: openai/gpt-image-2.6-sunburst URL: https://thebestmodelfor.com/models/openai--gpt-image-2.6-sunburst OpenRouter: https://openrouter.ai/openai/gpt-image-2.6-sunburst Kind: image Listed: 2026-11-04 Context tokens: 400000 Max output tokens: 360000 Input USD per million: 8 Output USD per million: 8 Input per token (published): 0.000008 Output per token (published): 0.000008 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: image_output=0.00003, web_search=0.01, input_cache_read=0.000002, input_cache_write=0.00001 Input modalities: image, text Output modalities: image Tools: Not listed Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: GPT Image 2.6 Sunburst is OpenAI's image generation and editing model optimized for detail: dense compositions, text-heavy layouts, and edits that keep details consistent from one edit to the next... Checked: 20 Nov 2026 ## gpt-oss-120b Platform: OpenAI Id: openai/gpt-oss-120b URL: https://thebestmodelfor.com/models/openai--gpt-oss-120b OpenRouter: https://openrouter.ai/openai/gpt-oss-120b Kind: chat Listed: 2025-08-05 Context tokens: 131072 Max output tokens: 117964 Input USD per million: 0.09 Output USD per million: 0.36 Input per token (published): 0.00000009 Output per token (published): 0.00000036 Batch input USD per million: 0.0296 Batch output USD per million: 0.136 Other raw prices: none Input modalities: text Output modalities: text Tools: Yes Open weights: Yes (openai/gpt-oss-120b) Knowledge cutoff: 2024-06-30 Reasoning: required Third-party intelligence index: 3.8 Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized... Checked: 20 Nov 2026 ## gpt-oss-20b Platform: OpenAI Id: openai/gpt-oss-20b URL: https://thebestmodelfor.com/models/openai--gpt-oss-20b OpenRouter: https://openrouter.ai/openai/gpt-oss-20b Kind: chat Listed: 2025-08-05 Context tokens: 131072 Max output tokens: 117964 Input USD per million: 0.018 Output USD per million: 0.09 Input per token (published): 0.000000018 Output per token (published): 0.00000009 Batch input USD per million: 0.024 Batch output USD per million: 0.112 Other raw prices: input_cache_read=0.000000009 Input modalities: text Output modalities: text Tools: Yes Open weights: Yes (openai/gpt-oss-20b) Knowledge cutoff: 2024-06-30 Reasoning: required Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for... Checked: 20 Nov 2026 ## gpt-oss-safeguard-20b Platform: OpenAI Id: openai/gpt-oss-safeguard-20b URL: https://thebestmodelfor.com/models/openai--gpt-oss-safeguard-20b OpenRouter: https://openrouter.ai/openai/gpt-oss-safeguard-20b Kind: chat Listed: 2025-10-29 Context tokens: 131072 Max output tokens: 65536 Input USD per million: 0.075 Output USD per million: 0.3 Input per token (published): 0.000000075 Output per token (published): 0.0000003 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: input_cache_read=0.0000000375 Input modalities: text Output modalities: text Tools: Yes Open weights: Yes (openai/gpt-oss-safeguard-20b) Knowledge cutoff: unknown Reasoning: required Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: gpt-oss-safeguard-20b is a safety reasoning model from OpenAI built upon gpt-oss-20b. This open-weight, 21B-parameter Mixture-of-Experts (MoE) model offers lower latency for safety tasks like content classification, LLM filtering, and trust... Checked: 20 Nov 2026 ## GPT Transcribe Platform: OpenAI Id: openai/gpt-transcribe URL: https://thebestmodelfor.com/models/openai--gpt-transcribe OpenRouter: https://openrouter.ai/openai/gpt-transcribe Kind: transcription Listed: 2026-08-05 Context tokens: unknown Max output tokens: unknown Input USD per million: 75 Output USD per million: 0 Input per token (published): 0.000075 Output per token (published): 0 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: audio Output modalities: transcription Tools: Not listed Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: GPT Transcribe is a high-accuracy speech-to-text model from OpenAI. It is suited for recorded audio, streamed file transcription, and committed Realtime turns, with free-form context, keyword hints, and multiple language... Checked: 20 Nov 2026 ## o3 Platform: OpenAI Id: openai/o3 URL: https://thebestmodelfor.com/models/openai--o3 OpenRouter: https://openrouter.ai/openai/o3 Kind: chat Listed: 2025-04-16 Context tokens: 200000 Max output tokens: 100000 Input USD per million: 2 Output USD per million: 8 Input per token (published): 0.000002 Output per token (published): 0.000008 Batch input USD per million: 1 Batch output USD per million: 4 Other raw prices: web_search=0.01, input_cache_read=0.0000005 Input modalities: file, image, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: 2024-06-30 Reasoning: required Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following.... Checked: 20 Nov 2026 ## o3 Pro Platform: OpenAI Id: openai/o3-pro URL: https://thebestmodelfor.com/models/openai--o3-pro OpenRouter: https://openrouter.ai/openai/o3-pro Kind: chat Listed: 2025-06-10 Context tokens: 200000 Max output tokens: 100000 Input USD per million: 20 Output USD per million: 80 Input per token (published): 0.00002 Output per token (published): 0.00008 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: web_search=0.01 Input modalities: file, image, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: 2024-06-30 Reasoning: required Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: The o-series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o3-pro model uses more compute to think harder and provide consistently... Checked: 20 Nov 2026 ## Text Embedding 3 Large Platform: OpenAI Id: openai/text-embedding-3-large URL: https://thebestmodelfor.com/models/openai--text-embedding-3-large OpenRouter: https://openrouter.ai/openai/text-embedding-3-large Kind: embeddings Listed: 2025-10-30 Context tokens: 8192 Max output tokens: 7372 Input USD per million: 0.13 Output USD per million: 0 Input per token (published): 0.00000013 Output per token (published): 0 Batch input USD per million: 0.065 Batch output USD per million: 0 Other raw prices: none Input modalities: text Output modalities: embeddings Tools: Not listed Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: text-embedding-3-large is OpenAI's most capable embedding model for both english and non-english tasks. Embeddings are a numerical representation of text that can be used to measure the relatedness between two... Checked: 20 Nov 2026 ## Text Embedding 3 Small Platform: OpenAI Id: openai/text-embedding-3-small URL: https://thebestmodelfor.com/models/openai--text-embedding-3-small OpenRouter: https://openrouter.ai/openai/text-embedding-3-small Kind: embeddings Listed: 2025-10-30 Context tokens: 8192 Max output tokens: 7372 Input USD per million: 0.02 Output USD per million: 0 Input per token (published): 0.00000002 Output per token (published): 0 Batch input USD per million: 0.01 Batch output USD per million: 0 Other raw prices: none Input modalities: text Output modalities: embeddings Tools: Not listed Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: text-embedding-3-small is OpenAI's improved, more performant version of the ada embedding model. Embeddings are a numerical representation of text that can be used to measure the relatedness between two pieces... Checked: 20 Nov 2026 ## Text Embedding Ada 002 Platform: OpenAI Id: openai/text-embedding-ada-002 URL: https://thebestmodelfor.com/models/openai--text-embedding-ada-002 OpenRouter: https://openrouter.ai/openai/text-embedding-ada-002 Kind: embeddings Listed: 2025-10-30 Context tokens: 8192 Max output tokens: 7372 Input USD per million: 0.1 Output USD per million: 0 Input per token (published): 0.0000001 Output per token (published): 0 Batch input USD per million: 0.05 Batch output USD per million: 0 Other raw prices: none Input modalities: text Output modalities: embeddings Tools: Not listed Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: text-embedding-ada-002 is OpenAI's legacy text embedding model. Checked: 20 Nov 2026 ## Whisper 1 Platform: OpenAI Id: openai/whisper-1 URL: https://thebestmodelfor.com/models/openai--whisper-1 OpenRouter: https://openrouter.ai/openai/whisper-1 Kind: transcription Listed: 2026-04-27 Context tokens: unknown Max output tokens: unknown Input USD per million: 100 Output USD per million: 0 Input per token (published): 0.0001 Output per token (published): 0 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: audio Output modalities: transcription Tools: Not listed Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Whisper is OpenAI's open-source automatic speech recognition model, available via API as whisper-1. It supports transcription and translation across 50+ languages from audio files up to 25 MB. Accepts formats... Checked: 20 Nov 2026 ## Whisper Large V3 Platform: OpenAI Id: openai/whisper-large-v3 URL: https://thebestmodelfor.com/models/openai--whisper-large-v3 OpenRouter: https://openrouter.ai/openai/whisper-large-v3 Kind: transcription Listed: 2026-05-01 Context tokens: unknown Max output tokens: unknown Input USD per million: 7.5 Output USD per million: 0 Input per token (published): 0.0000075 Output per token (published): 0 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: audio Output modalities: transcription Tools: Not listed Open weights: Yes (openai/whisper-large-v3) Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Whisper Large V3 is OpenAI's open-source automatic speech recognition model offering both audio transcription and translation. It supports 99+ languages and accepts common audio formats including mp3, mp4, wav, webm,... Checked: 20 Nov 2026 ## Whisper Large V3 Turbo Platform: OpenAI Id: openai/whisper-large-v3-turbo URL: https://thebestmodelfor.com/models/openai--whisper-large-v3-turbo OpenRouter: https://openrouter.ai/openai/whisper-large-v3-turbo Kind: transcription Listed: 2026-05-01 Context tokens: unknown Max output tokens: unknown Input USD per million: 3.33 Output USD per million: 0 Input per token (published): 0.00000333 Output per token (published): 0 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: audio Output modalities: transcription Tools: Not listed Open weights: Yes (openai/whisper-large-v3-turbo) Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Whisper Large V3 Turbo is an optimized version of OpenAI's Whisper Large V3 speech recognition model, designed for speed and cost efficiency. It supports transcription across 99+ languages with a... Checked: 20 Nov 2026 ## Claude Fable 5 Platform: Anthropic Id: anthropic/claude-fable-5 URL: https://thebestmodelfor.com/models/anthropic--claude-fable-5 OpenRouter: https://openrouter.ai/anthropic/claude-fable-5 Kind: chat Listed: 2026-06-09 Context tokens: 1000000 Max output tokens: 128000 Input USD per million: 10 Output USD per million: 50 Input per token (published): 0.00001 Output per token (published): 0.00005 Batch input USD per million: 5 Batch output USD per million: 25 Other raw prices: web_search=0.01, input_cache_read=0.000001, input_cache_write=0.0000125, input_cache_write_1h=0.00002 Input modalities: file, image, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: required Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and... Checked: 20 Nov 2026 ## Claude Fable 5.1 Platform: Anthropic Id: anthropic/claude-fable-5.1 URL: https://thebestmodelfor.com/models/anthropic--claude-fable-5.1 OpenRouter: https://openrouter.ai/anthropic/claude-fable-5.1 Kind: chat Listed: 2026-09-01 Context tokens: 1000000 Max output tokens: 128000 Input USD per million: 10 Output USD per million: 50 Input per token (published): 0.00001 Output per token (published): 0.00005 Batch input USD per million: 5 Batch output USD per million: 25 Other raw prices: web_search=0.01, input_cache_read=0.00000025, input_cache_write=0.0000125, input_cache_write_1h=0.00002 Input modalities: file, image, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: required Third-party intelligence index: 50 Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work: long code refactors, front-end and visual... Checked: 20 Nov 2026 ## Claude Fable 5.2 Platform: Anthropic Id: anthropic/claude-fable-5.2 URL: https://thebestmodelfor.com/models/anthropic--claude-fable-5.2 OpenRouter: https://openrouter.ai/anthropic/claude-fable-5.2 Kind: chat Listed: 2026-11-09 Context tokens: 1000000 Max output tokens: 128000 Input USD per million: 8 Output USD per million: 40 Input per token (published): 0.000008 Output per token (published): 0.00004 Batch input USD per million: 4 Batch output USD per million: 20 Other raw prices: web_search=0.01, input_cache_read=0.0000002, input_cache_write=0.00001, input_cache_write_1h=0.000016 Input modalities: file, image, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: required Third-party intelligence index: 64.6 Third-party coding index: unknown Guide: reviewed 2026-11-19 — OpenRouter calls Claude Fable 5.2 Anthropic's most capable model for demanding technical work, with gains in coding, reasoning, and vision over Fable 5.1. It is the model to spend money on when the problem is actually hard. Listing blurb: Claude Fable 5.2 is Anthropic's most capable model for the most demanding technical work, with gains over Fable 5.1 in coding, reasoning, and vision. In prerelease testing it completed otherwise-infeasible... Checked: 20 Nov 2026 ## Claude Haiku 4.5 Platform: Anthropic Id: anthropic/claude-haiku-4.5 URL: https://thebestmodelfor.com/models/anthropic--claude-haiku-4.5 OpenRouter: https://openrouter.ai/anthropic/claude-haiku-4.5 Kind: chat Listed: 2025-10-15 Context tokens: 200000 Max output tokens: 64000 Input USD per million: 1 Output USD per million: 5 Input per token (published): 0.000001 Output per token (published): 0.000005 Batch input USD per million: 0.5 Batch output USD per million: 2.5 Other raw prices: web_search=0.01, input_cache_read=0.0000001, input_cache_write=0.00000125, input_cache_write_1h=0.000002 Input modalities: file, image, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: optional Third-party intelligence index: 7.4 Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance... Checked: 20 Nov 2026 ## Claude Haiku 5.5 Platform: Anthropic Id: anthropic/claude-haiku-5.5 URL: https://thebestmodelfor.com/models/anthropic--claude-haiku-5.5 OpenRouter: https://openrouter.ai/anthropic/claude-haiku-5.5 Kind: chat Listed: 2026-10-07 Context tokens: 1000000 Max output tokens: 128000 Input USD per million: 0.1 Output USD per million: 0.5 Input per token (published): 0.0000001 Output per token (published): 0.0000005 Batch input USD per million: 0.05 Batch output USD per million: 0.25 Other raw prices: web_search=0.01, input_cache_read=0.00000001, input_cache_write=0.000000125, input_cache_write_1h=0.0000002 Input modalities: file, image, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: optional Third-party intelligence index: 36.5 Third-party coding index: unknown Guide: reviewed 2026-11-19 — OpenRouter describes Claude Haiku 5.5 as Anthropic's small, fast model for high-volume work such as summarisation, subagents, and browser use. Stronger than Haiku 4.5 at coding, on the listing's own words, and far cheaper than Sonnet. Listing blurb: Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. It succeeds Claude Haiku 4.5 with stronger coding, computer use, and... Checked: 20 Nov 2026 ## Claude Opus 4.1 Platform: Anthropic Id: anthropic/claude-opus-4.1 URL: https://thebestmodelfor.com/models/anthropic--claude-opus-4.1 OpenRouter: https://openrouter.ai/anthropic/claude-opus-4.1 Kind: chat Listed: 2025-08-05 Context tokens: 200000 Max output tokens: 32000 Input USD per million: 15 Output USD per million: 75 Input per token (published): 0.000015 Output per token (published): 0.000075 Batch input USD per million: 7.5 Batch output USD per million: 37.5 Other raw prices: web_search=0.01, input_cache_read=0.0000015, input_cache_write=0.00001875, input_cache_write_1h=0.00003 Input modalities: file, image, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: 2025-01-31 Reasoning: optional Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks. It achieves 74.5% on SWE-bench Verified and shows notable gains... Checked: 20 Nov 2026 ## Claude Opus 4.5 Platform: Anthropic Id: anthropic/claude-opus-4.5 URL: https://thebestmodelfor.com/models/anthropic--claude-opus-4.5 OpenRouter: https://openrouter.ai/anthropic/claude-opus-4.5 Kind: chat Listed: 2025-11-24 Context tokens: 200000 Max output tokens: 64000 Input USD per million: 5 Output USD per million: 25 Input per token (published): 0.000005 Output per token (published): 0.000025 Batch input USD per million: 2.5 Batch output USD per million: 12.5 Other raw prices: web_search=0.01, input_cache_read=0.0000005, input_cache_write=0.00000625, input_cache_write_1h=0.00001 Input modalities: file, image, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: optional Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and... Checked: 20 Nov 2026 ## Claude Opus 4.6 Platform: Anthropic Id: anthropic/claude-opus-4.6 URL: https://thebestmodelfor.com/models/anthropic--claude-opus-4.6 OpenRouter: https://openrouter.ai/anthropic/claude-opus-4.6 Kind: chat Listed: 2026-02-04 Context tokens: 1000000 Max output tokens: 128000 Input USD per million: 5 Output USD per million: 25 Input per token (published): 0.000005 Output per token (published): 0.000025 Batch input USD per million: 2.5 Batch output USD per million: 12.5 Other raw prices: web_search=0.01, input_cache_read=0.0000005, input_cache_write=0.00000625, input_cache_write_1h=0.00001 Input modalities: file, image, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: optional Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective... Checked: 20 Nov 2026 ## Claude Opus 4.7 Platform: Anthropic Id: anthropic/claude-opus-4.7 URL: https://thebestmodelfor.com/models/anthropic--claude-opus-4.7 OpenRouter: https://openrouter.ai/anthropic/claude-opus-4.7 Kind: chat Listed: 2026-04-16 Context tokens: 1000000 Max output tokens: 128000 Input USD per million: 5 Output USD per million: 25 Input per token (published): 0.000005 Output per token (published): 0.000025 Batch input USD per million: 2.5 Batch output USD per million: 12.5 Other raw prices: web_search=0.01, input_cache_read=0.0000005, input_cache_write=0.00000625, input_cache_write_1h=0.00001 Input modalities: file, image, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: optional Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers stronger performance on... Checked: 20 Nov 2026 ## Claude Opus 4.8 Platform: Anthropic Id: anthropic/claude-opus-4.8 URL: https://thebestmodelfor.com/models/anthropic--claude-opus-4.8 OpenRouter: https://openrouter.ai/anthropic/claude-opus-4.8 Kind: chat Listed: 2026-05-27 Context tokens: 1000000 Max output tokens: 128000 Input USD per million: 5 Output USD per million: 25 Input per token (published): 0.000005 Output per token (published): 0.000025 Batch input USD per million: 2.5 Batch output USD per million: 12.5 Other raw prices: web_search=0.01, input_cache_read=0.0000005, input_cache_write=0.00000625, input_cache_write_1h=0.00001 Input modalities: file, image, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: optional Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token... Checked: 20 Nov 2026 ## Claude Opus 5 Platform: Anthropic Id: anthropic/claude-opus-5 URL: https://thebestmodelfor.com/models/anthropic--claude-opus-5 OpenRouter: https://openrouter.ai/anthropic/claude-opus-5 Kind: chat Listed: 2026-07-24 Context tokens: 1000000 Max output tokens: 128000 Input USD per million: 5 Output USD per million: 25 Input per token (published): 0.000005 Output per token (published): 0.000025 Batch input USD per million: 2.5 Batch output USD per million: 12.5 Other raw prices: web_search=0.01, input_cache_read=0.0000005, input_cache_write=0.00000625, input_cache_write_1h=0.00001 Input modalities: file, image, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: optional Third-party intelligence index: 44.2 Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis... Checked: 20 Nov 2026 ## Claude Opus 5.5 Platform: Anthropic Id: anthropic/claude-opus-5.5 URL: https://thebestmodelfor.com/models/anthropic--claude-opus-5.5 OpenRouter: https://openrouter.ai/anthropic/claude-opus-5.5 Kind: chat Listed: 2026-09-22 Context tokens: 1000000 Max output tokens: 128000 Input USD per million: 4 Output USD per million: 20 Input per token (published): 0.000004 Output per token (published): 0.00002 Batch input USD per million: 2 Batch output USD per million: 10 Other raw prices: web_search=0.01, input_cache_read=0.0000002, input_cache_write=0.000005, input_cache_write_1h=0.000008 Input modalities: file, image, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: required Third-party intelligence index: 59.1 Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. It is particularly strong at multi-step changes in large codebases, code... Checked: 20 Nov 2026 ## Claude Sonnet 4.5 Platform: Anthropic Id: anthropic/claude-sonnet-4.5 URL: https://thebestmodelfor.com/models/anthropic--claude-sonnet-4.5 OpenRouter: https://openrouter.ai/anthropic/claude-sonnet-4.5 Kind: chat Listed: 2025-09-29 Context tokens: 1000000 Max output tokens: 64000 Input USD per million: 3 Output USD per million: 15 Input per token (published): 0.000003 Output per token (published): 0.000015 Batch input USD per million: 1.5 Batch output USD per million: 7.5 Other raw prices: web_search=0.01, input_cache_read=0.0000003, input_cache_write=0.00000375, input_cache_write_1h=0.000006 Input modalities: file, image, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: 2025-01-31 Reasoning: optional Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with... Checked: 20 Nov 2026 ## Claude Sonnet 4.6 Platform: Anthropic Id: anthropic/claude-sonnet-4.6 URL: https://thebestmodelfor.com/models/anthropic--claude-sonnet-4.6 OpenRouter: https://openrouter.ai/anthropic/claude-sonnet-4.6 Kind: chat Listed: 2026-02-17 Context tokens: 1000000 Max output tokens: 128000 Input USD per million: 3 Output USD per million: 15 Input per token (published): 0.000003 Output per token (published): 0.000015 Batch input USD per million: 1.5 Batch output USD per million: 7.5 Other raw prices: web_search=0.01, input_cache_read=0.0000003, input_cache_write=0.00000375, input_cache_write_1h=0.000006 Input modalities: file, image, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: optional Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with... Checked: 20 Nov 2026 ## Claude Sonnet 5 Platform: Anthropic Id: anthropic/claude-sonnet-5 URL: https://thebestmodelfor.com/models/anthropic--claude-sonnet-5 OpenRouter: https://openrouter.ai/anthropic/claude-sonnet-5 Kind: chat Listed: 2026-06-30 Context tokens: 1000000 Max output tokens: 128000 Input USD per million: 2 Output USD per million: 10 Input per token (published): 0.000002 Output per token (published): 0.00001 Batch input USD per million: 1 Batch output USD per million: 5 Other raw prices: web_search=0.01, input_cache_read=0.0000002, input_cache_write=0.0000025, input_cache_write_1h=0.000004 Input modalities: file, image, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: optional Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max,... Checked: 20 Nov 2026 ## Claude Sonnet 5.5 Platform: Anthropic Id: anthropic/claude-sonnet-5.5 URL: https://thebestmodelfor.com/models/anthropic--claude-sonnet-5.5 OpenRouter: https://openrouter.ai/anthropic/claude-sonnet-5.5 Kind: chat Listed: 2026-09-28 Context tokens: 1000000 Max output tokens: 128000 Input USD per million: 2 Output USD per million: 10 Input per token (published): 0.000002 Output per token (published): 0.00001 Batch input USD per million: 1 Batch output USD per million: 5 Other raw prices: web_search=0.01, input_cache_read=0.0000001, input_cache_write=0.0000025, input_cache_write_1h=0.000004 Input modalities: file, image, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: required Third-party intelligence index: 54.5 Third-party coding index: unknown Guide: reviewed 2026-11-19 — OpenRouter describes Claude Sonnet 5.5 as the Sonnet-class model for well-scoped everyday work, especially building features, fixing bugs, and producing finished text. It is the reviewed default for most coding and writing. Listing blurb: Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade. It is especially strong at building features, fixing bugs, and producing... Checked: 20 Nov 2026 ## Chirp 3 Platform: Google (Gemini) Id: google/chirp-3 URL: https://thebestmodelfor.com/models/google--chirp-3 OpenRouter: https://openrouter.ai/google/chirp-3 Kind: transcription Listed: 2026-05-05 Context tokens: unknown Max output tokens: unknown Input USD per million: 266.666666667 Output USD per million: 0 Input per token (published): 0.000266666666667 Output per token (published): 0 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: audio Output modalities: transcription Tools: Not listed Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Chirp 3 is Google's latest multilingual speech-to-text model. It offers enhanced transcription accuracy across 24 GA languages and 77+ preview languages, with support for automatic language detection, automatic punctuation, and... Checked: 20 Nov 2026 ## Gemini 2.5 Flash Platform: Google (Gemini) Id: google/gemini-2.5-flash URL: https://thebestmodelfor.com/models/google--gemini-2.5-flash OpenRouter: https://openrouter.ai/google/gemini-2.5-flash Kind: chat Listed: 2025-06-17 Context tokens: 1048576 Max output tokens: 65535 Input USD per million: 0.3 Output USD per million: 2.5 Input per token (published): 0.0000003 Output per token (published): 0.0000025 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: image=0.0000003, audio=0.000001, input_audio_cache=0.0000001, web_search=0.014, internal_reasoning=0.0000025, input_cache_read=0.00000003, input_cache_write=0.0000000833333333333333 Input modalities: audio, file, image, text, video Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: 2025-01-31 Reasoning: optional Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in "thinking" capabilities, enabling it to provide responses with greater... Checked: 20 Nov 2026 ## Nano Banana (Gemini 2.5 Flash Image) Platform: Google (Gemini) Id: google/gemini-2.5-flash-image URL: https://thebestmodelfor.com/models/google--gemini-2.5-flash-image OpenRouter: https://openrouter.ai/google/gemini-2.5-flash-image Kind: image Listed: 2025-10-07 Context tokens: 32768 Max output tokens: 8192 Input USD per million: 0.3 Output USD per million: 2.5 Input per token (published): 0.0000003 Output per token (published): 0.0000025 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: image=0.0000003, image_output=0.00003, audio=0.000001, input_audio_cache=0.0000001, web_search=0.014, internal_reasoning=0.0000025, input_cache_read=0.00000003, input_cache_write=0.0000000833333333333333 Input modalities: image, text Output modalities: image, text Tools: Not listed Open weights: No public weights id listed Knowledge cutoff: 2025-01-31 Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Gemini 2.5 Flash Image, a.k.a. "Nano Banana," is now generally available. It is a state of the art image generation model with contextual understanding. It is capable of image generation,... Checked: 20 Nov 2026 ## Gemini 2.5 Flash Lite Platform: Google (Gemini) Id: google/gemini-2.5-flash-lite URL: https://thebestmodelfor.com/models/google--gemini-2.5-flash-lite OpenRouter: https://openrouter.ai/google/gemini-2.5-flash-lite Kind: chat Listed: 2025-07-22 Context tokens: 1048576 Max output tokens: 65535 Input USD per million: 0.1 Output USD per million: 0.4 Input per token (published): 0.0000001 Output per token (published): 0.0000004 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: image=0.0000001, audio=0.0000003, input_audio_cache=0.00000003, web_search=0.014, internal_reasoning=0.0000004, input_cache_read=0.00000001, input_cache_write=0.0000000833333333333333 Input modalities: audio, file, image, text, video Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: 2025-01-31 Reasoning: optional Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance... Checked: 20 Nov 2026 ## Gemini 2.5 Flash TTS Platform: Google (Gemini) Id: google/gemini-2.5-flash-tts URL: https://thebestmodelfor.com/models/google--gemini-2.5-flash-tts OpenRouter: https://openrouter.ai/google/gemini-2.5-flash-tts Kind: speech Listed: 2026-11-20 Context tokens: 8192 Max output tokens: 7372 Input USD per million: 0.5 Output USD per million: 10 Input per token (published): 0.0000005 Output per token (published): 0.00001 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: text Output modalities: speech Tools: Not listed Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Gemini 2.5 Flash TTS is a text-to-speech model from Google. It turns text into single-speaker or multi-speaker audio, with style, pace, and tone steered by natural-language instructions in the prompt,... Checked: 20 Nov 2026 ## Gemini 2.5 Pro Platform: Google (Gemini) Id: google/gemini-2.5-pro URL: https://thebestmodelfor.com/models/google--gemini-2.5-pro OpenRouter: https://openrouter.ai/google/gemini-2.5-pro Kind: chat Listed: 2025-06-17 Context tokens: 1048576 Max output tokens: 65536 Input USD per million: 1.25 Output USD per million: 10 Input per token (published): 0.00000125 Output per token (published): 0.00001 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: image=0.00000125, audio=0.00000125, input_audio_cache=0.000000125, web_search=0.014, internal_reasoning=0.00001, input_cache_read=0.000000125, input_cache_write=0.000000375 Input modalities: audio, file, image, text, video Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: 2025-01-31 Reasoning: required Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy... Checked: 20 Nov 2026 ## Gemini 2.5 Pro Preview 06-05 Platform: Google (Gemini) Id: google/gemini-2.5-pro-preview URL: https://thebestmodelfor.com/models/google--gemini-2.5-pro-preview OpenRouter: https://openrouter.ai/google/gemini-2.5-pro-preview Kind: chat Listed: 2025-06-05 Context tokens: 1048576 Max output tokens: 65536 Input USD per million: 1.25 Output USD per million: 10 Input per token (published): 0.00000125 Output per token (published): 0.00001 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: image=0.00000125, audio=0.00000125, input_audio_cache=0.000000125, web_search=0.014, internal_reasoning=0.00001, input_cache_read=0.000000125, input_cache_write=0.000000375 Input modalities: audio, file, image, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: 2025-01-31 Reasoning: required Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy... Checked: 20 Nov 2026 ## Gemini 2.5 Pro TTS Platform: Google (Gemini) Id: google/gemini-2.5-pro-tts URL: https://thebestmodelfor.com/models/google--gemini-2.5-pro-tts OpenRouter: https://openrouter.ai/google/gemini-2.5-pro-tts Kind: speech Listed: 2026-11-20 Context tokens: 8192 Max output tokens: 7372 Input USD per million: 1 Output USD per million: 20 Input per token (published): 0.000001 Output per token (published): 0.00002 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: text Output modalities: speech Tools: Not listed Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Gemini 2.5 Pro TTS is a text-to-speech model from Google. It turns text into single-speaker or multi-speaker audio, with style, pace, and tone steered by natural-language instructions in the prompt,... Checked: 20 Nov 2026 ## Gemini 3 Flash Preview Platform: Google (Gemini) Id: google/gemini-3-flash-preview URL: https://thebestmodelfor.com/models/google--gemini-3-flash-preview OpenRouter: https://openrouter.ai/google/gemini-3-flash-preview Kind: chat Listed: 2025-12-17 Context tokens: 1048576 Max output tokens: 65536 Input USD per million: 0.5 Output USD per million: 3 Input per token (published): 0.0000005 Output per token (published): 0.000003 Batch input USD per million: 0.25 Batch output USD per million: 1.5 Other raw prices: image=0.0000005, audio=0.000001, input_audio_cache=0.0000001, web_search=0.014, internal_reasoning=0.000003, input_cache_read=0.00000005, input_cache_write=0.0000000833333333333333 Input modalities: audio, file, image, text, video Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: optional Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It delivers near Pro level reasoning and tool... Checked: 20 Nov 2026 ## Nano Banana Pro (Gemini 3 Pro Image) Platform: Google (Gemini) Id: google/gemini-3-pro-image URL: https://thebestmodelfor.com/models/google--gemini-3-pro-image OpenRouter: https://openrouter.ai/google/gemini-3-pro-image Kind: image Listed: 2026-06-18 Context tokens: 131072 Max output tokens: 32768 Input USD per million: 2 Output USD per million: 12 Input per token (published): 0.000002 Output per token (published): 0.000012 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: image=0.000002, image_output=0.00012, audio=0.000002, input_audio_cache=0.0000002, web_search=0.014, internal_reasoning=0.000012, input_cache_read=0.0000002, input_cache_write=0.000000375 Input modalities: image, text Output modalities: image, text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: required Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and... Checked: 20 Nov 2026 ## Nano Banana Pro (Gemini 3 Pro Image Preview) Platform: Google (Gemini) Id: google/gemini-3-pro-image-preview URL: https://thebestmodelfor.com/models/google--gemini-3-pro-image-preview OpenRouter: https://openrouter.ai/google/gemini-3-pro-image-preview Kind: image Listed: 2025-11-20 Context tokens: 65536 Max output tokens: 32768 Input USD per million: 2 Output USD per million: 12 Input per token (published): 0.000002 Output per token (published): 0.000012 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: image=0.000002, image_output=0.00012, audio=0.000002, input_audio_cache=0.0000002, web_search=0.014, internal_reasoning=0.000012, input_cache_read=0.0000002, input_cache_write=0.000000375 Input modalities: image, text Output modalities: image, text Tools: Not listed Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: required Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and... Checked: 20 Nov 2026 ## Nano Banana 2 (Gemini 3.1 Flash Image) Platform: Google (Gemini) Id: google/gemini-3.1-flash-image URL: https://thebestmodelfor.com/models/google--gemini-3.1-flash-image OpenRouter: https://openrouter.ai/google/gemini-3.1-flash-image Kind: image Listed: 2026-06-18 Context tokens: 131072 Max output tokens: 32768 Input USD per million: 0.5 Output USD per million: 3 Input per token (published): 0.0000005 Output per token (published): 0.000003 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: image_output=0.00006, web_search=0.014 Input modalities: image, text Output modalities: image, text Tools: Not listed Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: optional Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Gemini 3.1 Flash Image, a.k.a. "Nano Banana 2," is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines advanced... Checked: 20 Nov 2026 ## Nano Banana 2 (Gemini 3.1 Flash Image Preview) Platform: Google (Gemini) Id: google/gemini-3.1-flash-image-preview URL: https://thebestmodelfor.com/models/google--gemini-3.1-flash-image-preview OpenRouter: https://openrouter.ai/google/gemini-3.1-flash-image-preview Kind: image Listed: 2026-02-26 Context tokens: 65536 Max output tokens: 58982 Input USD per million: 0.5 Output USD per million: 3 Input per token (published): 0.0000005 Output per token (published): 0.000003 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: image_output=0.00006, web_search=0.014 Input modalities: image, text Output modalities: image, text Tools: Not listed Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: optional Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Gemini 3.1 Flash Image Preview, a.k.a. "Nano Banana 2," is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines... Checked: 20 Nov 2026 ## Gemini 3.1 Flash Lite Platform: Google (Gemini) Id: google/gemini-3.1-flash-lite URL: https://thebestmodelfor.com/models/google--gemini-3.1-flash-lite OpenRouter: https://openrouter.ai/google/gemini-3.1-flash-lite Kind: chat Listed: 2026-05-07 Context tokens: 1048576 Max output tokens: 65536 Input USD per million: 0.25 Output USD per million: 1.5 Input per token (published): 0.00000025 Output per token (published): 0.0000015 Batch input USD per million: 0.125 Batch output USD per million: 0.75 Other raw prices: image=0.00000025, audio=0.0000005, input_audio_cache=0.00000005, web_search=0.014, internal_reasoning=0.0000015, input_cache_read=0.000000025, input_cache_write=0.0000000833333333333333 Input modalities: audio, file, image, text, video Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: optional Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads. It supports text, image, video, audio, and PDF inputs, and is designed for lightweight agentic... Checked: 20 Nov 2026 ## Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) Platform: Google (Gemini) Id: google/gemini-3.1-flash-lite-image URL: https://thebestmodelfor.com/models/google--gemini-3.1-flash-lite-image OpenRouter: https://openrouter.ai/google/gemini-3.1-flash-lite-image Kind: image Listed: 2026-06-30 Context tokens: 65536 Max output tokens: 58982 Input USD per million: 0.25 Output USD per million: 1.5 Input per token (published): 0.00000025 Output per token (published): 0.0000015 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: image_output=0.00003, web_search=0.014 Input modalities: image, text Output modalities: image, text Tools: Not listed Open weights: No public weights id listed Knowledge cutoff: 2025-01-01 Reasoning: optional Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) is Google's fastest, most cost-efficient Gemini image model, built for high-velocity developer pipelines and rapid-fire visual exploration. It delivers text-to-image generation... Checked: 20 Nov 2026 ## Gemini 3.1 Flash Lite Preview Platform: Google (Gemini) Id: google/gemini-3.1-flash-lite-preview URL: https://thebestmodelfor.com/models/google--gemini-3.1-flash-lite-preview OpenRouter: https://openrouter.ai/google/gemini-3.1-flash-lite-preview Kind: chat Listed: 2026-03-03 Context tokens: 1048576 Max output tokens: 65536 Input USD per million: 0.25 Output USD per million: 1.5 Input per token (published): 0.00000025 Output per token (published): 0.0000015 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: image=0.00000025, audio=0.0000005, input_audio_cache=0.00000005, web_search=0.014, internal_reasoning=0.0000015, input_cache_read=0.000000025, input_cache_write=0.0000000833333333333333 Input modalities: audio, file, image, text, video Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: optional Third-party intelligence index: 6.2 Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Gemini 3.1 Flash Lite Preview is Google's high-efficiency model optimized for high-volume use cases. It outperforms Gemini 2.5 Flash Lite on overall quality and approaches Gemini 2.5 Flash performance across... Checked: 20 Nov 2026 ## Gemini 3.1 Flash TTS Preview Platform: Google (Gemini) Id: google/gemini-3.1-flash-tts-preview URL: https://thebestmodelfor.com/models/google--gemini-3.1-flash-tts-preview OpenRouter: https://openrouter.ai/google/gemini-3.1-flash-tts-preview Kind: speech Listed: 2026-04-24 Context tokens: 32768 Max output tokens: 16384 Input USD per million: 1 Output USD per million: 20 Input per token (published): 0.000001 Output per token (published): 0.00002 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: text Output modalities: speech Tools: Not listed Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Gemini 3.1 Flash TTS Preview is a text-to-speech model from Google, and a substantial generational step up from Gemini 2.5 Flash TTS. It takes text input and produces audio output... Checked: 20 Nov 2026 ## Gemini 3.1 Pro Preview Platform: Google (Gemini) Id: google/gemini-3.1-pro-preview URL: https://thebestmodelfor.com/models/google--gemini-3.1-pro-preview OpenRouter: https://openrouter.ai/google/gemini-3.1-pro-preview Kind: chat Listed: 2026-02-19 Context tokens: 1048576 Max output tokens: 65536 Input USD per million: 2 Output USD per million: 12 Input per token (published): 0.000002 Output per token (published): 0.000012 Batch input USD per million: 1 Batch output USD per million: 6 Other raw prices: image=0.000002, audio=0.000002, input_audio_cache=0.0000002, web_search=0.014, internal_reasoning=0.000012, input_cache_read=0.0000002, input_cache_write=0.000000375 Input modalities: audio, file, image, text, video Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: required Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows. Building on the multimodal foundation... Checked: 20 Nov 2026 ## Gemini 3.1 Pro Preview Custom Tools Platform: Google (Gemini) Id: google/gemini-3.1-pro-preview-customtools URL: https://thebestmodelfor.com/models/google--gemini-3.1-pro-preview-customtools OpenRouter: https://openrouter.ai/google/gemini-3.1-pro-preview-customtools Kind: chat Listed: 2026-02-25 Context tokens: 1048576 Max output tokens: 65536 Input USD per million: 2 Output USD per million: 12 Input per token (published): 0.000002 Output per token (published): 0.000012 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: image=0.000002, audio=0.000002, input_audio_cache=0.0000002, web_search=0.014, internal_reasoning=0.000012, input_cache_read=0.0000002, input_cache_write=0.000000375 Input modalities: audio, file, image, text, video Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: required Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Gemini 3.1 Pro Preview Custom Tools is a variant of Gemini 3.1 Pro that improves tool selection behavior by preventing overuse of a general bash tool when more efficient third-party... Checked: 20 Nov 2026 ## Gemini 3.5 Flash Platform: Google (Gemini) Id: google/gemini-3.5-flash URL: https://thebestmodelfor.com/models/google--gemini-3.5-flash OpenRouter: https://openrouter.ai/google/gemini-3.5-flash Kind: chat Listed: 2026-05-19 Context tokens: 1048576 Max output tokens: 65536 Input USD per million: 1.5 Output USD per million: 9 Input per token (published): 0.0000015 Output per token (published): 0.000009 Batch input USD per million: 0.75 Batch output USD per million: 4.5 Other raw prices: image=0.0000015, audio=0.000003, input_audio_cache=0.0000003, web_search=0.014, internal_reasoning=0.000009, input_cache_read=0.00000015, input_cache_write=0.0000000833333333333333 Input modalities: audio, file, image, text, video Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: 2025-01-01 Reasoning: required Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution... Checked: 20 Nov 2026 ## Gemini 3.5 Flash Lite Platform: Google (Gemini) Id: google/gemini-3.5-flash-lite URL: https://thebestmodelfor.com/models/google--gemini-3.5-flash-lite OpenRouter: https://openrouter.ai/google/gemini-3.5-flash-lite Kind: chat Listed: 2026-07-21 Context tokens: 1048576 Max output tokens: 65536 Input USD per million: 0.3 Output USD per million: 2.5 Input per token (published): 0.0000003 Output per token (published): 0.0000025 Batch input USD per million: 0.15 Batch output USD per million: 1.25 Other raw prices: image=0.0000003, audio=0.0000003, input_audio_cache=0.00000003, web_search=0.014, internal_reasoning=0.0000025, input_cache_read=0.00000003, input_cache_write=0.0000000833333333333333 Input modalities: audio, file, image, text, video Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: required Third-party intelligence index: 11.7 Third-party coding index: unknown Guide: reviewed 2026-11-19 — OpenRouter describes Gemini 3.5 Flash Lite as a high-efficiency model for subagents that do one focused task inside a larger workflow. It still accepts text, images, audio, video, and files, at a lower input rate than Gemini 4. Listing blurb: Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks within complex, multi-agent workflows. Checked: 20 Nov 2026 ## Gemini 3.5 Transcribe Platform: Google (Gemini) Id: google/gemini-3.5-transcribe URL: https://thebestmodelfor.com/models/google--gemini-3.5-transcribe OpenRouter: https://openrouter.ai/google/gemini-3.5-transcribe Kind: transcription Listed: 2026-09-25 Context tokens: 98304 Max output tokens: 32768 Input USD per million: 2 Output USD per million: 12 Input per token (published): 0.000002 Output per token (published): 0.000012 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: audio Output modalities: transcription Tools: Not listed Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Gemini 3.5 Transcribe is a speech-to-text model from Google. It is suited for synchronous transcription that needs word-level timestamps or speaker diarization, with support for up to eight speakers. Audio... Checked: 20 Nov 2026 ## Gemini 3.6 Flash Platform: Google (Gemini) Id: google/gemini-3.6-flash URL: https://thebestmodelfor.com/models/google--gemini-3.6-flash OpenRouter: https://openrouter.ai/google/gemini-3.6-flash Kind: chat Listed: 2026-07-21 Context tokens: 1048576 Max output tokens: 65536 Input USD per million: 0.75 Output USD per million: 3.75 Input per token (published): 0.00000075 Output per token (published): 0.00000375 Batch input USD per million: 0.375 Batch output USD per million: 1.875 Other raw prices: image=0.00000075, audio=0.00000075, input_audio_cache=0.000000075, web_search=0.014, internal_reasoning=0.00000375, input_cache_read=0.000000075, input_cache_write=0.0000000416666666666667 Input modalities: audio, file, image, text, video Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: required Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce polished outputs with fewer unnecessary edits and... Checked: 20 Nov 2026 ## Gemini 3.7 Flash Platform: Google (Gemini) Id: google/gemini-3.7-flash URL: https://thebestmodelfor.com/models/google--gemini-3.7-flash OpenRouter: https://openrouter.ai/google/gemini-3.7-flash Kind: chat Listed: 2026-08-13 Context tokens: 1048576 Max output tokens: 65536 Input USD per million: 0.75 Output USD per million: 3.75 Input per token (published): 0.00000075 Output per token (published): 0.00000375 Batch input USD per million: 0.375 Batch output USD per million: 1.875 Other raw prices: image=0.00000075, audio=0.00000075, input_audio_cache=0.000000075, web_search=0.014, internal_reasoning=0.00000375, input_cache_read=0.000000075, input_cache_write=0.0000000416666666666667 Input modalities: audio, file, image, text, video Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: required Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step... Checked: 20 Nov 2026 ## Gemini 3.8 Flash Platform: Google (Gemini) Id: google/gemini-3.8-flash URL: https://thebestmodelfor.com/models/google--gemini-3.8-flash OpenRouter: https://openrouter.ai/google/gemini-3.8-flash Kind: chat Listed: 2026-09-02 Context tokens: 1048576 Max output tokens: 65536 Input USD per million: 0.825 Output USD per million: 4.125 Input per token (published): 0.000000825 Output per token (published): 0.000004125 Batch input USD per million: 0.375 Batch output USD per million: 1.875 Other raw prices: image=0.000000825, audio=0.000000825, input_audio_cache=0.0000000825, web_search=0.014, internal_reasoning=0.000004125, input_cache_read=0.0000000825, input_cache_write=0.0000000416666666666667 Input modalities: audio, file, image, text, video Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: required Third-party intelligence index: 30.8 Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning. Checked: 20 Nov 2026 ## Gemini 3.8 Flash Lite TTS Platform: Google (Gemini) Id: google/gemini-3.8-flash-lite-tts URL: https://thebestmodelfor.com/models/google--gemini-3.8-flash-lite-tts OpenRouter: https://openrouter.ai/google/gemini-3.8-flash-lite-tts Kind: speech Listed: 2026-09-23 Context tokens: 32768 Max output tokens: 16384 Input USD per million: 0.5 Output USD per million: 6 Input per token (published): 0.0000005 Output per token (published): 0.000006 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: text Output modalities: speech Tools: Not listed Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Gemini 3.8 Flash Lite TTS is a text-to-speech model from Google and the fast, high-throughput member of the 3.8 TTS family alongside Gemini 3.8 Flash TTS. It is suited for... Checked: 20 Nov 2026 ## Gemini 3.8 Flash TTS Platform: Google (Gemini) Id: google/gemini-3.8-flash-tts URL: https://thebestmodelfor.com/models/google--gemini-3.8-flash-tts OpenRouter: https://openrouter.ai/google/gemini-3.8-flash-tts Kind: speech Listed: 2026-09-23 Context tokens: 32768 Max output tokens: 16384 Input USD per million: 0.5 Output USD per million: 9 Input per token (published): 0.0000005 Output per token (published): 0.000009 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: text Output modalities: speech Tools: Not listed Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Gemini 3.8 Flash TTS is a text-to-speech model from Google and the successor to Gemini 3.1 Flash TTS Preview. It is the creative tier of the 3.8 TTS family, suited... Checked: 20 Nov 2026 ## Gemini 4 Argon Platform: Google (Gemini) Id: google/gemini-4-argon URL: https://thebestmodelfor.com/models/google--gemini-4-argon OpenRouter: https://openrouter.ai/google/gemini-4-argon Kind: chat Listed: 2026-10-13 Context tokens: 1048576 Max output tokens: 943718 Input USD per million: 2 Output USD per million: 10 Input per token (published): 0.000002 Output per token (published): 0.00001 Batch input USD per million: 1 Batch output USD per million: 5 Other raw prices: image=0.000002, audio=0.000002, input_audio_cache=0.0000001, web_search=0.014, internal_reasoning=0.00001, input_cache_read=0.0000001, input_cache_write=0.0000001875 Input modalities: audio, file, image, text, video Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: required Third-party intelligence index: 50.4 Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. Google trained it to keep context across... Checked: 20 Nov 2026 ## Gemini 4 Carbon Platform: Google (Gemini) Id: google/gemini-4-carbon URL: https://thebestmodelfor.com/models/google--gemini-4-carbon OpenRouter: https://openrouter.ai/google/gemini-4-carbon Kind: chat Listed: 2026-11-10 Context tokens: 1048576 Max output tokens: 943718 Input USD per million: 2 Output USD per million: 10 Input per token (published): 0.000002 Output per token (published): 0.00001 Batch input USD per million: 1 Batch output USD per million: 5 Other raw prices: image=0.000002, audio=0.000002, input_audio_cache=0.0000001, web_search=0.014, internal_reasoning=0.00001, input_cache_read=0.0000001, input_cache_write=0.0000001875 Input modalities: audio, file, image, text, video Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: required Third-party intelligence index: 60 Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Gemini 4 Carbon is a frontier Gemini 4 model from Google for coding, agentic and complex reasoning work. It takes text, image, audio, video and file input, supports long decode... Checked: 20 Nov 2026 ## Gemini 4 Hydrogen Platform: Google (Gemini) Id: google/gemini-4-hydrogen URL: https://thebestmodelfor.com/models/google--gemini-4-hydrogen OpenRouter: https://openrouter.ai/google/gemini-4-hydrogen Kind: chat Listed: 2026-11-12 Context tokens: 1048576 Max output tokens: 943718 Input USD per million: 1.5 Output USD per million: 7.5 Input per token (published): 0.0000015 Output per token (published): 0.0000075 Batch input USD per million: 0.75 Batch output USD per million: 3.75 Other raw prices: image=0.0000015, audio=0.0000015, input_audio_cache=0.000000075, web_search=0.014, internal_reasoning=0.0000075, input_cache_read=0.000000075, input_cache_write=0.0000000833333333333333 Input modalities: audio, file, image, text, video Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: required Third-party intelligence index: 53.9 Third-party coding index: unknown Guide: reviewed 2026-11-19 — OpenRouter calls Gemini 4 Hydrogen the high-efficiency workhorse of Gemini 4, for high-throughput agents and coding at a lower cost than the models above it. It accepts the same broad input list as Neon. Listing blurb: Gemini 4 Hydrogen is the high-efficiency workhorse model of the Gemini 4 family from Google, built for high-throughput agentic workflows, coding and multi-model routing at lower cost and latency than... Checked: 20 Nov 2026 ## Gemini 4 Neon Platform: Google (Gemini) Id: google/gemini-4-neon URL: https://thebestmodelfor.com/models/google--gemini-4-neon OpenRouter: https://openrouter.ai/google/gemini-4-neon Kind: chat Listed: 2026-11-18 Context tokens: 1048576 Max output tokens: 943718 Input USD per million: 3 Output USD per million: 15 Input per token (published): 0.000003 Output per token (published): 0.000015 Batch input USD per million: 1.5 Batch output USD per million: 7.5 Other raw prices: image=0.000003, audio=0.000003, input_audio_cache=0.00000015, web_search=0.014, internal_reasoning=0.000015, input_cache_read=0.00000015, input_cache_write=0.0000000833333333333333 Input modalities: audio, file, image, text, video Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: required Third-party intelligence index: 61.4 Third-party coding index: unknown Guide: reviewed 2026-11-19 — Gemini 4 Neon is the newest Gemini 4 model on the feed. OpenRouter describes it as a fast, mid-priced model for coding and agentic work. The practical reason to pick it is the input list: text, images, audio, video, and files, in one model. Listing blurb: Gemini 4 Neon is a fast, mid-priced model in the Gemini 4 family from Google, built for coding and agentic work. It is suited for repository and terminal coding, web... Checked: 20 Nov 2026 ## Gemini Decision 1 Platform: Google (Gemini) Id: google/gemini-decision-1 URL: https://thebestmodelfor.com/models/google--gemini-decision-1 OpenRouter: https://openrouter.ai/google/gemini-decision-1 Kind: decisions Listed: 2026-11-11 Context tokens: 262144 Max output tokens: 235929 Input USD per million: 0.1 Output USD per million: 0 Input per token (published): 0.0000001 Output per token (published): 0 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: web_search=0.014 Input modalities: audio, file, image, text, video Output modalities: decisions Tools: Not listed Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Gemini Decision 1 is Google's model for the Decisions API. It answers structured questions about an input state (true/false, multiple choice with up to 255 options, and score with up... Checked: 20 Nov 2026 ## Gemini Embedding 001 Platform: Google (Gemini) Id: google/gemini-embedding-001 URL: https://thebestmodelfor.com/models/google--gemini-embedding-001 OpenRouter: https://openrouter.ai/google/gemini-embedding-001 Kind: embeddings Listed: 2025-10-31 Context tokens: 20000 Max output tokens: 18000 Input USD per million: 0.15 Output USD per million: 0 Input per token (published): 0.00000015 Output per token (published): 0 Batch input USD per million: 0.075 Batch output USD per million: 0 Other raw prices: image=0, audio=0 Input modalities: text Output modalities: embeddings Tools: Not listed Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: gemini-embedding-001 provides a unified cutting edge experience across domains, including science, legal, finance, and coding. This embedding model has consistently held a top spot on the Massive Text Embedding Benchmark... Checked: 20 Nov 2026 ## Gemini Embedding 2 Platform: Google (Gemini) Id: google/gemini-embedding-2 URL: https://thebestmodelfor.com/models/google--gemini-embedding-2 OpenRouter: https://openrouter.ai/google/gemini-embedding-2 Kind: embeddings Listed: 2026-05-20 Context tokens: 8192 Max output tokens: 7372 Input USD per million: 0.2 Output USD per million: 0 Input per token (published): 0.0000002 Output per token (published): 0 Batch input USD per million: 0.1 Batch output USD per million: 0 Other raw prices: image=0.00000045, audio=0.0000065 Input modalities: audio, file, image, text, video Output modalities: embeddings Tools: Not listed Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Gemini Embedding 2 is Google's first multimodal embedding model. We currently support mapping text and images into a unified vector space for semantic search and retrieval-augmented generation (RAG). It supports... Checked: 20 Nov 2026 ## Gemini Embedding 2 Preview Platform: Google (Gemini) Id: google/gemini-embedding-2-preview URL: https://thebestmodelfor.com/models/google--gemini-embedding-2-preview OpenRouter: https://openrouter.ai/google/gemini-embedding-2-preview Kind: embeddings Listed: 2026-04-17 Context tokens: 8192 Max output tokens: 7372 Input USD per million: 0.2 Output USD per million: 0 Input per token (published): 0.0000002 Output per token (published): 0 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: image=0.00000045, audio=0.0000065 Input modalities: audio, file, image, text, video Output modalities: embeddings Tools: Not listed Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Gemini Embedding 2 Preview is Google's first multimodal embedding model. We currently support mapping text and images into a unified vector space for semantic search and retrieval-augmented generation (RAG). It... Checked: 20 Nov 2026 ## Nano Banana 2.1 Platform: Google (Gemini) Id: google/gemini-nano-banana-2.1 URL: https://thebestmodelfor.com/models/google--gemini-nano-banana-2.1 OpenRouter: https://openrouter.ai/google/gemini-nano-banana-2.1 Kind: image Listed: 2026-10-06 Context tokens: 65536 Max output tokens: 58982 Input USD per million: 1.5 Output USD per million: 7.5 Input per token (published): 0.0000015 Output per token (published): 0.0000075 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: image_output=0.00003, web_search=0.014 Input modalities: image, text Output modalities: image, text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: optional Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Nano Banana 2.1 (Gemini Nano Banana 2.1) is Google's image generation and editing model on the Flash tier, succeeding Nano Banana 2 and Nano Banana Pro. It improves product recontextualization,... Checked: 20 Nov 2026 ## Gemini Omni 1.1 Flash Platform: Google (Gemini) Id: google/gemini-omni-1.1-flash URL: https://thebestmodelfor.com/models/google--gemini-omni-1.1-flash OpenRouter: https://openrouter.ai/google/gemini-omni-1.1-flash Kind: video Listed: 2026-11-04 Context tokens: 131072 Max output tokens: 65536 Input USD per million: 1.5 Output USD per million: 9 Input per token (published): 0.0000015 Output per token (published): 0.000009 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: web_search=0.014 Input modalities: image, text, video Output modalities: text, video Tools: Not listed Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: required Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Gemini Omni 1.1 Flash is Google's native multimodal video generation and editing model, the generally available successor to Gemini Omni Flash Preview. It is suited for text-to-video, image-to-video, first and... Checked: 20 Nov 2026 ## Gemini Omni 1.2 Flash Platform: Google (Gemini) Id: google/gemini-omni-1.2-flash URL: https://thebestmodelfor.com/models/google--gemini-omni-1.2-flash OpenRouter: https://openrouter.ai/google/gemini-omni-1.2-flash Kind: video Listed: 2026-11-05 Context tokens: 131072 Max output tokens: 65536 Input USD per million: 1.5 Output USD per million: 9 Input per token (published): 0.0000015 Output per token (published): 0.000009 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: web_search=0.014 Input modalities: image, text, video Output modalities: text, video Tools: Not listed Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: required Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Gemini Omni 1.2 Flash is Google's native multimodal video generation and editing model, the successor to Gemini Omni 1.1 Flash. It generates clips up to 15 seconds long with native... Checked: 20 Nov 2026 ## Gemma 2 27B Platform: Google (Gemini) Id: google/gemma-2-27b-it URL: https://thebestmodelfor.com/models/google--gemma-2-27b-it OpenRouter: https://openrouter.ai/google/gemma-2-27b-it Kind: chat Listed: 2024-07-13 Context tokens: 8192 Max output tokens: 2048 Input USD per million: 0.65 Output USD per million: 0.65 Input per token (published): 0.00000065 Output per token (published): 0.00000065 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: text Output modalities: text Tools: Not listed Open weights: Yes (google/gemma-2-27b-it) Knowledge cutoff: 2024-06-30 Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Gemma 2 27B by Google is an open model built from the same research and technology used to create the Gemini models. Gemma models are well-suited for a variety of... Checked: 20 Nov 2026 ## Gemma 3 12B Platform: Google (Gemini) Id: google/gemma-3-12b-it URL: https://thebestmodelfor.com/models/google--gemma-3-12b-it OpenRouter: https://openrouter.ai/google/gemma-3-12b-it Kind: chat Listed: 2025-03-13 Context tokens: 131072 Max output tokens: 16384 Input USD per million: 0.05 Output USD per million: 0.15 Input per token (published): 0.00000005 Output per token (published): 0.00000015 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: image, text Output modalities: text Tools: Yes Open weights: Yes (google/gemma-3-12b-it) Knowledge cutoff: 2024-08-31 Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,... Checked: 20 Nov 2026 ## Gemma 3 27B Platform: Google (Gemini) Id: google/gemma-3-27b-it URL: https://thebestmodelfor.com/models/google--gemma-3-27b-it OpenRouter: https://openrouter.ai/google/gemma-3-27b-it Kind: chat Listed: 2025-03-12 Context tokens: 131072 Max output tokens: 16384 Input USD per million: 0.08 Output USD per million: 0.16 Input per token (published): 0.00000008 Output per token (published): 0.00000016 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: image, text Output modalities: text Tools: Yes Open weights: Yes (google/gemma-3-27b-it) Knowledge cutoff: 2024-08-31 Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,... Checked: 20 Nov 2026 ## Gemma 3 4B Platform: Google (Gemini) Id: google/gemma-3-4b-it URL: https://thebestmodelfor.com/models/google--gemma-3-4b-it OpenRouter: https://openrouter.ai/google/gemma-3-4b-it Kind: chat Listed: 2025-03-13 Context tokens: 131072 Max output tokens: 16384 Input USD per million: 0.05 Output USD per million: 0.1 Input per token (published): 0.00000005 Output per token (published): 0.0000001 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: image, text Output modalities: text Tools: Not listed Open weights: Yes (google/gemma-3-4b-it) Knowledge cutoff: 2024-08-31 Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,... Checked: 20 Nov 2026 ## Gemma 4 26B A4B Platform: Google (Gemini) Id: google/gemma-4-26b-a4b-it URL: https://thebestmodelfor.com/models/google--gemma-4-26b-a4b-it OpenRouter: https://openrouter.ai/google/gemma-4-26b-a4b-it Kind: chat Listed: 2026-04-03 Context tokens: 262144 Max output tokens: 235929 Input USD per million: 0.09 Output USD per million: 0.3 Input per token (published): 0.00000009 Output per token (published): 0.0000003 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: input_cache_read=0.00000005 Input modalities: image, text, video Output modalities: text Tools: Yes Open weights: Yes (google/gemma-4-26B-A4B-it) Knowledge cutoff: unknown Reasoning: optional Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at... Checked: 20 Nov 2026 ## Gemma 4 31B Platform: Google (Gemini) Id: google/gemma-4-31b-it URL: https://thebestmodelfor.com/models/google--gemma-4-31b-it OpenRouter: https://openrouter.ai/google/gemma-4-31b-it Kind: chat Listed: 2026-04-02 Context tokens: 262144 Max output tokens: 16384 Input USD per million: 0.2 Output USD per million: 0.4 Input per token (published): 0.0000002 Output per token (published): 0.0000004 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: image, text, video Output modalities: text Tools: Yes Open weights: Yes (google/gemma-4-31B-it) Knowledge cutoff: unknown Reasoning: optional Third-party intelligence index: 4.4 Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function... Checked: 20 Nov 2026 ## Lyria 3 Clip Preview Platform: Google (Gemini) Id: google/lyria-3-clip-preview URL: https://thebestmodelfor.com/models/google--lyria-3-clip-preview OpenRouter: https://openrouter.ai/google/lyria-3-clip-preview Kind: speech Listed: 2026-03-30 Context tokens: 1048576 Max output tokens: 65536 Input USD per million: 0 Output USD per million: 0 Input per token (published): 0 Output per token (published): 0 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: image, text Output modalities: audio, text Tools: Not listed Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: 30 second duration clips are priced at $0.04 per clip. Lyria 3 is Google's family of music generation models, available through the Gemini API. With Lyria 3, you can generate... Checked: 20 Nov 2026 ## Lyria 3 Pro Preview Platform: Google (Gemini) Id: google/lyria-3-pro-preview URL: https://thebestmodelfor.com/models/google--lyria-3-pro-preview OpenRouter: https://openrouter.ai/google/lyria-3-pro-preview Kind: speech Listed: 2026-03-30 Context tokens: 1048576 Max output tokens: 65536 Input USD per million: 0 Output USD per million: 0 Input per token (published): 0 Output per token (published): 0 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: image, text Output modalities: audio, text Tools: Not listed Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Full-length songs are priced at $0.08 per song. Lyria 3 is Google's family of music generation models, available through the Gemini API. With Lyria 3, you can generate high-quality, 48kHz... Checked: 20 Nov 2026 ## Veo 3.1 Platform: Google (Gemini) Id: google/veo-3.1 URL: https://thebestmodelfor.com/models/google--veo-3.1 OpenRouter: https://openrouter.ai/google/veo-3.1 Kind: video Listed: 2026-03-23 Context tokens: unknown Max output tokens: unknown Input USD per million: 0 Output USD per million: 0 Input per token (published): 0 Output per token (published): 0 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: image, text Output modalities: video Tools: Not listed Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Google's state-of-the-art video generation model, built for maximum visual fidelity in final production cuts. Veo 3.1 generates high-quality 1080p video from text or image prompts with native synchronized audio —... Checked: 20 Nov 2026 ## Veo 3.1 Fast Platform: Google (Gemini) Id: google/veo-3.1-fast URL: https://thebestmodelfor.com/models/google--veo-3.1-fast OpenRouter: https://openrouter.ai/google/veo-3.1-fast Kind: video Listed: 2026-04-24 Context tokens: unknown Max output tokens: unknown Input USD per million: 0 Output USD per million: 0 Input per token (published): 0 Output per token (published): 0 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: image, text Output modalities: video Tools: Not listed Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Google's mid-tier video generation model balancing speed and quality. Veo 3.1 Fast generates high-quality video from text or image prompts with native synchronized audio, offering faster turnaround than Veo 3.1... Checked: 20 Nov 2026 ## Veo 3.1 Lite Platform: Google (Gemini) Id: google/veo-3.1-lite URL: https://thebestmodelfor.com/models/google--veo-3.1-lite OpenRouter: https://openrouter.ai/google/veo-3.1-lite Kind: video Listed: 2026-04-23 Context tokens: unknown Max output tokens: unknown Input USD per million: 0 Output USD per million: 0 Input per token (published): 0 Output per token (published): 0 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: image, text Output modalities: video Tools: Not listed Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Google's most cost-effective video generation model, designed for high-volume applications and rapid iteration. Veo 3.1 Lite generates 720p and 1080p video from text or image prompts with native synchronized audio... Checked: 20 Nov 2026 ## Grok 4.20 Platform: xAI (Grok) Id: x-ai/grok-4.20 URL: https://thebestmodelfor.com/models/x-ai--grok-4.20 OpenRouter: https://openrouter.ai/x-ai/grok-4.20 Kind: chat Listed: 2026-03-31 Context tokens: 2000000 Max output tokens: 1800000 Input USD per million: 1.25 Output USD per million: 2.5 Input per token (published): 0.00000125 Output per token (published): 0.0000025 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: web_search=0.005, input_cache_read=0.0000002 Input modalities: file, image, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: 2025-09-01 Reasoning: optional Third-party intelligence index: unknown Third-party coding index: unknown Guide: reviewed 2026-11-19 — Grok 4.20 lists a 2,000,000-token context, the longest among the reviewed Grok models, plus tool calling. The same row publishes a knowledge cutoff of 2025-09-01. Use it to read a corpus you supply, not to ask what happened last week. Listing blurb: Grok 4.20 is a reasoning model from SpaceXSI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering... Checked: 20 Nov 2026 ## Grok 4.20 Multi-Agent Platform: xAI (Grok) Id: x-ai/grok-4.20-multi-agent URL: https://thebestmodelfor.com/models/x-ai--grok-4.20-multi-agent OpenRouter: https://openrouter.ai/x-ai/grok-4.20-multi-agent Kind: chat Listed: 2026-03-31 Context tokens: 2000000 Max output tokens: 1800000 Input USD per million: 1.25 Output USD per million: 2.5 Input per token (published): 0.00000125 Output per token (published): 0.0000025 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: web_search=0.005, input_cache_read=0.0000002 Input modalities: file, image, text Output modalities: text Tools: Not listed Open weights: No public weights id listed Knowledge cutoff: 2025-09-01 Reasoning: required Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Grok 4.20 Multi-Agent is a variant of SpaceXSI’s Grok 4.20 designed for collaborative, agent-based workflows. Multiple agents operate in parallel to conduct deep research, coordinate tool use, and synthesize information... Checked: 20 Nov 2026 ## Grok 4.3 Platform: xAI (Grok) Id: x-ai/grok-4.3 URL: https://thebestmodelfor.com/models/x-ai--grok-4.3 OpenRouter: https://openrouter.ai/x-ai/grok-4.3 Kind: chat Listed: 2026-04-30 Context tokens: 1000000 Max output tokens: 900000 Input USD per million: 1.25 Output USD per million: 2.5 Input per token (published): 0.00000125 Output per token (published): 0.0000025 Batch input USD per million: 1 Batch output USD per million: 2 Other raw prices: web_search=0.005, input_cache_read=0.0000002 Input modalities: file, image, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: optional Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Grok 4.3 is a reasoning model from SpaceXSI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual... Checked: 20 Nov 2026 ## Grok 4.5 Platform: xAI (Grok) Id: x-ai/grok-4.5 URL: https://thebestmodelfor.com/models/x-ai--grok-4.5 OpenRouter: https://openrouter.ai/x-ai/grok-4.5 Kind: chat Listed: 2026-07-08 Context tokens: 500000 Max output tokens: 450000 Input USD per million: 2 Output USD per million: 6 Input per token (published): 0.000002 Output per token (published): 0.000006 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: web_search=0.005, input_cache_read=0.0000003 Input modalities: file, image, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: required Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Grok 4.5 is a model from SpaceXSI with frontier performance on coding, knowledge work, and STEM. Checked: 20 Nov 2026 ## Grok 4.6 Platform: xAI (Grok) Id: x-ai/grok-4.6 URL: https://thebestmodelfor.com/models/x-ai--grok-4.6 OpenRouter: https://openrouter.ai/x-ai/grok-4.6 Kind: chat Listed: 2026-08-12 Context tokens: 500000 Max output tokens: 450000 Input USD per million: 2 Output USD per million: 6 Input per token (published): 0.000002 Output per token (published): 0.000006 Batch input USD per million: 1.6 Batch output USD per million: 4.8 Other raw prices: web_search=0.005, input_cache_read=0.0000005 Input modalities: file, image, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: required Third-party intelligence index: 31 Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Grok 4.6 is a model from SpaceXSI with frontier performance on coding, knowledge work, and STEM. It is succeeded by Grok 4.7. Checked: 20 Nov 2026 ## Grok 4.7 Platform: xAI (Grok) Id: x-ai/grok-4.7 URL: https://thebestmodelfor.com/models/x-ai--grok-4.7 OpenRouter: https://openrouter.ai/x-ai/grok-4.7 Kind: chat Listed: 2026-09-21 Context tokens: 500000 Max output tokens: 450000 Input USD per million: 2 Output USD per million: 6 Input per token (published): 0.000002 Output per token (published): 0.000006 Batch input USD per million: 1.6 Batch output USD per million: 4.8 Other raw prices: web_search=0.005, input_cache_read=0.0000005 Input modalities: file, image, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: required Third-party intelligence index: 35.5 Third-party coding index: unknown Guide: reviewed 2026-11-19 — OpenRouter describes Grok 4.7 as SpaceXAI's flagship for coding, agentic tasks, and knowledge work, particularly long-running software engineering where the model checks its own work. Context on this row is 500,000 tokens. No knowledge cutoff is published. Listing blurb: Grok 4.7 is SpaceXSI's flagship model for coding, agentic tasks, and knowledge work, succeeding Grok 4.6. It is particularly strong at long-running software engineering tasks, verifying its own work, and... Checked: 20 Nov 2026 ## Grok Imagine Image 2.0 Platform: xAI (Grok) Id: x-ai/grok-imagine-image-2.0 URL: https://thebestmodelfor.com/models/x-ai--grok-imagine-image-2.0 OpenRouter: https://openrouter.ai/x-ai/grok-imagine-image-2.0 Kind: image Listed: 2026-08-11 Context tokens: 65536 Max output tokens: 58982 Input USD per million: 0 Output USD per million: 0 Input per token (published): 0 Output per token (published): 0 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: image=0.01, image_token=0.00000958083832335329, image_output=0.00000958083832335329 Input modalities: image, text Output modalities: image Tools: Not listed Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Grok Imagine Image 2.0 is an image generation and editing model from xAI. It is suited for creating images from text prompts and editing images from references, with low and... Checked: 20 Nov 2026 ## Grok Imagine Video Platform: xAI (Grok) Id: x-ai/grok-imagine-video URL: https://thebestmodelfor.com/models/x-ai--grok-imagine-video OpenRouter: https://openrouter.ai/x-ai/grok-imagine-video Kind: video Listed: 2026-05-18 Context tokens: unknown Max output tokens: unknown Input USD per million: 0 Output USD per million: 0 Input per token (published): 0 Output per token (published): 0 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: image, text Output modalities: video Tools: Not listed Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Grok Imagine Video is SpaceXSI's fast, text-, image-, and reference-conditioned video generation model. It produces short videos (1–15 seconds, 24 fps) at 480p or 720p across seven aspect ratios -... Checked: 20 Nov 2026 ## Grok Imagine Video 1.5 Platform: xAI (Grok) Id: x-ai/grok-imagine-video-1.5 URL: https://thebestmodelfor.com/models/x-ai--grok-imagine-video-1.5 OpenRouter: https://openrouter.ai/x-ai/grok-imagine-video-1.5 Kind: video Listed: 2026-07-20 Context tokens: unknown Max output tokens: unknown Input USD per million: 0 Output USD per million: 0 Input per token (published): 0 Output per token (published): 0 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: image, text Output modalities: video Tools: Not listed Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Grok Imagine Video 1.5 is a video generation model from SpaceXSI. It creates videos from text prompts, with an optional starting image to guide the scene. It can direct subject... Checked: 20 Nov 2026 ## Grok Imagine Video 1.5 Lite Platform: xAI (Grok) Id: x-ai/grok-imagine-video-1.5-lite URL: https://thebestmodelfor.com/models/x-ai--grok-imagine-video-1.5-lite OpenRouter: https://openrouter.ai/x-ai/grok-imagine-video-1.5-lite Kind: video Listed: 2026-10-06 Context tokens: unknown Max output tokens: unknown Input USD per million: 0 Output USD per million: 0 Input per token (published): 0 Output per token (published): 0 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: image, text Output modalities: video Tools: Not listed Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Grok Imagine Video 1.5 Lite is a faster, lower-cost video generation model from SpaceXSI, distilled from Grok Imagine Video 1.5. It supports text-to-video and image-to-video, trading some quality for speed... Checked: 20 Nov 2026 ## Grok STT 2.0 Platform: xAI (Grok) Id: x-ai/grok-stt-2.0 URL: https://thebestmodelfor.com/models/x-ai--grok-stt-2.0 OpenRouter: https://openrouter.ai/x-ai/grok-stt-2.0 Kind: transcription Listed: 2026-11-10 Context tokens: unknown Max output tokens: unknown Input USD per million: 27.7777777778 Output USD per million: 0 Input per token (published): 0.0000277777777778 Output per token (published): 0 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: audio Output modalities: transcription Tools: Not listed Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Grok STT 2.0 is a speech-to-text model from SpaceXSI and the successor to Grok STT 1.0. It is suited for transcription workloads that need word-level timestamps, optional speaker diarization, and... Checked: 20 Nov 2026 ## Grok Voice TTS 1.0 Platform: xAI (Grok) Id: x-ai/grok-voice-tts-1.0 URL: https://thebestmodelfor.com/models/x-ai--grok-voice-tts-1.0 OpenRouter: https://openrouter.ai/x-ai/grok-voice-tts-1.0 Kind: speech Listed: 2026-05-15 Context tokens: 15000 Max output tokens: 13500 Input USD per million: 15 Output USD per million: 0 Input per token (published): 0.000015 Output per token (published): 0 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: text Output modalities: speech Tools: Not listed Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Grok Voice TTS 1.0 is a text-to-speech model from SpaceXSI. It converts text into spoken audio across 20+ languages with automatic language detection, and offers five built-in voices (Eve, Ara,... Checked: 20 Nov 2026 ## Llama 3.1 70B Instruct Platform: Meta (Llama) Id: meta-llama/llama-3.1-70b-instruct URL: https://thebestmodelfor.com/models/meta-llama--llama-3.1-70b-instruct OpenRouter: https://openrouter.ai/meta-llama/llama-3.1-70b-instruct Kind: chat Listed: 2024-07-23 Context tokens: 131072 Max output tokens: 8192 Input USD per million: 0.72 Output USD per million: 0.72 Input per token (published): 0.00000072 Output per token (published): 0.00000072 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: text Output modalities: text Tools: Yes Open weights: Yes (meta-llama/Meta-Llama-3.1-70B-Instruct) Knowledge cutoff: 2023-12-31 Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 70B instruct-tuned version is optimized for high quality dialogue usecases. It has demonstrated strong... Checked: 20 Nov 2026 ## Llama 3.1 8B Instruct Platform: Meta (Llama) Id: meta-llama/llama-3.1-8b-instruct URL: https://thebestmodelfor.com/models/meta-llama--llama-3.1-8b-instruct OpenRouter: https://openrouter.ai/meta-llama/llama-3.1-8b-instruct Kind: chat Listed: 2024-07-23 Context tokens: 131072 Max output tokens: 16384 Input USD per million: 0.02 Output USD per million: 0.04 Input per token (published): 0.00000002 Output per token (published): 0.00000004 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: text Output modalities: text Tools: Yes Open weights: Yes (meta-llama/Meta-Llama-3.1-8B-Instruct) Knowledge cutoff: 2023-12-31 Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 8B instruct-tuned version is fast and efficient. It has demonstrated strong performance compared to... Checked: 20 Nov 2026 ## Llama 3.2 3B Instruct Platform: Meta (Llama) Id: meta-llama/llama-3.2-3b-instruct URL: https://thebestmodelfor.com/models/meta-llama--llama-3.2-3b-instruct OpenRouter: https://openrouter.ai/meta-llama/llama-3.2-3b-instruct Kind: chat Listed: 2024-09-25 Context tokens: 131072 Max output tokens: 117964 Input USD per million: 0.05 Output USD per million: 0.33 Input per token (published): 0.00000005 Output per token (published): 0.00000033 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: text Output modalities: text Tools: Not listed Open weights: Yes (meta-llama/Llama-3.2-3B-Instruct) Knowledge cutoff: 2023-12-31 Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization. Designed with the latest transformer architecture, it... Checked: 20 Nov 2026 ## Llama 3.3 70B Instruct Platform: Meta (Llama) Id: meta-llama/llama-3.3-70b-instruct URL: https://thebestmodelfor.com/models/meta-llama--llama-3.3-70b-instruct OpenRouter: https://openrouter.ai/meta-llama/llama-3.3-70b-instruct Kind: chat Listed: 2024-12-06 Context tokens: 131072 Max output tokens: 115200 Input USD per million: 0.71 Output USD per million: 0.71 Input per token (published): 0.00000071 Output per token (published): 0.00000071 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: input_cache_read=0.00000071 Input modalities: text Output modalities: text Tools: Yes Open weights: Yes (meta-llama/Llama-3.3-70B-Instruct) Knowledge cutoff: 2023-12-31 Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model... Checked: 20 Nov 2026 ## Llama 4 Maverick Platform: Meta (Llama) Id: meta-llama/llama-4-maverick URL: https://thebestmodelfor.com/models/meta-llama--llama-4-maverick OpenRouter: https://openrouter.ai/meta-llama/llama-4-maverick Kind: chat Listed: 2025-04-05 Context tokens: 524288 Max output tokens: 32768 Input USD per million: 0.35 Output USD per million: 1 Input per token (published): 0.00000035 Output per token (published): 0.000001 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: input_cache_read=0.00000017 Input modalities: image, text Output modalities: text Tools: Yes Open weights: Yes (meta-llama/Llama-4-Maverick-17B-128E-Instruct) Knowledge cutoff: 2024-08-31 Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward... Checked: 20 Nov 2026 ## Llama 4 Scout Platform: Meta (Llama) Id: meta-llama/llama-4-scout URL: https://thebestmodelfor.com/models/meta-llama--llama-4-scout OpenRouter: https://openrouter.ai/meta-llama/llama-4-scout Kind: chat Listed: 2025-04-05 Context tokens: 1310720 Max output tokens: 16384 Input USD per million: 0.1 Output USD per million: 0.3 Input per token (published): 0.0000001 Output per token (published): 0.0000003 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: image, text Output modalities: text Tools: Yes Open weights: Yes (meta-llama/Llama-4-Scout-17B-16E-Instruct) Knowledge cutoff: 2024-08-31 Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: reviewed 2026-11-19 — Llama 4 Scout is the open-weight, long-context Meta model on this feed: a public Hugging Face id, image input, a window above a million tokens, and a low rate. The feed lists a knowledge cutoff of 2024-08-31. It is a reader of documents you supply. Listing blurb: Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input... Checked: 20 Nov 2026 ## Llama Guard 4 12B Platform: Meta (Llama) Id: meta-llama/llama-guard-4-12b URL: https://thebestmodelfor.com/models/meta-llama--llama-guard-4-12b OpenRouter: https://openrouter.ai/meta-llama/llama-guard-4-12b Kind: chat Listed: 2025-04-30 Context tokens: 163840 Max output tokens: 16384 Input USD per million: 0.18 Output USD per million: 0.18 Input per token (published): 0.00000018 Output per token (published): 0.00000018 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: image, text Output modalities: text Tools: Not listed Open weights: Yes (meta-llama/Llama-Guard-4-12B) Knowledge cutoff: 2024-08-31 Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Llama Guard 4 is a Llama 4 Scout-derived multimodal pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM... Checked: 20 Nov 2026 ## Muse Ember Platform: Meta (Llama) Id: meta/muse-ember URL: https://thebestmodelfor.com/models/meta--muse-ember OpenRouter: https://openrouter.ai/meta/muse-ember Kind: chat Listed: 2026-11-09 Context tokens: 1048576 Max output tokens: 943718 Input USD per million: 0.1 Output USD per million: 0.5 Input per token (published): 0.0000001 Output per token (published): 0.0000005 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: web_search=0.0025, input_cache_read=0.000000004, input_cache_write=0.000000125 Input modalities: audio, file, image, text, video Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: required Third-party intelligence index: 36 Third-party coding index: unknown Guide: reviewed 2026-11-19 — OpenRouter describes Muse Ember as Meta's smallest model for the work agents repeat all day: tool calls, coding subtasks, and routing. It keeps the wide input list — text, image, video, audio, and files — at a much lower rate than Wonder. Listing blurb: Muse Ember is the smallest and most efficient model from Meta that’s designed for complex reasoning execution and the work agents repeat all day: tool calls, coding agent subtasks, routing,... Checked: 20 Nov 2026 ## Muse Glimmer 30B Platform: Meta (Llama) Id: meta/muse-glimmer-30b URL: https://thebestmodelfor.com/models/meta--muse-glimmer-30b OpenRouter: https://openrouter.ai/meta/muse-glimmer-30b Kind: chat Listed: 2026-08-09 Context tokens: 131072 Max output tokens: 117964 Input USD per million: 0.35 Output USD per million: 1.5 Input per token (published): 0.00000035 Output per token (published): 0.0000015 Batch input USD per million: 0.24 Batch output USD per million: 0.96 Other raw prices: input_cache_read=0.00000004 Input modalities: image, text Output modalities: text Tools: Yes Open weights: Yes (meta-models/Muse-Glimmer-30B) Knowledge cutoff: unknown Reasoning: required Third-party intelligence index: 6.3 Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Muse Glimmer 30B is a dense, open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and optimized for autonomous agents on consumer hardware. It is suited for long-horizon... Checked: 20 Nov 2026 ## Muse Image Platform: Meta (Llama) Id: meta/muse-image URL: https://thebestmodelfor.com/models/meta--muse-image OpenRouter: https://openrouter.ai/meta/muse-image Kind: image Listed: 2026-08-26 Context tokens: 65536 Max output tokens: 58982 Input USD per million: 0 Output USD per million: 0 Input per token (published): 0 Output per token (published): 0 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: image_token=0.00000239520958083832, image_output=0.00000239520958083832 Input modalities: image, text Output modalities: image Tools: Not listed Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Muse Image is an agentic image generation model from Meta that generates and edits images from text and reference images. Unlike single-pass image models, it reasons before it renders, breaking... Checked: 20 Nov 2026 ## Muse Spark 1.1 Platform: Meta (Llama) Id: meta/muse-spark-1.1 URL: https://thebestmodelfor.com/models/meta--muse-spark-1.1 OpenRouter: https://openrouter.ai/meta/muse-spark-1.1 Kind: chat Listed: 2026-07-16 Context tokens: 1048576 Max output tokens: 943718 Input USD per million: 1.25 Output USD per million: 4.25 Input per token (published): 0.00000125 Output per token (published): 0.00000425 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: web_search=0.0025, input_cache_read=0.00000015 Input modalities: file, image, text, video Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: required Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Muse Spark 1.1 is a multimodal reasoning model from Meta, built for agentic tasks. It accepts text, images, video, and PDF documents and returns text, with a 1M-token context window.... Checked: 20 Nov 2026 ## Muse Spark 1.2 Platform: Meta (Llama) Id: meta/muse-spark-1.2 URL: https://thebestmodelfor.com/models/meta--muse-spark-1.2 OpenRouter: https://openrouter.ai/meta/muse-spark-1.2 Kind: chat Listed: 2026-08-05 Context tokens: 1048576 Max output tokens: 943718 Input USD per million: 1.25 Output USD per million: 4.25 Input per token (published): 0.00000125 Output per token (published): 0.00000425 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: web_search=0.0025, input_cache_read=0.00000015 Input modalities: file, image, text, video Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: required Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Muse Spark 1.2 is a reasoning model from Meta, designed for complex agentic tasks. It accepts text, images, video, and PDF documents, returns text, and offers a 1M-token context window.... Checked: 20 Nov 2026 ## Muse Spark 1.2 Contributor Platform: Meta (Llama) Id: meta/muse-spark-1.2-contributor URL: https://thebestmodelfor.com/models/meta--muse-spark-1.2-contributor OpenRouter: https://openrouter.ai/meta/muse-spark-1.2-contributor Kind: chat Listed: 2026-08-21 Context tokens: 1048576 Max output tokens: 943718 Input USD per million: 0.1 Output USD per million: 0.2 Input per token (published): 0.0000001 Output per token (published): 0.0000002 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: web_search=0.0025, input_cache_read=0.000000002 Input modalities: file, image, text, video Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: required Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Muse Spark 1.2 contributor tier is a reasoning model from Meta designed for developers who want to start building at an even lower cost. It’s meaningfully cheaper than Muse Spark... Checked: 20 Nov 2026 ## Muse Spark 1.3 Platform: Meta (Llama) Id: meta/muse-spark-1.3 URL: https://thebestmodelfor.com/models/meta--muse-spark-1.3 OpenRouter: https://openrouter.ai/meta/muse-spark-1.3 Kind: chat Listed: 2026-09-02 Context tokens: 1048576 Max output tokens: 943718 Input USD per million: 1.25 Output USD per million: 4.25 Input per token (published): 0.00000125 Output per token (published): 0.00000425 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: web_search=0.0025, input_cache_read=0.00000015 Input modalities: file, image, text, video Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: required Third-party intelligence index: 36.6 Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It is designed to keep track of information across extended tasks, work through... Checked: 20 Nov 2026 ## Muse Spark 1.3 Contributor Platform: Meta (Llama) Id: meta/muse-spark-1.3-contributor URL: https://thebestmodelfor.com/models/meta--muse-spark-1.3-contributor OpenRouter: https://openrouter.ai/meta/muse-spark-1.3-contributor Kind: chat Listed: 2026-09-02 Context tokens: 1048576 Max output tokens: 943718 Input USD per million: 0.1 Output USD per million: 0.2 Input per token (published): 0.0000001 Output per token (published): 0.0000002 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: web_search=0.0025, input_cache_read=0.000000002 Input modalities: file, image, text, video Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: required Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Muse Spark 1.3 Contributor is the cost-efficient contributor tier of Meta’s multimodal reasoning model for experimentation, learning, and early-stage agentic, multi-agent, and coding workflows. It is designed to track information... Checked: 20 Nov 2026 ## Muse Spark Open Platform: Meta (Llama) Id: meta/muse-spark-open URL: https://thebestmodelfor.com/models/meta--muse-spark-open OpenRouter: https://openrouter.ai/meta/muse-spark-open Kind: chat Listed: 2026-10-15 Context tokens: 1048576 Max output tokens: 943718 Input USD per million: 1.25 Output USD per million: 4.25 Input per token (published): 0.00000125 Output per token (published): 0.00000425 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: input_cache_read=0.00000015 Input modalities: audio, file, image, text, video Output modalities: text Tools: Yes Open weights: Yes (meta-models/Muse-Spark-Open-816B-A42B) Knowledge cutoff: unknown Reasoning: required Third-party intelligence index: 24.9 Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Muse Spark Open is a coding-optimized open-weight model. Trained specifically for agentic coding workflows, it delivers higher first-attempt accuracy, reliable tool calling, and deep codebase understanding across the repos developers... Checked: 20 Nov 2026 ## Muse Voice Transcribe 1.0 Platform: Meta (Llama) Id: meta/muse-voice-transcribe-1.0 URL: https://thebestmodelfor.com/models/meta--muse-voice-transcribe-1.0 OpenRouter: https://openrouter.ai/meta/muse-voice-transcribe-1.0 Kind: transcription Listed: 2026-09-11 Context tokens: unknown Max output tokens: unknown Input USD per million: 50 Output USD per million: 0 Input per token (published): 0.00005 Output per token (published): 0 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: audio Output modalities: transcription Tools: Not listed Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Muse Voice Transcribe 1.0 is a synchronous speech-to-text model from Meta. It is suited for push-to-talk, endpointing, and speaker-aware transcription, with keyword biasing for domain terms and language biasing through... Checked: 20 Nov 2026 ## Muse Wonder Platform: Meta (Llama) Id: meta/muse-wonder URL: https://thebestmodelfor.com/models/meta--muse-wonder OpenRouter: https://openrouter.ai/meta/muse-wonder Kind: chat Listed: 2026-10-12 Context tokens: 1048576 Max output tokens: 943718 Input USD per million: 4 Output USD per million: 20 Input per token (published): 0.000004 Output per token (published): 0.00002 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: web_search=0.01, input_cache_read=0.0000002 Input modalities: audio, file, image, text, video Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: required Third-party intelligence index: 43.6 Third-party coding index: unknown Guide: reviewed 2026-11-19 — OpenRouter describes Muse Wonder as Meta's frontier reasoning model for complex personal and professional agent tasks. It accepts text, images, video, audio, and files, and returns text. No public weights id is listed. Listing blurb: Muse Wonder is a frontier reasoning model from Meta, designed for complex personal and professional agentic tasks. It accepts text, images, video, audio, and PDF documents and returns text, with... Checked: 20 Nov 2026 ## Codestral 2508 Platform: Mistral Id: mistralai/codestral-2508 URL: https://thebestmodelfor.com/models/mistralai--codestral-2508 OpenRouter: https://openrouter.ai/mistralai/codestral-2508 Kind: chat Listed: 2025-08-01 Context tokens: 256000 Max output tokens: 204800 Input USD per million: 0.3 Output USD per million: 0.9 Input per token (published): 0.0000003 Output per token (published): 0.0000009 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: input_cache_read=0.00000003 Input modalities: file, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: 2025-03-31 Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation. Blog Post Checked: 20 Nov 2026 ## Codestral Embed 2505 Platform: Mistral Id: mistralai/codestral-embed-2505 URL: https://thebestmodelfor.com/models/mistralai--codestral-embed-2505 OpenRouter: https://openrouter.ai/mistralai/codestral-embed-2505 Kind: embeddings Listed: 2025-10-30 Context tokens: 8192 Max output tokens: 6553 Input USD per million: 0.15 Output USD per million: 0 Input per token (published): 0.00000015 Output per token (published): 0 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: text Output modalities: embeddings Tools: Not listed Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Mistral Codestral Embed is specially designed for code, perfect for embedding code databases, repositories, and powering coding assistants with state-of-the-art retrieval. Checked: 20 Nov 2026 ## Devstral 2 2512 Platform: Mistral Id: mistralai/devstral-2512 URL: https://thebestmodelfor.com/models/mistralai--devstral-2512 OpenRouter: https://openrouter.ai/mistralai/devstral-2512 Kind: chat Listed: 2025-12-09 Context tokens: 262144 Max output tokens: 209715 Input USD per million: 0.4 Output USD per million: 2 Input per token (published): 0.0000004 Output per token (published): 0.000002 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: input_cache_read=0.00000004 Input modalities: file, text Output modalities: text Tools: Yes Open weights: Yes (mistralai/Devstral-2-123B-Instruct-2512) Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: reviewed 2026-11-19 — OpenRouter describes Devstral 2 as Mistral's open-weight coding model for agentic work, including exploring a repository. Text and file input, text output, a 256,000-token window. It is a coding tool, not a general writer. Listing blurb: Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding. It is a 123B-parameter dense transformer model supporting a 256K context window. Devstral 2 supports exploring... Checked: 20 Nov 2026 ## Ministral 3 14B 2512 Platform: Mistral Id: mistralai/ministral-14b-2512 URL: https://thebestmodelfor.com/models/mistralai--ministral-14b-2512 OpenRouter: https://openrouter.ai/mistralai/ministral-14b-2512 Kind: chat Listed: 2025-12-02 Context tokens: 262144 Max output tokens: 209715 Input USD per million: 0.2 Output USD per million: 0.2 Input per token (published): 0.0000002 Output per token (published): 0.0000002 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: input_cache_read=0.00000002 Input modalities: image, text Output modalities: text Tools: Yes Open weights: Yes (mistralai/Ministral-3-14B-Instruct-2512) Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart. A powerful and efficient language... Checked: 20 Nov 2026 ## Ministral 3 3B 2512 Platform: Mistral Id: mistralai/ministral-3b-2512 URL: https://thebestmodelfor.com/models/mistralai--ministral-3b-2512 OpenRouter: https://openrouter.ai/mistralai/ministral-3b-2512 Kind: chat Listed: 2025-12-02 Context tokens: 131072 Max output tokens: 104857 Input USD per million: 0.1 Output USD per million: 0.1 Input per token (published): 0.0000001 Output per token (published): 0.0000001 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: input_cache_read=0.00000001 Input modalities: image, text Output modalities: text Tools: Yes Open weights: Yes (mistralai/Ministral-3-3B-Instruct-2512) Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities. Checked: 20 Nov 2026 ## Ministral 3 8B 2512 Platform: Mistral Id: mistralai/ministral-8b-2512 URL: https://thebestmodelfor.com/models/mistralai--ministral-8b-2512 OpenRouter: https://openrouter.ai/mistralai/ministral-8b-2512 Kind: chat Listed: 2025-12-02 Context tokens: 262144 Max output tokens: 209715 Input USD per million: 0.15 Output USD per million: 0.15 Input per token (published): 0.00000015 Output per token (published): 0.00000015 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: input_cache_read=0.000000015 Input modalities: image, text Output modalities: text Tools: Yes Open weights: Yes (mistralai/Ministral-3-8B-Instruct-2512) Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities. Checked: 20 Nov 2026 ## Mistral Embed 2312 Platform: Mistral Id: mistralai/mistral-embed-2312 URL: https://thebestmodelfor.com/models/mistralai--mistral-embed-2312 OpenRouter: https://openrouter.ai/mistralai/mistral-embed-2312 Kind: embeddings Listed: 2025-10-31 Context tokens: 8192 Max output tokens: 6553 Input USD per million: 0.1 Output USD per million: 0 Input per token (published): 0.0000001 Output per token (published): 0 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: text Output modalities: embeddings Tools: Not listed Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Mistral Embed is a specialized embedding model for text data, optimized for semantic search and RAG applications. Developed by Mistral AI in late 2023, it produces 1024-dimensional vectors that effectively... Checked: 20 Nov 2026 ## Mistral Large Platform: Mistral Id: mistralai/mistral-large URL: https://thebestmodelfor.com/models/mistralai--mistral-large OpenRouter: https://openrouter.ai/mistralai/mistral-large Kind: chat Listed: 2024-02-26 Context tokens: 128000 Max output tokens: 102400 Input USD per million: 2 Output USD per million: 6 Input per token (published): 0.000002 Output per token (published): 0.000006 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: input_cache_read=0.0000002 Input modalities: file, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: 2024-11-30 Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: This is Mistral AI's flagship model, Mistral Large 2 (version mistral-large-2407). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement here.... Checked: 20 Nov 2026 ## Mistral Large 2407 Platform: Mistral Id: mistralai/mistral-large-2407 URL: https://thebestmodelfor.com/models/mistralai--mistral-large-2407 OpenRouter: https://openrouter.ai/mistralai/mistral-large-2407 Kind: chat Listed: 2024-11-19 Context tokens: 131072 Max output tokens: 104857 Input USD per million: 2 Output USD per million: 6 Input per token (published): 0.000002 Output per token (published): 0.000006 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: input_cache_read=0.0000002 Input modalities: file, text Output modalities: text Tools: Yes Open weights: Yes (mistralai/Mistral-Large-Instruct-2407) Knowledge cutoff: 2024-03-31 Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: This is Mistral AI's flagship model, Mistral Large 2 (version mistral-large-2407). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement here.... Checked: 20 Nov 2026 ## Mistral Large 3 2512 Platform: Mistral Id: mistralai/mistral-large-2512 URL: https://thebestmodelfor.com/models/mistralai--mistral-large-2512 OpenRouter: https://openrouter.ai/mistralai/mistral-large-2512 Kind: chat Listed: 2025-12-01 Context tokens: 262144 Max output tokens: 209715 Input USD per million: 0.5 Output USD per million: 1.5 Input per token (published): 0.0000005 Output per token (published): 0.0000015 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: input_cache_read=0.00000005 Input modalities: file, image, text Output modalities: text Tools: Yes Open weights: Yes (mistralai/Mistral-Large-3-675B-Instruct-2512) Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Mistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B total), and released under the Apache 2.0 license. Checked: 20 Nov 2026 ## Mistral Large 4 Platform: Mistral Id: mistralai/mistral-large-4-0 URL: https://thebestmodelfor.com/models/mistralai--mistral-large-4-0 OpenRouter: https://openrouter.ai/mistralai/mistral-large-4-0 Kind: chat Listed: 2026-10-06 Context tokens: 1048576 Max output tokens: 262144 Input USD per million: 0.7 Output USD per million: 2.1 Input per token (published): 0.0000007 Output per token (published): 0.0000021 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: input_cache_read=0.00000007 Input modalities: image, text Output modalities: text Tools: Yes Open weights: Yes (mistralai/Mistral-Large-4-1T-A52B) Knowledge cutoff: unknown Reasoning: optional Third-party intelligence index: 26.1 Third-party coding index: unknown Guide: reviewed 2026-11-19 — Mistral Large 4 is listed with a public weights id, image input, about a million tokens of context, and a blurb aimed at reasoning, coding, and agents. Pick it when open weights are a requirement and you still want a frontier-shaped model. Listing blurb: Mistral Large 4 is a frontier multimodal (text and image input) model from Mistral AI built for reasoning, coding, and agentic workloads. It offers a 1M-token context window with up... Checked: 20 Nov 2026 ## Mistral Medium 3 Platform: Mistral Id: mistralai/mistral-medium-3 URL: https://thebestmodelfor.com/models/mistralai--mistral-medium-3 OpenRouter: https://openrouter.ai/mistralai/mistral-medium-3 Kind: chat Listed: 2025-05-07 Context tokens: 131072 Max output tokens: 104857 Input USD per million: 0.44 Output USD per million: 2.2 Input per token (published): 0.00000044 Output per token (published): 0.0000022 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: input_cache_read=0.000000044 Input modalities: file, image, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: 2025-03-31 Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Mistral Medium 3 is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances state-of-the-art reasoning and multimodal performance with 8× lower cost... Checked: 20 Nov 2026 ## Mistral Medium 3.5 Platform: Mistral Id: mistralai/mistral-medium-3-5 URL: https://thebestmodelfor.com/models/mistralai--mistral-medium-3-5 OpenRouter: https://openrouter.ai/mistralai/mistral-medium-3-5 Kind: chat Listed: 2026-04-30 Context tokens: 262144 Max output tokens: 209715 Input USD per million: 1.5 Output USD per million: 7.5 Input per token (published): 0.0000015 Output per token (published): 0.0000075 Batch input USD per million: 0.75 Batch output USD per million: 3.75 Other raw prices: none Input modalities: file, image, text Output modalities: text Tools: Yes Open weights: Yes (mistralai/Mistral-Medium-3.5-128B) Knowledge cutoff: unknown Reasoning: optional Third-party intelligence index: 4.6 Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex... Checked: 20 Nov 2026 ## Mistral Medium 3.1 Platform: Mistral Id: mistralai/mistral-medium-3.1 URL: https://thebestmodelfor.com/models/mistralai--mistral-medium-3.1 OpenRouter: https://openrouter.ai/mistralai/mistral-medium-3.1 Kind: chat Listed: 2025-08-13 Context tokens: 131072 Max output tokens: 104857 Input USD per million: 0.44 Output USD per million: 2.2 Input per token (published): 0.00000044 Output per token (published): 0.0000022 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: input_cache_read=0.000000044 Input modalities: file, image, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: 2025-06-30 Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Mistral Medium 3.1 is an updated version of Mistral Medium 3, which is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances... Checked: 20 Nov 2026 ## Mistral Nemo Platform: Mistral Id: mistralai/mistral-nemo URL: https://thebestmodelfor.com/models/mistralai--mistral-nemo OpenRouter: https://openrouter.ai/mistralai/mistral-nemo Kind: chat Listed: 2024-07-19 Context tokens: 131072 Max output tokens: 16384 Input USD per million: 0.029 Output USD per million: 0.03 Input per token (published): 0.000000029 Output per token (published): 0.00000003 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: text Output modalities: text Tools: Yes Open weights: Yes (mistralai/Mistral-Nemo-Instruct-2407) Knowledge cutoff: 2024-04-30 Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA. The model is multilingual, supporting English, French, German, Spanish, Italian, Portuguese, Chinese, Japanese,... Checked: 20 Nov 2026 ## Saba Platform: Mistral Id: mistralai/mistral-saba URL: https://thebestmodelfor.com/models/mistralai--mistral-saba OpenRouter: https://openrouter.ai/mistralai/mistral-saba Kind: chat Listed: 2025-02-17 Context tokens: 32768 Max output tokens: 26214 Input USD per million: 0.2 Output USD per million: 0.6 Input per token (published): 0.0000002 Output per token (published): 0.0000006 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: input_cache_read=0.00000002 Input modalities: file, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: 2024-09-30 Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Mistral Saba is a 24B-parameter language model specifically designed for the Middle East and South Asia, delivering accurate and contextually relevant responses while maintaining efficient performance. Trained on curated regional... Checked: 20 Nov 2026 ## Mistral Small 3 Platform: Mistral Id: mistralai/mistral-small-24b-instruct-2501 URL: https://thebestmodelfor.com/models/mistralai--mistral-small-24b-instruct-2501 OpenRouter: https://openrouter.ai/mistralai/mistral-small-24b-instruct-2501 Kind: chat Listed: 2025-01-30 Context tokens: 32768 Max output tokens: 16384 Input USD per million: 0.05 Output USD per million: 0.08 Input per token (published): 0.00000005 Output per token (published): 0.00000008 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: text Output modalities: text Tools: Not listed Open weights: Yes (mistralai/Mistral-Small-24B-Instruct-2501) Knowledge cutoff: 2023-10-31 Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0 license, it features both pre-trained and instruction-tuned versions designed... Checked: 20 Nov 2026 ## Mistral Small 4 Platform: Mistral Id: mistralai/mistral-small-2603 URL: https://thebestmodelfor.com/models/mistralai--mistral-small-2603 OpenRouter: https://openrouter.ai/mistralai/mistral-small-2603 Kind: chat Listed: 2026-03-16 Context tokens: 262144 Max output tokens: 209715 Input USD per million: 0.15 Output USD per million: 0.6 Input per token (published): 0.00000015 Output per token (published): 0.0000006 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: input_cache_read=0.000000015 Input modalities: image, text Output modalities: text Tools: Yes Open weights: Yes (mistralai/Mistral-Small-4-119B-2603) Knowledge cutoff: unknown Reasoning: optional Third-party intelligence index: 4.3 Third-party coding index: unknown Guide: reviewed 2026-11-19 — Mistral Small 4 is the reviewed everyday Mistral model: open weights, image input, a 262,144-token window, and a low rate. The listing presents it as the small model that folds several earlier Mistral lines into one. Listing blurb: Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system. It combines strong reasoning from... Checked: 20 Nov 2026 ## Mistral Small 3.1 24B Platform: Mistral Id: mistralai/mistral-small-3.1-24b-instruct URL: https://thebestmodelfor.com/models/mistralai--mistral-small-3.1-24b-instruct OpenRouter: https://openrouter.ai/mistralai/mistral-small-3.1-24b-instruct Kind: chat Listed: 2025-03-17 Context tokens: 128000 Max output tokens: 102400 Input USD per million: 0.351 Output USD per million: 0.555 Input per token (published): 0.000000351 Output per token (published): 0.000000555 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: image, text Output modalities: text Tools: Yes Open weights: Yes (mistralai/Mistral-Small-3.1-24B-Instruct-2503) Knowledge cutoff: 2023-10-31 Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Mistral Small 3.1 24B Instruct is an upgraded variant of Mistral Small 3 (2501), featuring 24 billion parameters with advanced multimodal capabilities. It provides state-of-the-art performance in text-based reasoning and... Checked: 20 Nov 2026 ## Mistral Small 3.2 24B Platform: Mistral Id: mistralai/mistral-small-3.2-24b-instruct URL: https://thebestmodelfor.com/models/mistralai--mistral-small-3.2-24b-instruct OpenRouter: https://openrouter.ai/mistralai/mistral-small-3.2-24b-instruct Kind: chat Listed: 2025-06-20 Context tokens: 256000 Max output tokens: 16384 Input USD per million: 0.075 Output USD per million: 0.2 Input per token (published): 0.000000075 Output per token (published): 0.0000002 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: image, text Output modalities: text Tools: Yes Open weights: Yes (mistralai/Mistral-Small-3.2-24B-Instruct-2506) Knowledge cutoff: 2023-10-31 Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Mistral-Small-3.2-24B-Instruct-2506 is an updated 24B parameter model from Mistral optimized for instruction following, repetition reduction, and improved function calling. Compared to the 3.1 release, version 3.2 significantly improves accuracy on... Checked: 20 Nov 2026 ## Mixtral 8x22B Instruct Platform: Mistral Id: mistralai/mixtral-8x22b-instruct URL: https://thebestmodelfor.com/models/mistralai--mixtral-8x22b-instruct OpenRouter: https://openrouter.ai/mistralai/mixtral-8x22b-instruct Kind: chat Listed: 2024-04-17 Context tokens: 65536 Max output tokens: 52428 Input USD per million: 2 Output USD per million: 6 Input per token (published): 0.000002 Output per token (published): 0.000006 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: input_cache_read=0.0000002 Input modalities: file, text Output modalities: text Tools: Yes Open weights: Yes (mistralai/Mixtral-8x22B-Instruct-v0.1) Knowledge cutoff: 2024-01-31 Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Mistral's official instruct fine-tuned version of Mixtral 8x22B. It uses 39B active parameters out of 141B, offering unparalleled cost efficiency for its size. Its strengths include: - strong math, coding,... Checked: 20 Nov 2026 ## Pixtral Large 2502 Platform: Mistral Id: mistralai/pixtral-large-2502 URL: https://thebestmodelfor.com/models/mistralai--pixtral-large-2502 OpenRouter: https://openrouter.ai/mistralai/pixtral-large-2502 Kind: chat Listed: 2026-11-20 Context tokens: 128000 Max output tokens: 102400 Input USD per million: 2 Output USD per million: 6 Input per token (published): 0.000002 Output per token (published): 0.000006 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: image, text Output modalities: text Tools: Not listed Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Pixtral Large 2502 is the February 2025 version of Mistral AI's large multimodal model, following Pixtral Large 2411. It accepts text and image input, including documents, charts, and natural images,... Checked: 20 Nov 2026 ## Voxtral Mini 3B 2507 Platform: Mistral Id: mistralai/voxtral-mini-3b-2507 URL: https://thebestmodelfor.com/models/mistralai--voxtral-mini-3b-2507 OpenRouter: https://openrouter.ai/mistralai/voxtral-mini-3b-2507 Kind: transcription Listed: 2026-08-13 Context tokens: unknown Max output tokens: unknown Input USD per million: 16.6667 Output USD per million: 0 Input per token (published): 0.0000166667 Output per token (published): 0 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: audio Output modalities: transcription Tools: Not listed Open weights: Yes (mistralai/Voxtral-Mini-3B-2507) Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Voxtral Mini 3B 2507 is a speech and audio understanding model from Mistral AI. It is suited for transcription, translation, and compact audio processing workloads. Checked: 20 Nov 2026 ## Voxtral Mini Transcribe Platform: Mistral Id: mistralai/voxtral-mini-transcribe URL: https://thebestmodelfor.com/models/mistralai--voxtral-mini-transcribe OpenRouter: https://openrouter.ai/mistralai/voxtral-mini-transcribe Kind: transcription Listed: 2026-05-15 Context tokens: 16384 Max output tokens: 13107 Input USD per million: 50 Output USD per million: 0 Input per token (published): 0.00005 Output per token (published): 0 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: audio Output modalities: transcription Tools: Not listed Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Voxtral Mini Transcribe is Mistral's speech-to-text model, derived from the Voxtral Mini family. It accepts audio input and returns transcribed text via the standard transcription API. Suited for transcribing meetings,... Checked: 20 Nov 2026 ## Voxtral Mini Transcribe 3 Platform: Mistral Id: mistralai/voxtral-mini-transcribe-3-0 URL: https://thebestmodelfor.com/models/mistralai--voxtral-mini-transcribe-3-0 OpenRouter: https://openrouter.ai/mistralai/voxtral-mini-transcribe-3-0 Kind: transcription Listed: 2026-10-20 Context tokens: 65536 Max output tokens: 52428 Input USD per million: 58.3333 Output USD per million: 0 Input per token (published): 0.0000583333 Output per token (published): 0 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: audio Output modalities: transcription Tools: Not listed Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Voxtral Mini Transcribe 3 is Mistral's compact speech-to-text model. It takes audio input and returns a transcript with timestamps and speaker diarization. It also supports context biasing for domain terms.... Checked: 20 Nov 2026 ## Voxtral Mini TTS Platform: Mistral Id: mistralai/voxtral-mini-tts-2603 URL: https://thebestmodelfor.com/models/mistralai--voxtral-mini-tts-2603 OpenRouter: https://openrouter.ai/mistralai/voxtral-mini-tts-2603 Kind: speech Listed: 2026-04-19 Context tokens: 4096 Max output tokens: 3276 Input USD per million: 16 Output USD per million: 0 Input per token (published): 0.000016 Output per token (published): 0 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: text Output modalities: speech Tools: Not listed Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Voxtral Mini TTS is Mistral's text-to-speech model featuring zero-shot voice cloning and multilingual support. It converts text input into natural-sounding audio output. Checked: 20 Nov 2026 ## Voxtral TTS 3 Platform: Mistral Id: mistralai/voxtral-mini-tts-3-0 URL: https://thebestmodelfor.com/models/mistralai--voxtral-mini-tts-3-0 OpenRouter: https://openrouter.ai/mistralai/voxtral-mini-tts-3-0 Kind: speech Listed: 2026-10-20 Context tokens: 4096 Max output tokens: 3276 Input USD per million: 13 Output USD per million: 0 Input per token (published): 0.000013 Output per token (published): 0 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: text Output modalities: speech Tools: Not listed Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Voxtral TTS 3 is Mistral's text-to-speech model. It converts text into natural-sounding speech, offers a library of preset voices, supports zero-shot voice cloning, and accepts emotion and pace tags in... Checked: 20 Nov 2026 ## Voxtral Small 24B 2507 Platform: Mistral Id: mistralai/voxtral-small-24b-2507 URL: https://thebestmodelfor.com/models/mistralai--voxtral-small-24b-2507 OpenRouter: https://openrouter.ai/mistralai/voxtral-small-24b-2507 Kind: chat Listed: 2025-10-30 Context tokens: 32768 Max output tokens: 26214 Input USD per million: 0.1 Output USD per million: 0.3 Input per token (published): 0.0000001 Output per token (published): 0.0000003 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: audio=0.0001, input_cache_read=0.00000001 Input modalities: audio, file, text Output modalities: text Tools: Yes Open weights: Yes (mistralai/Voxtral-Small-24B-2507) Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: reviewed 2026-11-19 — Voxtral Small is listed with audio input and a public weights id. OpenRouter describes it for transcription, translation, and audio understanding. It returns text. It does not speak. Listing blurb: Voxtral Small is an enhancement of Mistral Small 3, incorporating state-of-the-art audio input capabilities while retaining best-in-class text performance. It excels at speech transcription, translation and audio understanding. Input audio... Checked: 20 Nov 2026 ## Voxtral Small 24B 2507 STT Platform: Mistral Id: mistralai/voxtral-small-24b-2507-stt URL: https://thebestmodelfor.com/models/mistralai--voxtral-small-24b-2507-stt OpenRouter: https://openrouter.ai/mistralai/voxtral-small-24b-2507-stt Kind: transcription Listed: 2026-08-13 Context tokens: unknown Max output tokens: unknown Input USD per million: 50 Output USD per million: 0 Input per token (published): 0.00005 Output per token (published): 0 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: audio Output modalities: transcription Tools: Not listed Open weights: Yes (mistralai/Voxtral-Small-24B-2507) Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Voxtral Small 24B 2507 STT is a speech transcription model from Mistral AI. It is suited for transcription, translation, and audio understanding workloads that benefit from its larger model capacity. Checked: 20 Nov 2026 ## Voxtral Small Transcribe 3 Platform: Mistral Id: mistralai/voxtral-small-transcribe-3-0 URL: https://thebestmodelfor.com/models/mistralai--voxtral-small-transcribe-3-0 OpenRouter: https://openrouter.ai/mistralai/voxtral-small-transcribe-3-0 Kind: transcription Listed: 2026-10-20 Context tokens: 65536 Max output tokens: 52428 Input USD per million: 66.6667 Output USD per million: 0 Input per token (published): 0.0000666667 Output per token (published): 0 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: audio Output modalities: transcription Tools: Not listed Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Voxtral Small Transcribe 3 is Mistral's flagship speech-to-text model. It takes audio input and returns a transcript with timestamps and speaker diarization, and supports context biasing for domain-specific vocabulary. Suited... Checked: 20 Nov 2026 ## DeepSeek V3 Platform: DeepSeek Id: deepseek/deepseek-chat URL: https://thebestmodelfor.com/models/deepseek--deepseek-chat OpenRouter: https://openrouter.ai/deepseek/deepseek-chat Kind: chat Listed: 2024-12-26 Context tokens: 163840 Max output tokens: 16000 Input USD per million: 0.2574 Output USD per million: 1.0287 Input per token (published): 0.0000002574 Output per token (published): 0.0000010287 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: text Output modalities: text Tools: Yes Open weights: Yes (deepseek-ai/DeepSeek-V3) Knowledge cutoff: 2024-07-31 Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tokens, the reported evaluations... Checked: 20 Nov 2026 ## DeepSeek V3 0324 Platform: DeepSeek Id: deepseek/deepseek-chat-v3-0324 URL: https://thebestmodelfor.com/models/deepseek--deepseek-chat-v3-0324 OpenRouter: https://openrouter.ai/deepseek/deepseek-chat-v3-0324 Kind: chat Listed: 2025-03-24 Context tokens: 163840 Max output tokens: 115200 Input USD per million: 0.29 Output USD per million: 1.14 Input per token (published): 0.00000029 Output per token (published): 0.00000114 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: input_cache_read=0.00000011 Input modalities: text Output modalities: text Tools: Yes Open weights: Yes (deepseek-ai/DeepSeek-V3-0324) Knowledge cutoff: 2024-07-31 Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the DeepSeek V3 model and performs really well... Checked: 20 Nov 2026 ## DeepSeek V3.1 Platform: DeepSeek Id: deepseek/deepseek-chat-v3.1 URL: https://thebestmodelfor.com/models/deepseek--deepseek-chat-v3.1 OpenRouter: https://openrouter.ai/deepseek/deepseek-chat-v3.1 Kind: chat Listed: 2025-08-21 Context tokens: 163840 Max output tokens: 147456 Input USD per million: 0.25 Output USD per million: 0.95 Input per token (published): 0.00000025 Output per token (published): 0.00000095 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: input_cache_read=0.00000013 Input modalities: text Output modalities: text Tools: Yes Open weights: Yes (deepseek-ai/DeepSeek-V3.1) Knowledge cutoff: 2025-03-31 Reasoning: optional Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context... Checked: 20 Nov 2026 ## R1 0528 Platform: DeepSeek Id: deepseek/deepseek-r1-0528 URL: https://thebestmodelfor.com/models/deepseek--deepseek-r1-0528 OpenRouter: https://openrouter.ai/deepseek/deepseek-r1-0528 Kind: chat Listed: 2025-05-28 Context tokens: 163840 Max output tokens: 32000 Input USD per million: 0.571 Output USD per million: 2.286 Input per token (published): 0.000000571 Output per token (published): 0.000002286 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: text Output modalities: text Tools: Yes Open weights: Yes (deepseek-ai/DeepSeek-R1-0528) Knowledge cutoff: 2025-03-31 Reasoning: required Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: May 28th update to the original DeepSeek R1 Performance on par with OpenAI o1, but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active... Checked: 20 Nov 2026 ## DeepSeek V3.1 Terminus Platform: DeepSeek Id: deepseek/deepseek-v3.1-terminus URL: https://thebestmodelfor.com/models/deepseek--deepseek-v3.1-terminus OpenRouter: https://openrouter.ai/deepseek/deepseek-v3.1-terminus Kind: chat Listed: 2025-09-22 Context tokens: 163840 Max output tokens: 147456 Input USD per million: 0.27 Output USD per million: 1 Input per token (published): 0.00000027 Output per token (published): 0.000001 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: text Output modalities: text Tools: Yes Open weights: Yes (deepseek-ai/DeepSeek-V3.1-Terminus) Knowledge cutoff: 2025-03-31 Reasoning: optional Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: DeepSeek-V3.1 Terminus is an update to DeepSeek V3.1 that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further optimizing the model's... Checked: 20 Nov 2026 ## DeepSeek V3.2 Platform: DeepSeek Id: deepseek/deepseek-v3.2 URL: https://thebestmodelfor.com/models/deepseek--deepseek-v3.2 OpenRouter: https://openrouter.ai/deepseek/deepseek-v3.2 Kind: chat Listed: 2025-12-01 Context tokens: 163840 Max output tokens: 147456 Input USD per million: 0.26 Output USD per million: 0.38 Input per token (published): 0.00000026 Output per token (published): 0.00000038 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: input_cache_read=0.00000013 Input modalities: text Output modalities: text Tools: Yes Open weights: Yes (deepseek-ai/DeepSeek-V3.2) Knowledge cutoff: unknown Reasoning: optional Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism... Checked: 20 Nov 2026 ## DeepSeek V3.2 Exp Platform: DeepSeek Id: deepseek/deepseek-v3.2-exp URL: https://thebestmodelfor.com/models/deepseek--deepseek-v3.2-exp OpenRouter: https://openrouter.ai/deepseek/deepseek-v3.2-exp Kind: chat Listed: 2025-09-29 Context tokens: 163840 Max output tokens: 147456 Input USD per million: 0.27 Output USD per million: 0.41 Input per token (published): 0.00000027 Output per token (published): 0.00000041 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: text Output modalities: text Tools: Yes Open weights: Yes (deepseek-ai/DeepSeek-V3.2-Exp) Knowledge cutoff: 2025-07-31 Reasoning: optional Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism... Checked: 20 Nov 2026 ## DeepSeek V4 Flash 0423 Platform: DeepSeek Id: deepseek/deepseek-v4-flash URL: https://thebestmodelfor.com/models/deepseek--deepseek-v4-flash OpenRouter: https://openrouter.ai/deepseek/deepseek-v4-flash Kind: chat Listed: 2026-04-24 Context tokens: 1048576 Max output tokens: 393216 Input USD per million: 0.09 Output USD per million: 0.18 Input per token (published): 0.00000009 Output per token (published): 0.00000018 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: input_cache_read=0.000000018 Input modalities: text Output modalities: text Tools: Yes Open weights: Yes (deepseek-ai/DeepSeek-V4-Flash) Knowledge cutoff: unknown Reasoning: optional Third-party intelligence index: unknown Third-party coding index: unknown Guide: reviewed 2026-11-19 — The April 2026 V4 Flash row is the cheapest reviewed text model with a million-token window and open weights. It does not accept images. Use it for bulk text. Listing blurb: DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and... Checked: 20 Nov 2026 ## DeepSeek V4 Flash 0731 Platform: DeepSeek Id: deepseek/deepseek-v4-flash-0731 URL: https://thebestmodelfor.com/models/deepseek--deepseek-v4-flash-0731 OpenRouter: https://openrouter.ai/deepseek/deepseek-v4-flash-0731 Kind: chat Listed: 2026-07-31 Context tokens: 1048576 Max output tokens: 943718 Input USD per million: 0.0443 Output USD per million: 0.3 Input per token (published): 0.0000000443 Output per token (published): 0.0000003 Batch input USD per million: 0.048 Batch output USD per million: 0.144 Other raw prices: input_cache_read=0.000000035 Input modalities: text Output modalities: text Tools: Yes Open weights: Yes (deepseek-ai/DeepSeek-V4-Flash-0731) Knowledge cutoff: unknown Reasoning: optional Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows.... Checked: 20 Nov 2026 ## DeepSeek V4 Flash Vision Exp Platform: DeepSeek Id: deepseek/deepseek-v4-flash-vision-exp URL: https://thebestmodelfor.com/models/deepseek--deepseek-v4-flash-vision-exp OpenRouter: https://openrouter.ai/deepseek/deepseek-v4-flash-vision-exp Kind: chat Listed: 2026-08-21 Context tokens: 1048576 Max output tokens: 943717 Input USD per million: 0.44 Output USD per million: 1.32 Input per token (published): 0.00000044 Output per token (published): 0.00000132 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: input_cache_read=0.000000014 Input modalities: image, text Output modalities: text Tools: Yes Open weights: Yes (deepseek-ai/DeepSeek-V4-Flash-Vision-Exp) Knowledge cutoff: unknown Reasoning: optional Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of DeepSeek V4 Flash 0731 from DeepSeek, adding image understanding while matching the base model on text capabilities including agents,... Checked: 20 Nov 2026 ## DeepSeek V4 Pro 0423 Platform: DeepSeek Id: deepseek/deepseek-v4-pro URL: https://thebestmodelfor.com/models/deepseek--deepseek-v4-pro OpenRouter: https://openrouter.ai/deepseek/deepseek-v4-pro Kind: chat Listed: 2026-04-24 Context tokens: 1048576 Max output tokens: 393216 Input USD per million: 0.9 Output USD per million: 1.5 Input per token (published): 0.0000009 Output per token (published): 0.0000015 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: input_cache_read=0.0000002 Input modalities: text Output modalities: text Tools: Yes Open weights: Yes (deepseek-ai/DeepSeek-V4-Pro) Knowledge cutoff: unknown Reasoning: optional Third-party intelligence index: 20.8 Third-party coding index: unknown Guide: reviewed 2026-11-19 — OpenRouter describes the April V4 Pro row as a very large mixture-of-experts for advanced reasoning and coding, with open weights and a million-token window. Do not read the name as a leaderboard. On this feed its third-party intelligence index is lower than the October V4.1 Flash snapshot, and the token rate is higher. Listing blurb: DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,... Checked: 20 Nov 2026 ## DeepSeek V4 Pro 0813 Platform: DeepSeek Id: deepseek/deepseek-v4-pro-0813 URL: https://thebestmodelfor.com/models/deepseek--deepseek-v4-pro-0813 OpenRouter: https://openrouter.ai/deepseek/deepseek-v4-pro-0813 Kind: chat Listed: 2026-08-12 Context tokens: 1048576 Max output tokens: 943718 Input USD per million: 1.32 Output USD per million: 3.96 Input per token (published): 0.00000132 Output per token (published): 0.00000396 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: input_cache_read=0.000000044 Input modalities: text Output modalities: text Tools: Yes Open weights: Yes (deepseek-ai/DeepSeek-V4-Pro-0813) Knowledge cutoff: unknown Reasoning: optional Third-party intelligence index: 23.1 Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro. Checked: 20 Nov 2026 ## DeepSeek V4.1 Flash Platform: DeepSeek Id: deepseek/deepseek-v4.1-flash URL: https://thebestmodelfor.com/models/deepseek--deepseek-v4.1-flash OpenRouter: https://openrouter.ai/deepseek/deepseek-v4.1-flash Kind: chat Listed: 2026-09-10 Context tokens: 1048576 Max output tokens: 943718 Input USD per million: 0.3 Output USD per million: 1.2 Input per token (published): 0.0000003 Output per token (published): 0.0000012 Batch input USD per million: 0.05 Batch output USD per million: 0.15 Other raw prices: input_cache_read=0.000000006 Input modalities: image, text Output modalities: text Tools: Yes Open weights: Yes (deepseek-ai/DeepSeek-V4.1-Flash) Knowledge cutoff: unknown Reasoning: optional Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on... Checked: 20 Nov 2026 ## DeepSeek V4.1 Flash 1017 Platform: DeepSeek Id: deepseek/deepseek-v4.1-flash-1017 URL: https://thebestmodelfor.com/models/deepseek--deepseek-v4.1-flash-1017 OpenRouter: https://openrouter.ai/deepseek/deepseek-v4.1-flash-1017 Kind: chat Listed: 2026-10-17 Context tokens: 1048576 Max output tokens: 393216 Input USD per million: 0.15 Output USD per million: 0.6 Input per token (published): 0.00000015 Output per token (published): 0.0000006 Batch input USD per million: 0.035 Batch output USD per million: 0.149 Other raw prices: input_cache_read=0.000000003 Input modalities: image, text Output modalities: text Tools: Yes Open weights: Yes (deepseek-ai/DeepSeek-V4.1-Flash-1017) Knowledge cutoff: unknown Reasoning: optional Third-party intelligence index: 32.6 Third-party coding index: unknown Guide: reviewed 2026-11-19 — This is the 17 October 2026 snapshot of DeepSeek V4.1 Flash. It is open weights, accepts images, lists about a million tokens of context, and is priced like a budget model. On this feed its third-party intelligence index is higher than the April V4 Pro row. That index is not our measurement. It is a reason to try this snapshot first. Listing blurb: DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the deepseek-flash API model name. V4.1 Flash is a sparse mixture-of-experts model... Checked: 20 Nov 2026 ## Qwen2.5 72B Instruct Platform: Alibaba (Qwen) Id: qwen/qwen-2.5-72b-instruct URL: https://thebestmodelfor.com/models/qwen--qwen-2.5-72b-instruct OpenRouter: https://openrouter.ai/qwen/qwen-2.5-72b-instruct Kind: chat Listed: 2024-09-19 Context tokens: 32768 Max output tokens: 16384 Input USD per million: 0.36 Output USD per million: 0.4 Input per token (published): 0.00000036 Output per token (published): 0.0000004 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: text Output modalities: text Tools: Yes Open weights: Yes (Qwen/Qwen2.5-72B-Instruct) Knowledge cutoff: 2024-06-30 Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Qwen2.5 72B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and... Checked: 20 Nov 2026 ## Qwen2.5 Coder 32B Instruct Platform: Alibaba (Qwen) Id: qwen/qwen-2.5-coder-32b-instruct URL: https://thebestmodelfor.com/models/qwen--qwen-2.5-coder-32b-instruct OpenRouter: https://openrouter.ai/qwen/qwen-2.5-coder-32b-instruct Kind: chat Listed: 2024-11-11 Context tokens: 32768 Max output tokens: 29491 Input USD per million: 0.66 Output USD per million: 1 Input per token (published): 0.00000066 Output per token (published): 0.000001 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: text Output modalities: text Tools: Not listed Open weights: Yes (Qwen/Qwen2.5-Coder-32B-Instruct) Knowledge cutoff: 2024-06-30 Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). Qwen2.5-Coder brings the following improvements upon CodeQwen1.5: - Significantly improvements in code generation, code reasoning... Checked: 20 Nov 2026 ## Qwen-Audio-3.0-TTS Flash Platform: Alibaba (Qwen) Id: qwen/qwen-audio-3.0-tts-flash URL: https://thebestmodelfor.com/models/qwen--qwen-audio-3.0-tts-flash OpenRouter: https://openrouter.ai/qwen/qwen-audio-3.0-tts-flash Kind: speech Listed: 2026-07-23 Context tokens: unknown Max output tokens: unknown Input USD per million: 15 Output USD per million: 0 Input per token (published): 0.000015 Output per token (published): 0 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: text Output modalities: speech Tools: Not listed Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Qwen-Audio-3.0-TTS Flash is Alibaba's fast, cost-efficient text-to-speech model, generating spoken audio from text via the DashScope Speech Synthesizer API. Checked: 20 Nov 2026 ## Qwen-Audio-3.0-TTS Plus Platform: Alibaba (Qwen) Id: qwen/qwen-audio-3.0-tts-plus URL: https://thebestmodelfor.com/models/qwen--qwen-audio-3.0-tts-plus OpenRouter: https://openrouter.ai/qwen/qwen-audio-3.0-tts-plus Kind: speech Listed: 2026-07-23 Context tokens: unknown Max output tokens: unknown Input USD per million: 20 Output USD per million: 0 Input per token (published): 0.00002 Output per token (published): 0 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: text Output modalities: speech Tools: Not listed Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Qwen-Audio-3.0-TTS Plus is Alibaba's higher-quality text-to-speech model, generating spoken audio from text via the DashScope Speech Synthesizer API. Checked: 20 Nov 2026 ## Qwen Image 2.1 Pro Platform: Alibaba (Qwen) Id: qwen/qwen-image-2.1-pro URL: https://thebestmodelfor.com/models/qwen--qwen-image-2.1-pro OpenRouter: https://openrouter.ai/qwen/qwen-image-2.1-pro Kind: image Listed: 2026-10-16 Context tokens: 65536 Max output tokens: 58982 Input USD per million: 0 Output USD per million: 0 Input per token (published): 0 Output per token (published): 0 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: image=0, image_token=0.0000110179640718563, image_output=0.0000110179640718563 Input modalities: image, text Output modalities: image Tools: Not listed Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Qwen Image 2.1 Pro is an image generation and editing model from Qwen, the higher-quality tier of the Qwen Image 2.1 series. Choose it over Qwen Image 2.1 Turbo when... Checked: 20 Nov 2026 ## Qwen Image 2.1 Turbo Platform: Alibaba (Qwen) Id: qwen/qwen-image-2.1-turbo URL: https://thebestmodelfor.com/models/qwen--qwen-image-2.1-turbo OpenRouter: https://openrouter.ai/qwen/qwen-image-2.1-turbo Kind: image Listed: 2026-10-16 Context tokens: 65536 Max output tokens: 58982 Input USD per million: 0 Output USD per million: 0 Input per token (published): 0 Output per token (published): 0 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: image=0, image_token=0.00000440718562874251, image_output=0.00000440718562874251 Input modalities: image, text Output modalities: image Tools: Not listed Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Qwen Image 2.1 Turbo is the fast, lower-cost tier of the Qwen Image 2.1 series from Qwen, for image generation and editing where throughput and price matter more than peak... Checked: 20 Nov 2026 ## Qwen Image 3 Platform: Alibaba (Qwen) Id: qwen/qwen-image-3 URL: https://thebestmodelfor.com/models/qwen--qwen-image-3 OpenRouter: https://openrouter.ai/qwen/qwen-image-3 Kind: image Listed: 2026-08-05 Context tokens: 65536 Max output tokens: 58982 Input USD per million: 0 Output USD per million: 0 Input per token (published): 0 Output per token (published): 0 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: image=0.003, image_token=0.00000718562874251497, image_output=0.00000718562874251497 Input modalities: image, text Output modalities: image Tools: Not listed Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Qwen Image 3 is a unified image generation and editing model from Qwen. It supports precise rendering of text and details as small as 10px, along with a richer world... Checked: 20 Nov 2026 ## Qwen Image 3 Pro Platform: Alibaba (Qwen) Id: qwen/qwen-image-3-pro URL: https://thebestmodelfor.com/models/qwen--qwen-image-3-pro OpenRouter: https://openrouter.ai/qwen/qwen-image-3-pro Kind: image Listed: 2026-08-05 Context tokens: 65536 Max output tokens: 58982 Input USD per million: 0 Output USD per million: 0 Input per token (published): 0 Output per token (published): 0 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: image=0.003, image_token=0.00000958083832335329, image_output=0.00000958083832335329 Input modalities: image, text Output modalities: image Tools: Not listed Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Qwen Image 3 Pro is an image generation and editing model from Qwen. It supports precise rendering of text and details as small as 10px, along with richer world knowledge... Checked: 20 Nov 2026 ## Qwen-Plus Platform: Alibaba (Qwen) Id: qwen/qwen-plus URL: https://thebestmodelfor.com/models/qwen--qwen-plus OpenRouter: https://openrouter.ai/qwen/qwen-plus Kind: chat Listed: 2025-02-01 Context tokens: 1000000 Max output tokens: 32768 Input USD per million: 0.26 Output USD per million: 0.78 Input per token (published): 0.00000026 Output per token (published): 0.00000078 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: input_cache_read=0.000000052, input_cache_write=0.000000325 Input modalities: text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: 2025-03-31 Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Qwen-Plus, based on the Qwen2.5 foundation model, is a 131K context model with a balanced performance, speed, and cost combination. Checked: 20 Nov 2026 ## Qwen2.5 VL 72B Instruct Platform: Alibaba (Qwen) Id: qwen/qwen2.5-vl-72b-instruct URL: https://thebestmodelfor.com/models/qwen--qwen2.5-vl-72b-instruct OpenRouter: https://openrouter.ai/qwen/qwen2.5-vl-72b-instruct Kind: chat Listed: 2025-02-01 Context tokens: 128000 Max output tokens: 115200 Input USD per million: 0.8 Output USD per million: 1 Input per token (published): 0.0000008 Output per token (published): 0.000001 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: input_cache_read=0.0000004 Input modalities: image, text Output modalities: text Tools: Not listed Open weights: Yes (Qwen/Qwen2.5-VL-72B-Instruct) Knowledge cutoff: 2024-06-30 Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Qwen2.5-VL is proficient in recognizing common objects such as flowers, birds, fish, and insects. It is also highly capable of analyzing texts, charts, icons, graphics, and layouts within images. Checked: 20 Nov 2026 ## Qwen3 14B Platform: Alibaba (Qwen) Id: qwen/qwen3-14b URL: https://thebestmodelfor.com/models/qwen--qwen3-14b OpenRouter: https://openrouter.ai/qwen/qwen3-14b Kind: chat Listed: 2025-04-28 Context tokens: 40960 Max output tokens: 16384 Input USD per million: 0.12 Output USD per million: 0.24 Input per token (published): 0.00000012 Output per token (published): 0.00000024 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: text Output modalities: text Tools: Yes Open weights: Yes (Qwen/Qwen3-14B) Knowledge cutoff: 2025-03-31 Reasoning: optional Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Qwen3-14B is a dense 14.8B parameter causal language model from the Qwen3 series, designed for both complex reasoning and efficient dialogue. It supports seamless switching between a "thinking" mode for... Checked: 20 Nov 2026 ## Qwen3 235B A22B Instruct 2507 Platform: Alibaba (Qwen) Id: qwen/qwen3-235b-a22b-2507 URL: https://thebestmodelfor.com/models/qwen--qwen3-235b-a22b-2507 OpenRouter: https://openrouter.ai/qwen/qwen3-235b-a22b-2507 Kind: chat Listed: 2025-07-21 Context tokens: 262144 Max output tokens: 117964 Input USD per million: 0.14 Output USD per million: 0.8 Input per token (published): 0.00000014 Output per token (published): 0.0000008 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: input_cache_read=0.00000005 Input modalities: text Output modalities: text Tools: Yes Open weights: Yes (Qwen/Qwen3-235B-A22B-Instruct-2507) Knowledge cutoff: 2025-06-30 Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture, with 22B active parameters per forward pass. It is optimized for general-purpose text generation, including instruction following,... Checked: 20 Nov 2026 ## Qwen3 235B A22B Thinking 2507 Platform: Alibaba (Qwen) Id: qwen/qwen3-235b-a22b-thinking-2507 URL: https://thebestmodelfor.com/models/qwen--qwen3-235b-a22b-thinking-2507 OpenRouter: https://openrouter.ai/qwen/qwen3-235b-a22b-thinking-2507 Kind: chat Listed: 2025-07-25 Context tokens: 128000 Max output tokens: 16384 Input USD per million: 0.45 Output USD per million: 3.5 Input per token (published): 0.00000045 Output per token (published): 0.0000035 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: text Output modalities: text Tools: Yes Open weights: Yes (Qwen/Qwen3-235B-A22B-Thinking-2507) Knowledge cutoff: 2025-06-30 Reasoning: required Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively supports up to 262,144... Checked: 20 Nov 2026 ## Qwen3 30B A3B Platform: Alibaba (Qwen) Id: qwen/qwen3-30b-a3b URL: https://thebestmodelfor.com/models/qwen--qwen3-30b-a3b OpenRouter: https://openrouter.ai/qwen/qwen3-30b-a3b Kind: chat Listed: 2025-04-28 Context tokens: 40960 Max output tokens: 16384 Input USD per million: 0.12 Output USD per million: 0.5 Input per token (published): 0.00000012 Output per token (published): 0.0000005 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: text Output modalities: text Tools: Yes Open weights: Yes (Qwen/Qwen3-30B-A3B) Knowledge cutoff: 2025-03-31 Reasoning: optional Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks. Its unique... Checked: 20 Nov 2026 ## Qwen3 30B A3B Instruct 2507 Platform: Alibaba (Qwen) Id: qwen/qwen3-30b-a3b-instruct-2507 URL: https://thebestmodelfor.com/models/qwen--qwen3-30b-a3b-instruct-2507 OpenRouter: https://openrouter.ai/qwen/qwen3-30b-a3b-instruct-2507 Kind: chat Listed: 2025-07-29 Context tokens: 262144 Max output tokens: 235929 Input USD per million: 0.1 Output USD per million: 0.3 Input per token (published): 0.0000001 Output per token (published): 0.0000003 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: input_cache_read=0.0000001 Input modalities: text Output modalities: text Tools: Yes Open weights: Yes (Qwen/Qwen3-30B-A3B-Instruct-2507) Knowledge cutoff: 2025-06-30 Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference. It operates in non-thinking mode and is designed for high-quality instruction following, multilingual understanding, and... Checked: 20 Nov 2026 ## Qwen3 32B Platform: Alibaba (Qwen) Id: qwen/qwen3-32b URL: https://thebestmodelfor.com/models/qwen--qwen3-32b OpenRouter: https://openrouter.ai/qwen/qwen3-32b Kind: chat Listed: 2025-04-28 Context tokens: 131072 Max output tokens: 16384 Input USD per million: 0.08 Output USD per million: 0.28 Input per token (published): 0.00000008 Output per token (published): 0.00000028 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: text Output modalities: text Tools: Yes Open weights: Yes (Qwen/Qwen3-32B) Knowledge cutoff: 2025-03-31 Reasoning: optional Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Qwen3-32B is a dense 32.8B parameter causal language model from the Qwen3 series, optimized for both complex reasoning and efficient dialogue. It supports seamless switching between a "thinking" mode for... Checked: 20 Nov 2026 ## Qwen3 ASR 0.6B Platform: Alibaba (Qwen) Id: qwen/qwen3-asr-0.6b URL: https://thebestmodelfor.com/models/qwen--qwen3-asr-0.6b OpenRouter: https://openrouter.ai/qwen/qwen3-asr-0.6b Kind: transcription Listed: 2026-08-13 Context tokens: unknown Max output tokens: unknown Input USD per million: 3.33 Output USD per million: 0 Input per token (published): 0.00000333 Output per token (published): 0 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: audio Output modalities: transcription Tools: Not listed Open weights: Yes (Qwen/Qwen3-ASR-0.6B) Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Qwen3 ASR 0.6B is a compact automatic speech recognition model from Qwen. It supports multilingual language identification and transcription across 30 languages and 22 Chinese dialects, with streaming and offline... Checked: 20 Nov 2026 ## Qwen3 ASR 1.7B Platform: Alibaba (Qwen) Id: qwen/qwen3-asr-1.7b URL: https://thebestmodelfor.com/models/qwen--qwen3-asr-1.7b OpenRouter: https://openrouter.ai/qwen/qwen3-asr-1.7b Kind: transcription Listed: 2026-08-13 Context tokens: unknown Max output tokens: unknown Input USD per million: 7.5 Output USD per million: 0 Input per token (published): 0.0000075 Output per token (published): 0 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: audio Output modalities: transcription Tools: Not listed Open weights: Yes (Qwen/Qwen3-ASR-1.7B) Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Qwen3 ASR 1.7B is an automatic speech recognition model from Qwen. It supports multilingual language identification and transcription across 30 languages and 22 Chinese dialects, with streaming and offline inference... Checked: 20 Nov 2026 ## Qwen3 Coder 480B A35B Platform: Alibaba (Qwen) Id: qwen/qwen3-coder URL: https://thebestmodelfor.com/models/qwen--qwen3-coder OpenRouter: https://openrouter.ai/qwen/qwen3-coder Kind: chat Listed: 2025-07-23 Context tokens: 262144 Max output tokens: 65536 Input USD per million: 0.3 Output USD per million: 1 Input per token (published): 0.0000003 Output per token (published): 0.000001 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: input_cache_read=0.0000001 Input modalities: text Output modalities: text Tools: Yes Open weights: Yes (Qwen/Qwen3-Coder-480B-A35B-Instruct) Knowledge cutoff: 2025-06-30 Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over... Checked: 20 Nov 2026 ## Qwen3 Coder 30B A3B Instruct Platform: Alibaba (Qwen) Id: qwen/qwen3-coder-30b-a3b-instruct URL: https://thebestmodelfor.com/models/qwen--qwen3-coder-30b-a3b-instruct OpenRouter: https://openrouter.ai/qwen/qwen3-coder-30b-a3b-instruct Kind: chat Listed: 2025-07-31 Context tokens: 262144 Max output tokens: 235929 Input USD per million: 0.15 Output USD per million: 0.6 Input per token (published): 0.00000015 Output per token (published): 0.0000006 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: text Output modalities: text Tools: Yes Open weights: Yes (Qwen/Qwen3-Coder-30B-A3B-Instruct) Knowledge cutoff: 2025-06-30 Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for advanced code generation, repository-scale understanding, and agentic tool use. Built on the... Checked: 20 Nov 2026 ## Qwen3 Coder Flash Platform: Alibaba (Qwen) Id: qwen/qwen3-coder-flash URL: https://thebestmodelfor.com/models/qwen--qwen3-coder-flash OpenRouter: https://openrouter.ai/qwen/qwen3-coder-flash Kind: chat Listed: 2025-09-17 Context tokens: 1000000 Max output tokens: 65536 Input USD per million: 0.195 Output USD per million: 0.975 Input per token (published): 0.000000195 Output per token (published): 0.000000975 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: input_cache_read=0.000000039, input_cache_write=0.00000024375 Input modalities: text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: 2025-06-30 Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Qwen3 Coder Flash is Alibaba's fast and cost efficient version of their proprietary Qwen3 Coder Plus. It is a powerful coding agent model specializing in autonomous programming via tool calling... Checked: 20 Nov 2026 ## Qwen3 Coder Next Platform: Alibaba (Qwen) Id: qwen/qwen3-coder-next URL: https://thebestmodelfor.com/models/qwen--qwen3-coder-next OpenRouter: https://openrouter.ai/qwen/qwen3-coder-next Kind: chat Listed: 2026-02-04 Context tokens: 262144 Max output tokens: 235929 Input USD per million: 0.12 Output USD per million: 0.8 Input per token (published): 0.00000012 Output per token (published): 0.0000008 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: input_cache_read=0.00000007 Input modalities: text Output modalities: text Tools: Yes Open weights: Yes (Qwen/Qwen3-Coder-Next) Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: reviewed 2026-11-19 — OpenRouter describes Qwen3 Coder Next as an open-weight model for coding agents and local development, with a sparse design that activates few parameters per token. Text in, text out. Paste the code. It will not see a screenshot. Listing blurb: Qwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows. It uses a sparse MoE design with 80B total parameters and only 3B activated per... Checked: 20 Nov 2026 ## Qwen3 Embedding 4B Platform: Alibaba (Qwen) Id: qwen/qwen3-embedding-4b URL: https://thebestmodelfor.com/models/qwen--qwen3-embedding-4b OpenRouter: https://openrouter.ai/qwen/qwen3-embedding-4b Kind: embeddings Listed: 2025-10-28 Context tokens: 32768 Max output tokens: 29491 Input USD per million: 0.02 Output USD per million: 0 Input per token (published): 0.00000002 Output per token (published): 0 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: text Output modalities: embeddings Tools: Not listed Open weights: Yes (Qwen/Qwen3-Embedding-4B) Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks. This series inherits the exceptional multilingual capabilities, long-text... Checked: 20 Nov 2026 ## Qwen3 Embedding 8B Platform: Alibaba (Qwen) Id: qwen/qwen3-embedding-8b URL: https://thebestmodelfor.com/models/qwen--qwen3-embedding-8b OpenRouter: https://openrouter.ai/qwen/qwen3-embedding-8b Kind: embeddings Listed: 2025-10-28 Context tokens: 40960 Max output tokens: 29491 Input USD per million: 0.01 Output USD per million: 0 Input per token (published): 0.00000001 Output per token (published): 0 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: text Output modalities: embeddings Tools: Not listed Open weights: Yes (Qwen/Qwen3-Embedding-8B) Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks. This series inherits the exceptional multilingual capabilities, long-text... Checked: 20 Nov 2026 ## Qwen3 Next 80B A3B Instruct Platform: Alibaba (Qwen) Id: qwen/qwen3-next-80b-a3b-instruct URL: https://thebestmodelfor.com/models/qwen--qwen3-next-80b-a3b-instruct OpenRouter: https://openrouter.ai/qwen/qwen3-next-80b-a3b-instruct Kind: chat Listed: 2025-09-11 Context tokens: 262144 Max output tokens: 235929 Input USD per million: 0.1 Output USD per million: 1.1 Input per token (published): 0.0000001 Output per token (published): 0.0000011 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: input_cache_read=0.00000007 Input modalities: text Output modalities: text Tools: Yes Open weights: Yes (Qwen/Qwen3-Next-80B-A3B-Instruct) Knowledge cutoff: 2025-09-30 Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. It targets complex tasks across reasoning, code generation, knowledge QA, and multilingual... Checked: 20 Nov 2026 ## Qwen3 Reranker 0.6B Platform: Alibaba (Qwen) Id: qwen/qwen3-reranker-0.6b URL: https://thebestmodelfor.com/models/qwen--qwen3-reranker-0.6b OpenRouter: https://openrouter.ai/qwen/qwen3-reranker-0.6b Kind: rerank Listed: 2026-08-26 Context tokens: 32768 Max output tokens: unknown Input USD per million: 0 Output USD per million: 0 Input per token (published): 0 Output per token (published): 0 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: text Output modalities: rerank Tools: Not listed Open weights: Yes (Qwen/Qwen3-Reranker-0.6B) Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Qwen3 Reranker 0.6B is the smallest text reranking model from Alibaba Cloud in the Qwen3 Reranker series. Built on the Qwen3 architecture, it evaluates query-document pairs to produce relevance scores... Checked: 20 Nov 2026 ## Qwen3 Reranker 8B Platform: Alibaba (Qwen) Id: qwen/qwen3-reranker-8b URL: https://thebestmodelfor.com/models/qwen--qwen3-reranker-8b OpenRouter: https://openrouter.ai/qwen/qwen3-reranker-8b Kind: rerank Listed: 2026-08-13 Context tokens: 40960 Max output tokens: unknown Input USD per million: 0 Output USD per million: 0 Input per token (published): 0 Output per token (published): 0 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: text Output modalities: rerank Tools: Not listed Open weights: Yes (Qwen/Qwen3-Reranker-8B) Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Qwen3 Reranker 8B is a text reranking model from Alibaba Cloud built on the Qwen3 architecture. It evaluates query-document pairs to produce relevance scores for use in retrieval and RAG... Checked: 20 Nov 2026 ## Qwen3 VL 235B A22B Instruct Platform: Alibaba (Qwen) Id: qwen/qwen3-vl-235b-a22b-instruct URL: https://thebestmodelfor.com/models/qwen--qwen3-vl-235b-a22b-instruct OpenRouter: https://openrouter.ai/qwen/qwen3-vl-235b-a22b-instruct Kind: chat Listed: 2025-09-23 Context tokens: 262144 Max output tokens: 32768 Input USD per million: 0.21 Output USD per million: 1.9 Input per token (published): 0.00000021 Output per token (published): 0.0000019 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: input_cache_read=0.0000001 Input modalities: image, text Output modalities: text Tools: Yes Open weights: Yes (Qwen/Qwen3-VL-235B-A22B-Instruct) Knowledge cutoff: 2025-03-31 Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video. The Instruct model targets general vision-language use (VQA, document parsing, chart/table... Checked: 20 Nov 2026 ## Qwen3 VL 30B A3B Instruct Platform: Alibaba (Qwen) Id: qwen/qwen3-vl-30b-a3b-instruct URL: https://thebestmodelfor.com/models/qwen--qwen3-vl-30b-a3b-instruct OpenRouter: https://openrouter.ai/qwen/qwen3-vl-30b-a3b-instruct Kind: chat Listed: 2025-10-06 Context tokens: 262144 Max output tokens: 16384 Input USD per million: 0.15 Output USD per million: 0.6 Input per token (published): 0.00000015 Output per token (published): 0.0000006 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: image, text Output modalities: text Tools: Yes Open weights: Yes (Qwen/Qwen3-VL-30B-A3B-Instruct) Knowledge cutoff: 2025-03-31 Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Qwen3-VL-30B-A3B-Instruct is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Instruct variant optimizes instruction-following for general multimodal tasks. It excels in perception... Checked: 20 Nov 2026 ## Qwen3 VL 8B Instruct Platform: Alibaba (Qwen) Id: qwen/qwen3-vl-8b-instruct URL: https://thebestmodelfor.com/models/qwen--qwen3-vl-8b-instruct OpenRouter: https://openrouter.ai/qwen/qwen3-vl-8b-instruct Kind: chat Listed: 2025-10-14 Context tokens: 262144 Max output tokens: 235929 Input USD per million: 0.25 Output USD per million: 0.75 Input per token (published): 0.00000025 Output per token (published): 0.00000075 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: input_cache_read=0.00000012 Input modalities: image, text Output modalities: text Tools: Yes Open weights: Yes (Qwen/Qwen3-VL-8B-Instruct) Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Qwen3-VL-8B-Instruct is a multimodal vision-language model from the Qwen3-VL series, built for high-fidelity understanding and reasoning across text, images, and video. It features improved multimodal fusion with Interleaved-MRoPE for long-horizon... Checked: 20 Nov 2026 ## Qwen3.5-122B-A10B Platform: Alibaba (Qwen) Id: qwen/qwen3.5-122b-a10b URL: https://thebestmodelfor.com/models/qwen--qwen3.5-122b-a10b OpenRouter: https://openrouter.ai/qwen/qwen3.5-122b-a10b Kind: chat Listed: 2026-02-25 Context tokens: 262144 Max output tokens: 65536 Input USD per million: 0.26 Output USD per million: 2.08 Input per token (published): 0.00000026 Output per token (published): 0.00000208 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: image, text, video Output modalities: text Tools: Yes Open weights: Yes (Qwen/Qwen3.5-122B-A10B) Knowledge cutoff: unknown Reasoning: optional Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: The Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. In terms of... Checked: 20 Nov 2026 ## Qwen3.5-27B Platform: Alibaba (Qwen) Id: qwen/qwen3.5-27b URL: https://thebestmodelfor.com/models/qwen--qwen3.5-27b OpenRouter: https://openrouter.ai/qwen/qwen3.5-27b Kind: chat Listed: 2026-02-25 Context tokens: 262144 Max output tokens: 65536 Input USD per million: 0.195 Output USD per million: 1.56 Input per token (published): 0.000000195 Output per token (published): 0.00000156 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: image, text, video Output modalities: text Tools: Yes Open weights: Yes (Qwen/Qwen3.5-27B) Knowledge cutoff: unknown Reasoning: optional Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: The Qwen3.5 27B native vision-language Dense model incorporates a linear attention mechanism, delivering fast response times while balancing inference speed and performance. Its overall capabilities are comparable to those of... Checked: 20 Nov 2026 ## Qwen3.5-35B-A3B Platform: Alibaba (Qwen) Id: qwen/qwen3.5-35b-a3b URL: https://thebestmodelfor.com/models/qwen--qwen3.5-35b-a3b OpenRouter: https://openrouter.ai/qwen/qwen3.5-35b-a3b Kind: chat Listed: 2026-02-25 Context tokens: 262144 Max output tokens: 81920 Input USD per million: 0.14 Output USD per million: 1 Input per token (published): 0.00000014 Output per token (published): 0.000001 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: input_cache_read=0.00000005 Input modalities: image, text, video Output modalities: text Tools: Yes Open weights: Yes (Qwen/Qwen3.5-35B-A3B) Knowledge cutoff: unknown Reasoning: optional Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: The Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechanisms and a sparse mixture-of-experts model, achieving higher inference efficiency. Its overall... Checked: 20 Nov 2026 ## Qwen3.5 397B A17B Platform: Alibaba (Qwen) Id: qwen/qwen3.5-397b-a17b URL: https://thebestmodelfor.com/models/qwen--qwen3.5-397b-a17b OpenRouter: https://openrouter.ai/qwen/qwen3.5-397b-a17b Kind: chat Listed: 2026-02-16 Context tokens: 262144 Max output tokens: 81920 Input USD per million: 0.45 Output USD per million: 3 Input per token (published): 0.00000045 Output per token (published): 0.000003 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: input_cache_read=0.00000022 Input modalities: image, text, video Output modalities: text Tools: Yes Open weights: Yes (Qwen/Qwen3.5-397B-A17B) Knowledge cutoff: unknown Reasoning: optional Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. It delivers... Checked: 20 Nov 2026 ## Qwen3.5-9B Platform: Alibaba (Qwen) Id: qwen/qwen3.5-9b URL: https://thebestmodelfor.com/models/qwen--qwen3.5-9b OpenRouter: https://openrouter.ai/qwen/qwen3.5-9b Kind: chat Listed: 2026-03-10 Context tokens: 262144 Max output tokens: 235929 Input USD per million: 0.17 Output USD per million: 0.25 Input per token (published): 0.00000017 Output per token (published): 0.00000025 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: image, text, video Output modalities: text Tools: Yes Open weights: Yes (Qwen/Qwen3.5-9B) Knowledge cutoff: unknown Reasoning: optional Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Qwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong reasoning, coding, and visual understanding in an efficient 9B-parameter architecture. It uses a unified vision-language design... Checked: 20 Nov 2026 ## Qwen3.5-Flash Platform: Alibaba (Qwen) Id: qwen/qwen3.5-flash-02-23 URL: https://thebestmodelfor.com/models/qwen--qwen3.5-flash-02-23 OpenRouter: https://openrouter.ai/qwen/qwen3.5-flash-02-23 Kind: chat Listed: 2026-02-25 Context tokens: 1000000 Max output tokens: 65536 Input USD per million: 0.065 Output USD per million: 0.26 Input per token (published): 0.000000065 Output per token (published): 0.00000026 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: image, text, video Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: optional Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: The Qwen3.5 native vision-language Flash models are built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. Compared to the... Checked: 20 Nov 2026 ## Qwen3.5 Plus 2026-02-15 Platform: Alibaba (Qwen) Id: qwen/qwen3.5-plus-02-15 URL: https://thebestmodelfor.com/models/qwen--qwen3.5-plus-02-15 OpenRouter: https://openrouter.ai/qwen/qwen3.5-plus-02-15 Kind: chat Listed: 2026-02-16 Context tokens: 1000000 Max output tokens: 65536 Input USD per million: 0.26 Output USD per million: 1.56 Input per token (published): 0.00000026 Output per token (published): 0.00000156 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: image, text, video Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: optional Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: The Qwen3.5 native vision-language series Plus models are built on a hybrid architecture that integrates linear attention mechanisms with sparse mixture-of-experts models, achieving higher inference efficiency. In a variety of... Checked: 20 Nov 2026 ## Qwen3.5 Plus 2026-04-20 Platform: Alibaba (Qwen) Id: qwen/qwen3.5-plus-20260420 URL: https://thebestmodelfor.com/models/qwen--qwen3.5-plus-20260420 OpenRouter: https://openrouter.ai/qwen/qwen3.5-plus-20260420 Kind: chat Listed: 2026-04-27 Context tokens: 1000000 Max output tokens: 65536 Input USD per million: 0.3 Output USD per million: 1.8 Input per token (published): 0.0000003 Output per token (published): 0.0000018 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: input_cache_write=0.000000375 Input modalities: image, text, video Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: optional Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Qwen3.5 Plus (April 2026) is a large-scale multimodal language model from Alibaba. It accepts text, image, and video input and produces text output, with a 1M token context window. This... Checked: 20 Nov 2026 ## Qwen3.6 27B Platform: Alibaba (Qwen) Id: qwen/qwen3.6-27b URL: https://thebestmodelfor.com/models/qwen--qwen3.6-27b OpenRouter: https://openrouter.ai/qwen/qwen3.6-27b Kind: chat Listed: 2026-04-27 Context tokens: 262144 Max output tokens: 81920 Input USD per million: 0.32 Output USD per million: 3.2 Input per token (published): 0.00000032 Output per token (published): 0.0000032 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: image, text, video Output modalities: text Tools: Yes Open weights: Yes (Qwen/Qwen3.6-27B) Knowledge cutoff: unknown Reasoning: optional Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026. It features hybrid multimodal capabilities — accepting text, image, and video inputs... Checked: 20 Nov 2026 ## Qwen3.6 35B A3B Platform: Alibaba (Qwen) Id: qwen/qwen3.6-35b-a3b URL: https://thebestmodelfor.com/models/qwen--qwen3.6-35b-a3b OpenRouter: https://openrouter.ai/qwen/qwen3.6-35b-a3b Kind: chat Listed: 2026-04-27 Context tokens: 262144 Max output tokens: 235929 Input USD per million: 0.1 Output USD per million: 0.9 Input per token (published): 0.0000001 Output per token (published): 0.0000009 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: input_cache_read=0.000000025 Input modalities: image, text, video Output modalities: text Tools: Yes Open weights: Yes (Qwen/Qwen3.6-35B-A3B) Knowledge cutoff: unknown Reasoning: optional Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token. It uses a hybrid sparse mixture-of-experts architecture combining Gated... Checked: 20 Nov 2026 ## Qwen3.6 Flash Platform: Alibaba (Qwen) Id: qwen/qwen3.6-flash URL: https://thebestmodelfor.com/models/qwen--qwen3.6-flash OpenRouter: https://openrouter.ai/qwen/qwen3.6-flash Kind: chat Listed: 2026-04-27 Context tokens: 1000000 Max output tokens: 65536 Input USD per million: 0.1875 Output USD per million: 1.125 Input per token (published): 0.0000001875 Output per token (published): 0.000001125 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: input_cache_write=0.000000234375 Input modalities: image, text, video Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: optional Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Qwen3.6 Flash is a fast, efficient language model from Alibaba's Qwen 3.6 series. It supports text, image, and video input with a 1M token context window. Tiered pricing kicks in... Checked: 20 Nov 2026 ## Qwen3.6 Plus Platform: Alibaba (Qwen) Id: qwen/qwen3.6-plus URL: https://thebestmodelfor.com/models/qwen--qwen3.6-plus OpenRouter: https://openrouter.ai/qwen/qwen3.6-plus Kind: chat Listed: 2026-04-02 Context tokens: 1000000 Max output tokens: 65536 Input USD per million: 0.325 Output USD per million: 1.95 Input per token (published): 0.000000325 Output per token (published): 0.00000195 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: input_cache_write=0.00000040625 Input modalities: image, text, video Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: optional Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Qwen 3.6 Plus builds on a hybrid architecture that combines efficient linear attention with sparse mixture-of-experts routing, enabling strong scalability and high-performance inference. Compared to the 3.5 series, it delivers... Checked: 20 Nov 2026 ## Qwen3.7 Flash Platform: Alibaba (Qwen) Id: qwen/qwen3.7-flash URL: https://thebestmodelfor.com/models/qwen--qwen3.7-flash OpenRouter: https://openrouter.ai/qwen/qwen3.7-flash Kind: chat Listed: 2026-07-27 Context tokens: 1000000 Max output tokens: 65536 Input USD per million: 0.03 Output USD per million: 0.13 Input per token (published): 0.00000003 Output per token (published): 0.00000013 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: input_cache_read=0.000000006, input_cache_write=0.000000038 Input modalities: image, text, video Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: optional Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Qwen3.7 Flash is a vision-language reasoning model from Alibaba. It is suited for multimodal agents, visual coding, search, and computer interaction, with strengths in object recognition, spatial understanding, and real-world... Checked: 20 Nov 2026 ## Qwen3.7 Max Platform: Alibaba (Qwen) Id: qwen/qwen3.7-max URL: https://thebestmodelfor.com/models/qwen--qwen3.7-max OpenRouter: https://openrouter.ai/qwen/qwen3.7-max Kind: chat Listed: 2026-05-21 Context tokens: 1000000 Max output tokens: 131072 Input USD per million: 1.475 Output USD per million: 4.425 Input per token (published): 0.000001475 Output per token (published): 0.000004425 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: input_cache_read=0.000000295, input_cache_write=0.00000184375 Input modalities: text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: optional Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Qwen3.7-Max is the flagship model in Alibaba's Qwen3.7 series. It supports text input and output and is designed for agent-centric workloads, with particular strengths in coding, office and productivity tasks,... Checked: 20 Nov 2026 ## Qwen3.7 Plus Platform: Alibaba (Qwen) Id: qwen/qwen3.7-plus URL: https://thebestmodelfor.com/models/qwen--qwen3.7-plus OpenRouter: https://openrouter.ai/qwen/qwen3.7-plus Kind: chat Listed: 2026-06-03 Context tokens: 1000000 Max output tokens: 131072 Input USD per million: 0.32 Output USD per million: 1.28 Input per token (published): 0.00000032 Output per token (published): 0.00000128 Batch input USD per million: 0.23 Batch output USD per million: 0.92 Other raw prices: input_cache_read=0.000000064, input_cache_write=0.0000004 Input modalities: image, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: optional Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Qwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series. It supports text and image input with text output, building on the series' text capabilities with a comprehensive upgrade to its... Checked: 20 Nov 2026 ## Qwen3.8 2.4T A95B Platform: Alibaba (Qwen) Id: qwen/qwen3.8-2.4t-a95b URL: https://thebestmodelfor.com/models/qwen--qwen3.8-2.4t-a95b OpenRouter: https://openrouter.ai/qwen/qwen3.8-2.4t-a95b Kind: chat Listed: 2026-08-12 Context tokens: 1048576 Max output tokens: 131072 Input USD per million: 2 Output USD per million: 6 Input per token (published): 0.000002 Output per token (published): 0.000006 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: input_cache_read=0.00000025 Input modalities: text Output modalities: text Tools: Yes Open weights: Yes (Qwen/Qwen3.8-2.4T-A95B) Knowledge cutoff: unknown Reasoning: required Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of Qwen3.8 Max, with 95 billion active parameters out of 2.4 trillion total. It is... Checked: 20 Nov 2026 ## Qwen3.8 27B Platform: Alibaba (Qwen) Id: qwen/qwen3.8-27b URL: https://thebestmodelfor.com/models/qwen--qwen3.8-27b OpenRouter: https://openrouter.ai/qwen/qwen3.8-27b Kind: chat Listed: 2026-08-14 Context tokens: 1024000 Max output tokens: 235929 Input USD per million: 0.06 Output USD per million: 1.96 Input per token (published): 0.00000006 Output per token (published): 0.00000196 Batch input USD per million: 0.16 Batch output USD per million: 2 Other raw prices: input_cache_read=0.000000059 Input modalities: image, text, video Output modalities: text Tools: Yes Open weights: Yes (Qwen/Qwen3.8-27B) Knowledge cutoff: unknown Reasoning: optional Third-party intelligence index: 20.1 Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks, with flexible thinking that can be... Checked: 20 Nov 2026 ## Qwen3.8 Flash Platform: Alibaba (Qwen) Id: qwen/qwen3.8-flash URL: https://thebestmodelfor.com/models/qwen--qwen3.8-flash OpenRouter: https://openrouter.ai/qwen/qwen3.8-flash Kind: chat Listed: 2026-08-26 Context tokens: 1000000 Max output tokens: 131072 Input USD per million: 0.15 Output USD per million: 0.47 Input per token (published): 0.00000015 Output per token (published): 0.00000047 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: input_cache_read=0.000000016 Input modalities: image, text, video Output modalities: text Tools: Yes Open weights: Yes (Qwen/Qwen3.8-Flash-Next) Knowledge cutoff: unknown Reasoning: optional Third-party intelligence index: 28.6 Third-party coding index: unknown Guide: reviewed 2026-11-19 — OpenRouter describes Qwen3.8 Flash as a multimodal reasoning model for coding help, visual understanding, documents, charts, desktop screens, and long video. The feed includes a Hugging Face id and a low rate. It is the reviewed default when you want Qwen without Max prices. Listing blurb: Qwen3.8 Flash is a multimodal reasoning model from Alibaba. It is suited for coding assistance, agentic workflows, visual understanding, document and codebase analysis, desktop interaction, chart analysis, and long-video analysis. Checked: 20 Nov 2026 ## Qwen3.8 Max (0902) Platform: Alibaba (Qwen) Id: qwen/qwen3.8-max-0902 URL: https://thebestmodelfor.com/models/qwen--qwen3.8-max-0902 OpenRouter: https://openrouter.ai/qwen/qwen3.8-max-0902 Kind: chat Listed: 2026-09-03 Context tokens: 1000000 Max output tokens: 131072 Input USD per million: 2 Output USD per million: 6 Input per token (published): 0.000002 Output per token (published): 0.000006 Batch input USD per million: 1.15 Batch output USD per million: 3.45 Other raw prices: input_cache_read=0.00000025 Input modalities: image, text, video Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: required Third-party intelligence index: 33.7 Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Qwen3.8 Max 0902 is an updated snapshot of Qwen3.8 Max from Alibaba's Qwen team. It is a 2.4-trillion-parameter mixture-of-experts model that accepts text, image, and video input and returns text,... Checked: 20 Nov 2026 ## Qwen3.8 Max Prime Platform: Alibaba (Qwen) Id: qwen/qwen3.8-max-prime URL: https://thebestmodelfor.com/models/qwen--qwen3.8-max-prime OpenRouter: https://openrouter.ai/qwen/qwen3.8-max-prime Kind: chat Listed: 2026-09-23 Context tokens: 1000000 Max output tokens: 131072 Input USD per million: 4 Output USD per million: 12 Input per token (published): 0.000004 Output per token (published): 0.000012 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: input_cache_read=0.0000005 Input modalities: image, text, video Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: required Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Qwen3.8 Max Prime is a higher-throughput variant of Qwen3.8 Max from Alibaba's Qwen team, served as a separate SKU at a higher price point. It accepts text, image, and video... Checked: 20 Nov 2026 ## Qwen3.8 Omni Flash Platform: Alibaba (Qwen) Id: qwen/qwen3.8-omni-flash URL: https://thebestmodelfor.com/models/qwen--qwen3.8-omni-flash OpenRouter: https://openrouter.ai/qwen/qwen3.8-omni-flash Kind: chat Listed: 2026-09-21 Context tokens: 1000000 Max output tokens: 131072 Input USD per million: 0.15 Output USD per million: 0.47 Input per token (published): 0.00000015 Output per token (published): 0.00000047 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: input_cache_read=0.000000016 Input modalities: audio, image, text, video Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: optional Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Qwen3.8 Omni Flash is an omni-modal reasoning model from Alibaba, the first Qwen model built around agentic capabilities with native audio-video understanding. It is suited for audio-video analysis and summarization,... Checked: 20 Nov 2026 ## Qwen4 Max Platform: Alibaba (Qwen) Id: qwen/qwen4-max URL: https://thebestmodelfor.com/models/qwen--qwen4-max OpenRouter: https://openrouter.ai/qwen/qwen4-max Kind: chat Listed: 2026-11-16 Context tokens: 1000000 Max output tokens: 131072 Input USD per million: 1.425 Output USD per million: 4.275 Input per token (published): 0.000001425 Output per token (published): 0.000004275 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: input_cache_read=0.00000007125, input_cache_write=0.00000178125 Input modalities: image, text, video Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: optional Third-party intelligence index: 42.9 Third-party coding index: unknown Guide: reviewed 2026-11-19 — Qwen4 Max is the hosted flagship of Alibaba's Qwen4 series on this feed. It accepts text, images, and video, returns text, and lists a million-token window. No public weights id is on the row. Listing blurb: Qwen4 Max is the flagship model in Alibaba's Qwen4 series. It accepts text, image, and video input and returns text, with a 1M-token context window and reasoning enabled by default.... Checked: 20 Nov 2026 ## Command A Platform: Cohere Id: cohere/command-a URL: https://thebestmodelfor.com/models/cohere--command-a OpenRouter: https://openrouter.ai/cohere/command-a Kind: chat Listed: 2025-03-13 Context tokens: 256000 Max output tokens: 8192 Input USD per million: 2.5 Output USD per million: 10 Input per token (published): 0.0000025 Output per token (published): 0.00001 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: text Output modalities: text Tools: Yes Open weights: Yes (CohereForAI/c4ai-command-a-03-2025) Knowledge cutoff: 2024-08-31 Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: reviewed 2026-11-19 — Command A is the older open-weight 111B model. The listing gives it a 256,000-token window and points at agentic, multilingual, and coding use. On this feed its token price is higher than Command A+. Open weights are not a discount here. This row does not list image input. The published cutoff is 2024-08-31. Listing blurb: Command A is an open-weights 111B parameter model with a 256k context window focused on delivering great performance across agentic, multilingual, and coding use cases. Compared to other leading proprietary... Checked: 20 Nov 2026 ## Command A+ Platform: Cohere Id: cohere/command-a-plus URL: https://thebestmodelfor.com/models/cohere--command-a-plus OpenRouter: https://openrouter.ai/cohere/command-a-plus Kind: chat Listed: 2026-09-22 Context tokens: 192000 Max output tokens: 64000 Input USD per million: 0.3 Output USD per million: 1.5 Input per token (published): 0.0000003 Output per token (published): 0.0000015 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: input_cache_read=0.00000015 Input modalities: image, text Output modalities: text Tools: Yes Open weights: Yes (CohereLabs/command-a-plus-05-2026-bf16) Knowledge cutoff: unknown Reasoning: optional Third-party intelligence index: 6.2 Third-party coding index: unknown Guide: reviewed 2026-11-19 — OpenRouter describes Command A+ as Cohere's flagship for enterprise agent workflows: text and image input, a 192,000-token window, tool calling, and a public weights id. The window fits retrieved pages. It does not fit an entire unfiltered archive. Listing blurb: Command A+ is Cohere's flagship model for enterprise agentic workflows. It accepts text and image inputs with a 192K context window, supports native tool calling with strict tool schemas, structured... Checked: 20 Nov 2026 ## Command R (08-2024) Platform: Cohere Id: cohere/command-r-08-2024 URL: https://thebestmodelfor.com/models/cohere--command-r-08-2024 OpenRouter: https://openrouter.ai/cohere/command-r-08-2024 Kind: chat Listed: 2024-08-30 Context tokens: 128000 Max output tokens: 4000 Input USD per million: 0.15 Output USD per million: 0.6 Input per token (published): 0.00000015 Output per token (published): 0.0000006 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: text Output modalities: text Tools: Yes Open weights: Yes (CohereLabs/c4ai-command-r-08-2024) Knowledge cutoff: 2024-03-31 Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: command-r-08-2024 is an update of the Command R with improved performance for multilingual retrieval-augmented generation (RAG) and tool use. More broadly, it is better at math, code and reasoning and... Checked: 20 Nov 2026 ## Command R+ (08-2024) Platform: Cohere Id: cohere/command-r-plus-08-2024 URL: https://thebestmodelfor.com/models/cohere--command-r-plus-08-2024 OpenRouter: https://openrouter.ai/cohere/command-r-plus-08-2024 Kind: chat Listed: 2024-08-30 Context tokens: 128000 Max output tokens: 4000 Input USD per million: 2.5 Output USD per million: 10 Input per token (published): 0.0000025 Output per token (published): 0.00001 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: text Output modalities: text Tools: Yes Open weights: Yes (CohereLabs/c4ai-command-r-plus-08-2024) Knowledge cutoff: 2024-03-31 Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: command-r-plus-08-2024 is an update of the Command R+ with roughly 50% higher throughput and 25% lower latencies as compared to the previous Command R+ version, while keeping the hardware footprint... Checked: 20 Nov 2026 ## Command R7B (12-2024) Platform: Cohere Id: cohere/command-r7b-12-2024 URL: https://thebestmodelfor.com/models/cohere--command-r7b-12-2024 OpenRouter: https://openrouter.ai/cohere/command-r7b-12-2024 Kind: chat Listed: 2024-12-14 Context tokens: 128000 Max output tokens: 4000 Input USD per million: 0.0375 Output USD per million: 0.15 Input per token (published): 0.0000000375 Output per token (published): 0.00000015 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: text Output modalities: text Tools: Yes Open weights: Yes (CohereLabs/c4ai-command-r7b-12-2024) Knowledge cutoff: 2024-08-31 Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: reviewed 2026-11-19 — Command R7B (December 2024) is the small, cheap Cohere model. The listing says it is for RAG, tool use, and agents. It is older, text only, and open weights. Test it on your data before you trust a queue to it. Listing blurb: Command R7B (12-2024) is a small, fast update of the Command R+ model, delivered in December 2024. It excels at RAG, tool use, agents, and similar tasks requiring complex reasoning... Checked: 20 Nov 2026 ## Embed 5 Fast Platform: Cohere Id: cohere/embed-5-fast URL: https://thebestmodelfor.com/models/cohere--embed-5-fast OpenRouter: https://openrouter.ai/cohere/embed-5-fast Kind: embeddings Listed: 2026-11-03 Context tokens: 128000 Max output tokens: 115200 Input USD per million: 0.08 Output USD per million: 0 Input per token (published): 0.00000008 Output per token (published): 0 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: image_token=0.0000004 Input modalities: image, text Output modalities: embeddings Tools: Not listed Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Embed 5 Fast is the lower-latency, cost-efficient tier of Cohere's Embed 5 family of multimodal embedding models (about 1B parameters). It embeds text, images, and interleaved text and image content... Checked: 20 Nov 2026 ## Embed 5 Pro Platform: Cohere Id: cohere/embed-5-pro URL: https://thebestmodelfor.com/models/cohere--embed-5-pro OpenRouter: https://openrouter.ai/cohere/embed-5-pro Kind: embeddings Listed: 2026-11-03 Context tokens: 128000 Max output tokens: 115200 Input USD per million: 0.12 Output USD per million: 0 Input per token (published): 0.00000012 Output per token (published): 0 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: image_token=0.0000004 Input modalities: image, text Output modalities: embeddings Tools: Not listed Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Embed 5 Pro is the higher-accuracy tier of Cohere's Embed 5 family of multimodal embedding models (about 2.4B parameters). It embeds text, images, and interleaved text and image content into... Checked: 20 Nov 2026 ## Rerank 4 Fast Platform: Cohere Id: cohere/rerank-4-fast URL: https://thebestmodelfor.com/models/cohere--rerank-4-fast OpenRouter: https://openrouter.ai/cohere/rerank-4-fast Kind: rerank Listed: 2026-04-06 Context tokens: 32768 Max output tokens: 29491 Input USD per million: 0 Output USD per million: 0 Input per token (published): 0 Output per token (published): 0 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: text Output modalities: rerank Tools: Not listed Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Cohere's AI search foundation model for enhancing the relevance of information surfaced within search and RAG systems. Features a 32K context window, multilingual support across 100+ languages, no data pre-processing... Checked: 20 Nov 2026 ## Rerank 4 Pro Platform: Cohere Id: cohere/rerank-4-pro URL: https://thebestmodelfor.com/models/cohere--rerank-4-pro OpenRouter: https://openrouter.ai/cohere/rerank-4-pro Kind: rerank Listed: 2026-04-06 Context tokens: 32768 Max output tokens: 29491 Input USD per million: 0 Output USD per million: 0 Input per token (published): 0 Output per token (published): 0 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: text Output modalities: rerank Tools: Not listed Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Cohere's AI search foundation model for enhancing the relevance of information surfaced within search and RAG systems. Features a 32K context window, multilingual support across 100+ languages, no data pre-processing... Checked: 20 Nov 2026 ## Rerank 5 Fast Platform: Cohere Id: cohere/rerank-5-fast URL: https://thebestmodelfor.com/models/cohere--rerank-5-fast OpenRouter: https://openrouter.ai/cohere/rerank-5-fast Kind: rerank Listed: 2026-11-03 Context tokens: 32768 Max output tokens: 29491 Input USD per million: 0 Output USD per million: 0 Input per token (published): 0 Output per token (published): 0 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: text Output modalities: rerank Tools: Not listed Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Rerank 5 Fast is the low-latency tier of Cohere's Rerank 5 family of reranking models. It scores and reorders candidate documents against a query and is suited for high-throughput retrieval... Checked: 20 Nov 2026 ## Rerank 5 Pro Platform: Cohere Id: cohere/rerank-5-pro URL: https://thebestmodelfor.com/models/cohere--rerank-5-pro OpenRouter: https://openrouter.ai/cohere/rerank-5-pro Kind: rerank Listed: 2026-11-03 Context tokens: 32768 Max output tokens: 29491 Input USD per million: 0 Output USD per million: 0 Input per token (published): 0 Output per token (published): 0 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: text Output modalities: rerank Tools: Not listed Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Rerank 5 Pro is the higher-accuracy tier of Cohere's Rerank 5 family of reranking models. It scores and reorders candidate documents against a query and is suited for retrieval pipelines... Checked: 20 Nov 2026 ## Rerank v3.5 Platform: Cohere Id: cohere/rerank-v3.5 URL: https://thebestmodelfor.com/models/cohere--rerank-v3.5 OpenRouter: https://openrouter.ai/cohere/rerank-v3.5 Kind: rerank Listed: 2026-04-05 Context tokens: 4096 Max output tokens: 3686 Input USD per million: 0 Output USD per million: 0 Input per token (published): 0 Output per token (published): 0 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: text Output modalities: rerank Tools: Not listed Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Rerank v3.5 is designed to reorder search results for improved relevance. It supports multi-aspect and semi-structured data reranking over 100+ languages. Ideal for refining results from semantic or keyword search... Checked: 20 Nov 2026 ## Nova 2 Lite Platform: Amazon (Nova) Id: amazon/nova-2-lite-v1 URL: https://thebestmodelfor.com/models/amazon--nova-2-lite-v1 OpenRouter: https://openrouter.ai/amazon/nova-2-lite-v1 Kind: chat Listed: 2025-12-02 Context tokens: 1000000 Max output tokens: 65535 Input USD per million: 0.3 Output USD per million: 2.5 Input per token (published): 0.0000003 Output per token (published): 0.0000025 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: file, image, text, video Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: optional Third-party intelligence index: unknown Third-party coding index: unknown Guide: reviewed 2026-11-19 — OpenRouter describes Nova 2 Lite as the fast, cost-effective reasoning model for everyday work that can read text, images, and video. It is the reviewed Amazon default, and the Nova model to use when the input is a clip. Listing blurb: Nova 2 Lite is a fast, cost-effective reasoning model for everyday workloads that can process text, images, and videos to generate text. Nova 2 Lite demonstrates standout capabilities in processing... Checked: 20 Nov 2026 ## Nova Lite 1.0 Platform: Amazon (Nova) Id: amazon/nova-lite-v1 URL: https://thebestmodelfor.com/models/amazon--nova-lite-v1 OpenRouter: https://openrouter.ai/amazon/nova-lite-v1 Kind: chat Listed: 2024-12-05 Context tokens: 300000 Max output tokens: 5120 Input USD per million: 0.06 Output USD per million: 0.24 Input per token (published): 0.00000006 Output per token (published): 0.00000024 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: image, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: 2024-10-31 Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Amazon Nova Lite 1.0 is a very low-cost multimodal model from Amazon that focused on fast processing of image, video, and text inputs to generate text output. Amazon Nova Lite... Checked: 20 Nov 2026 ## Nova Micro 1.0 Platform: Amazon (Nova) Id: amazon/nova-micro-v1 URL: https://thebestmodelfor.com/models/amazon--nova-micro-v1 OpenRouter: https://openrouter.ai/amazon/nova-micro-v1 Kind: chat Listed: 2024-12-05 Context tokens: 128000 Max output tokens: 5120 Input USD per million: 0.035 Output USD per million: 0.14 Input per token (published): 0.000000035 Output per token (published): 0.00000014 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: 2024-10-31 Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: reviewed 2026-11-19 — Nova Micro is text-only. The listing calls it the lowest-latency Nova, at a very low cost, with a knowledge cutoff of 2024-10-31. Use it for short text. Do not use it for a photo, a video, or a question about this month's news. Listing blurb: Amazon Nova Micro 1.0 is a text-only model that delivers the lowest latency responses in the Amazon Nova family of models at a very low cost. With a context length... Checked: 20 Nov 2026 ## Nova Premier 1.0 Platform: Amazon (Nova) Id: amazon/nova-premier-v1 URL: https://thebestmodelfor.com/models/amazon--nova-premier-v1 OpenRouter: https://openrouter.ai/amazon/nova-premier-v1 Kind: chat Listed: 2025-10-31 Context tokens: 1000000 Max output tokens: 32000 Input USD per million: 2.5 Output USD per million: 12.5 Input per token (published): 0.0000025 Output per token (published): 0.0000125 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: input_cache_read=0.000000625 Input modalities: image, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: reviewed 2026-11-19 — OpenRouter calls Nova Premier the most capable Amazon multimodal model for complex reasoning, and a teacher for distilling custom models. Text and image in, text out, a million-token window. The feed has no third-party index for it. This guide does not invent one. The row does not list video input. Listing blurb: Amazon Nova Premier is the most capable of Amazon’s multimodal models for complex reasoning tasks and for use as the best teacher for distilling custom models. Checked: 20 Nov 2026 ## Nova Pro 1.0 Platform: Amazon (Nova) Id: amazon/nova-pro-v1 URL: https://thebestmodelfor.com/models/amazon--nova-pro-v1 OpenRouter: https://openrouter.ai/amazon/nova-pro-v1 Kind: chat Listed: 2024-12-05 Context tokens: 300000 Max output tokens: 5120 Input USD per million: 0.8 Output USD per million: 3.2 Input per token (published): 0.0000008 Output per token (published): 0.0000032 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: image, text Output modalities: text Tools: Yes Open weights: No public weights id listed Knowledge cutoff: 2024-10-31 Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Amazon Nova Pro 1.0 is a capable multimodal model from Amazon focused on providing a combination of accuracy, speed, and cost for a wide range of tasks. As of December... Checked: 20 Nov 2026 ## Titan Multimodal Embeddings G1 Platform: Amazon (Nova) Id: amazon/titan-embed-image-v1 URL: https://thebestmodelfor.com/models/amazon--titan-embed-image-v1 OpenRouter: https://openrouter.ai/amazon/titan-embed-image-v1 Kind: embeddings Listed: 2026-10-26 Context tokens: 128 Max output tokens: 115 Input USD per million: 0.8 Output USD per million: 0 Input per token (published): 0.0000008 Output per token (published): 0 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: image=0.00006 Input modalities: image, text Output modalities: embeddings Tools: Not listed Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Amazon Titan Multimodal Embeddings G1 embeds text, images, or text and image together into a shared vector space for multimodal search and recommendation. Images are sent as base64 (up to... Checked: 20 Nov 2026 ## Titan Embeddings G1 - Text Platform: Amazon (Nova) Id: amazon/titan-embed-text-v1 URL: https://thebestmodelfor.com/models/amazon--titan-embed-text-v1 OpenRouter: https://openrouter.ai/amazon/titan-embed-text-v1 Kind: embeddings Listed: 2026-10-26 Context tokens: 8192 Max output tokens: 7372 Input USD per million: 0.1 Output USD per million: 0 Input per token (published): 0.0000001 Output per token (published): 0 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: text Output modalities: embeddings Tools: Not listed Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Amazon Titan Embeddings G1 - Text is the first-generation Titan text embedding model. It accepts up to 8,192 tokens per input and returns fixed 1,536-dimension vectors; the dimensions parameter is... Checked: 20 Nov 2026 ## Titan Text Embeddings V2 Platform: Amazon (Nova) Id: amazon/titan-embed-text-v2 URL: https://thebestmodelfor.com/models/amazon--titan-embed-text-v2 OpenRouter: https://openrouter.ai/amazon/titan-embed-text-v2 Kind: embeddings Listed: 2026-10-26 Context tokens: 8192 Max output tokens: 7372 Input USD per million: 0.02 Output USD per million: 0 Input per token (published): 0.00000002 Output per token (published): 0 Batch input USD per million: not listed Batch output USD per million: not listed Other raw prices: none Input modalities: text Output modalities: embeddings Tools: Not listed Open weights: No public weights id listed Knowledge cutoff: unknown Reasoning: unknown Third-party intelligence index: unknown Third-party coding index: unknown Guide: new, not yet reviewed Listing blurb: Amazon Titan Text Embeddings V2 is a text embedding model for retrieval, search, and clustering. It accepts up to 8,192 tokens per input and returns normalized vectors of 1,024 dimensions... Checked: 20 Nov 2026