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 Coder Next ($0.12 in / $0.80 out). Lowest listed input price: Qwen3 Coder Next. Longest listed context: Qwen3 Coder Next at 262,144 tokens. A lower price is not a quality ranking.
| Fact | Qwen2.5 VL 72B Instruct | Qwen3 Coder Next |
|---|---|---|
| Lab | Alibaba (Qwen) | Alibaba (Qwen) |
| Kind | Chat | Chat |
| Listed | 1 Feb 2025 | 4 Feb 2026 |
| Context | 128,000 | 262,144 |
| Input / million | $0.80 | $0.12 |
| Output / million | $1.00 | $0.80 |
| Batch input | Not listed | Not listed |
| Batch output | Not listed | Not listed |
| Inputs | image, text | text |
| Outputs | text | text |
| Tools | Not listed | Yes |
| Open weights | Yes | Yes |
| Knowledge cutoff | 2024-06-30 | Unknown |
| Third-party index | Unknown | Unknown |
| 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 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.
Qwen3 Coder Next is listed at $0.12 input and $0.80 output per million tokens, with a 262,144-token context window.