Qwen2.5 VL 72B Instruct
New, not yet reviewed. No guide note yet.
Qwen2.5 VL 72B Instruct is listed at $0.80 input and $1.00 output per million tokens, with a 128,000-token context window.
Short answer
Qwen2.5 VL 72B Instruct ($0.80 in / $1.00 out); Qwen3.8 Flash ($0.15 in / $0.47 out). Lowest listed input price: Qwen3.8 Flash. Longest listed context: Qwen3.8 Flash at 1,000,000 tokens. A lower price is not a quality ranking.
| Fact | Qwen2.5 VL 72B Instruct | Qwen3.8 Flash |
|---|---|---|
| Lab | Alibaba (Qwen) | Alibaba (Qwen) |
| Kind | Chat | Chat |
| Listed | 1 Feb 2025 | 26 Aug 2026 |
| Context | 128,000 | 1,000,000 |
| Input / million | $0.80 | $0.15 |
| Output / million | $1.00 | $0.47 |
| Batch input | Not listed | Not listed |
| Batch output | Not listed | Not listed |
| Inputs | image, text | image, text, video |
| Outputs | text | text |
| Tools | Not listed | Yes |
| Open weights | Yes | Yes |
| Knowledge cutoff | 2024-06-30 | Unknown |
| Third-party index | Unknown | 28.6 |
| Guide | New, not yet reviewed | Reviewed |
Input and output prices are USD per million tokens, from pricing.prompt and pricing.completion. The index is not our benchmark.
New, not yet reviewed. No guide note yet.
Qwen2.5 VL 72B Instruct is listed at $0.80 input and $1.00 output per million tokens, with a 128,000-token context window.
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.
Qwen3.8 Flash is listed at $0.15 input and $0.47 output per million tokens, with a 1,000,000-token context window.