Input
$0.80
Output
$1
Context
128K
Qwen2.5 VL 72B Instruct costs $0.80 per million input tokens and $1 per million output tokens. Cached input is billed at $0.40 per million, 50% less than fresh input.
Specifications
| Lab | Qwen |
| Model id | qwen/qwen2.5-vl-72b-instruct |
| Input price | $0.80 per million tokens |
| Output price | $1 per million tokens |
| Cached input price | $0.40 per million tokens |
| Context window | 128,000 tokens (128K) |
| Maximum output | 115,200 tokens (115K) |
| Tool calling | no |
| Image input | yes |
| Reasoning | no |
| First listed | 1 February 2025 |
Qwen's other models
| Model | Input / 1M | Output / 1M | Context | Listed |
|---|---|---|---|---|
| Qwen3.8 Max Prime | $4 | $12 | 1M | 23 September 2026 |
| Qwen3.8 Omni Flash | $0.15 | $0.47 | 1M | 21 September 2026 |
| Qwen3.8 Max (0902) | $2 | $6 | 1M | 3 September 2026 |
| Qwen3.8 Flash | $0.15 | $0.47 | 1M | 26 August 2026 |
| Qwen3.8 27B | $0.15 | $1.875 | 1M | 14 August 2026 |
| Qwen3.8 2.4T A95B | $2 | $6 | 1M | 12 August 2026 |
| Qwen3.7 Flash | $0.03 | $0.13 | 1M | 27 July 2026 |
| Qwen3.7 Plus | $0.32 | $1.28 | 1M | 3 June 2026 |
| Qwen3.7 Max | $1.475 | $4.425 | 1M | 21 May 2026 |
| Qwen3.5 Plus 2026-04-20 | $0.30 | $1.80 | 1M | 27 April 2026 |
| Qwen3.6 27B | $0.32 | $3.20 | 256K | 27 April 2026 |
| Qwen3.6 35B A3B | $0.10 | $0.90 | 256K | 27 April 2026 |
Where these numbers come from
Read from OpenRouter's listing of Qwen2.5 VL 72B Instruct every 6 hours into the catalog Founden's builders choose their models from. Prices are OpenRouter's listed price per million tokens: for a lab's closed models that is the lab's own list price, and for an open-weight model it is the price of the host OpenRouter routes to by default, which can differ from the lab's own API and from other hosts. US dollars, before batch, volume or regional discounts. Every model.