Checked against the OpenRouter public models feed. Prices are copied, not estimated.

The Best Model ForWhich AI model to use, from ten labs.

Google (Gemini)

Short answer

Google's listing mixes Gemini 4 chat models, older Gemini 3 Flash models, open-weight Gemma models, and separate image, speech, and video models. Gemini 4 models accept text, images, audio, video, and files. Gemma rows carry a public weights id.

Lab site · Filter the full catalogue to Google (Gemini)

What the top models are good for

1. Gemini 4 Neon

Flagship · $3.00 in · $15.00 out · 1,048,576 tokens

Guide note · 19 Nov 2026

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.

  • Sees images, video, and audio
  • Coding and agentic work, per the listing
  • About a million tokens of context

What it is good for

Analyse a photo of a receipt and a short clip of a shelf

One request can hold the photo and the clip. Ask for the total, the tax, and whether the shelf matches the receipt. That is vision plus a bit of arithmetic, which is why the modality list matters more than the coding blurb.

Gemini 4 Neon is listed at $3.00 input and $15.00 output per million tokens, with a 1,048,576-token context window.

Fix a bug from a screenshot and a repo note

The listing aims Neon at repository and terminal coding. A screenshot plus the error text is the ordinary version of that job.

Gemini 4 Neon is listed at $3.00 input and $15.00 output per million tokens, with a 1,048,576-token context window.

The tasks are editorial illustrations, not measured benchmarks. The prices in them are read from today's feed.

2. Gemini 4 Hydrogen

Everyday · $1.50 in · $7.50 out · 1,048,576 tokens

Guide note · 19 Nov 2026

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.

  • Default Gemini 4 when Neon is more than you need
  • Images, audio, video, and files
  • Long context

What it is good for

Summarise a 300-page contract

A long contract fits a million-token window if you send the file rather than a vague question. Ask for the parties, the dates, the renewal, and any clause that is not boilerplate. This is reading, not legal advice.

Gemini 4 Hydrogen is listed at $1.50 input and $7.50 output per million tokens, with a 1,048,576-token context window.

The agent step you run thousands of times

The listing is explicit about high-throughput agent workflows. Give Hydrogen one bounded step: extract these fields, choose a label, draft a line.

Gemini 4 Hydrogen is listed at $1.50 input and $7.50 output per million tokens, with a 1,048,576-token context window.

The tasks are editorial illustrations, not measured benchmarks. The prices in them are read from today's feed.

3. Gemini 3.5 Flash Lite

Budget · $0.30 in · $2.50 out · 1,048,576 tokens

Guide note · 19 Nov 2026

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.

  • Focused subagent steps
  • Still multimodal
  • Lower input rate than Gemini 4

What it is good for

Extract fields from a photo of a receipt

Merchant, date, total, tax. One photo, one schema, many receipts. That is the focused task the listing describes. Check a sample of crumpled photos before you automate the rest.

Gemini 3.5 Flash Lite is listed at $0.30 input and $2.50 output per million tokens, with a 1,048,576-token context window.

A subagent that only classifies

Hand it one label set. Do not hand it the whole workflow. The listing is about subagents inside a larger system.

Gemini 3.5 Flash Lite is listed at $0.30 input and $2.50 output per million tokens, with a 1,048,576-token context window.

The tasks are editorial illustrations, not measured benchmarks. The prices in them are read from today's feed.

Every current row

49 Google (Gemini) rows on the feed.
ModelKindContextInputOutputListedGuide
Chirp 3 Transcription Unknown $266.6667 $0 5 May 2026 New, not yet reviewed
Gemini 2.5 Flash Chat 1,048,576 $0.30 $2.50 17 Jun 2025 New, not yet reviewed
Nano Banana (Gemini 2.5 Flash Image) Image 32,768 $0.30 $2.50 7 Oct 2025 New, not yet reviewed
Gemini 2.5 Flash Lite Chat 1,048,576 $0.10 $0.40 22 Jul 2025 New, not yet reviewed
Gemini 2.5 Flash TTS Speech 8,192 $0.50 $10.00 20 Nov 2026 New, not yet reviewed
Gemini 2.5 Pro Chat 1,048,576 $1.25 $10.00 17 Jun 2025 New, not yet reviewed
Gemini 2.5 Pro Preview 06-05 Chat 1,048,576 $1.25 $10.00 5 Jun 2025 New, not yet reviewed
Gemini 2.5 Pro TTS Speech 8,192 $1.00 $20.00 20 Nov 2026 New, not yet reviewed
Gemini 3 Flash Preview Chat 1,048,576 $0.50 $3.00 17 Dec 2025 New, not yet reviewed
Nano Banana Pro (Gemini 3 Pro Image) Image 131,072 $2.00 $12.00 18 Jun 2026 New, not yet reviewed
Nano Banana Pro (Gemini 3 Pro Image Preview) Image 65,536 $2.00 $12.00 20 Nov 2025 New, not yet reviewed
Nano Banana 2 (Gemini 3.1 Flash Image) Image 131,072 $0.50 $3.00 18 Jun 2026 New, not yet reviewed
Nano Banana 2 (Gemini 3.1 Flash Image Preview) Image 65,536 $0.50 $3.00 26 Feb 2026 New, not yet reviewed
Gemini 3.1 Flash Lite Chat 1,048,576 $0.25 $1.50 7 May 2026 New, not yet reviewed
Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) Image 65,536 $0.25 $1.50 30 Jun 2026 New, not yet reviewed
Gemini 3.1 Flash Lite Preview Chat 1,048,576 $0.25 $1.50 3 Mar 2026 New, not yet reviewed
Gemini 3.1 Flash TTS Preview Speech 32,768 $1.00 $20.00 24 Apr 2026 New, not yet reviewed
Gemini 3.1 Pro Preview Chat 1,048,576 $2.00 $12.00 19 Feb 2026 New, not yet reviewed
Gemini 3.1 Pro Preview Custom Tools Chat 1,048,576 $2.00 $12.00 25 Feb 2026 New, not yet reviewed
Gemini 3.5 Flash Chat 1,048,576 $1.50 $9.00 19 May 2026 New, not yet reviewed
Gemini 3.5 Flash Lite Chat 1,048,576 $0.30 $2.50 21 Jul 2026 Reviewed
Gemini 3.5 Transcribe Transcription 98,304 $2.00 $12.00 25 Sep 2026 New, not yet reviewed
Gemini 3.6 Flash Chat 1,048,576 $0.75 $3.75 21 Jul 2026 New, not yet reviewed
Gemini 3.7 Flash Chat 1,048,576 $0.75 $3.75 13 Aug 2026 New, not yet reviewed
Gemini 3.8 Flash Chat 1,048,576 $0.825 $4.125 2 Sep 2026 New, not yet reviewed
Gemini 3.8 Flash Lite TTS Speech 32,768 $0.50 $6.00 23 Sep 2026 New, not yet reviewed
Gemini 3.8 Flash TTS Speech 32,768 $0.50 $9.00 23 Sep 2026 New, not yet reviewed
Gemini 4 Argon Chat 1,048,576 $2.00 $10.00 13 Oct 2026 New, not yet reviewed
Gemini 4 Carbon Chat 1,048,576 $2.00 $10.00 10 Nov 2026 New, not yet reviewed
Gemini 4 Hydrogen Chat 1,048,576 $1.50 $7.50 12 Nov 2026 Reviewed
Gemini 4 Neon Chat 1,048,576 $3.00 $15.00 18 Nov 2026 Reviewed
Gemini Decision 1 Decisions 262,144 $0.10 $0 11 Nov 2026 New, not yet reviewed
Gemini Embedding 001 Embeddings 20,000 $0.15 $0 31 Oct 2025 New, not yet reviewed
Gemini Embedding 2 Embeddings 8,192 $0.20 $0 20 May 2026 New, not yet reviewed
Gemini Embedding 2 Preview Embeddings 8,192 $0.20 $0 17 Apr 2026 New, not yet reviewed
Nano Banana 2.1 Image 65,536 $1.50 $7.50 6 Oct 2026 New, not yet reviewed
Gemini Omni 1.1 Flash Video 131,072 $1.50 $9.00 4 Nov 2026 New, not yet reviewed
Gemini Omni 1.2 Flash Video 131,072 $1.50 $9.00 5 Nov 2026 New, not yet reviewed
Gemma 2 27B Chat 8,192 $0.65 $0.65 13 Jul 2024 New, not yet reviewed
Gemma 3 12B Chat 131,072 $0.05 $0.15 13 Mar 2025 New, not yet reviewed
Gemma 3 27B Chat 131,072 $0.08 $0.16 12 Mar 2025 New, not yet reviewed
Gemma 3 4B Chat 131,072 $0.05 $0.10 13 Mar 2025 New, not yet reviewed
Gemma 4 26B A4B Chat 262,144 $0.09 $0.30 3 Apr 2026 New, not yet reviewed
Gemma 4 31B Chat 262,144 $0.20 $0.40 2 Apr 2026 New, not yet reviewed
Lyria 3 Clip Preview Speech 1,048,576 $0 $0 30 Mar 2026 New, not yet reviewed
Lyria 3 Pro Preview Speech 1,048,576 $0 $0 30 Mar 2026 New, not yet reviewed
Veo 3.1 Video Unknown $0 $0 23 Mar 2026 New, not yet reviewed
Veo 3.1 Fast Video Unknown $0 $0 24 Apr 2026 New, not yet reviewed
Veo 3.1 Lite Video Unknown $0 $0 23 Apr 2026 New, not yet reviewed

Questions

Which Google (Gemini) model should I start with?

For most people, start with Gemini 4 Neon, then drop to the next model on this page when the task is routine. Read the cheaper-model note under each example.

Are the examples benchmarks?

No. They are concrete tasks used to explain fit. The prices next to them are live figures from the feed. The judgment is a guide note.