QQwen · Released Feb 1, 2025
Qwen2.5 VL 72B Instruct
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.
- Released
- Feb 1 2025
- Context window
- 128K 115K out
- Input / 1M tokens
- $0.80 from $0.70
- Output / 1M tokens
- $1.00 from $0.70
Where to run it
8 providers compared
Cheapest: NanoGPT at $0.70 / $0.70 per 1M input / output tokens — 83% less than the priciest option.
| Provider | Input | Output | Cache read | Context | Max output | Uptime | vs. best |
|---|---|---|---|---|---|---|---|
| NanoGPTno tool calling | $0.70 | $0.70 | $0.35 | 66K | 8K | — | Cheapest |
| ParasailFP8 · no tool calling | $0.80 | $1.00 | $0.40 | 128K | 115K | 99.9%24h | +21% |
| Kilo Gatewayno tool calling | $0.80 | $1.00 | $0.40 | 128K | 115K | — | +21% |
| OVHcloud AI Endpointsno tool calling | $1.01 | $1.01 | — | 33K | 33K | — | +44% |
| Cortecsno tool calling | $1.01 | $1.01 | — | 32K | 32K | — | +45% |
| Alibaba (China) | $2.29 | $6.88 | — | 131K | 8K | — | +392% |
| Qiniu | $2.32 | $6.96 | — | 128K | 8K | — | +397% |
| Alibaba | $2.80 | $8.40 | — | 131K | 8K | — | +500% |
Value
Price vs. performance
Qwen2.5 VL 72B Instruct Other Qwen Other labs Value frontier · OSWorld vs. input price per 1M tokens (log scale) · Drag to pan, pinch or Ctrl + scroll to zoom, double-click to zoom in.
Benchmarks
3 benchmark scores
| Benchmark | Score | Rank | Leader |
|---|---|---|---|
| OSWorldAgents & computer use · Desktop and web tasks with keyboard and mouse | 5.0% | #6of 6 | Claude Sonnet 4.672.1% |
| SpatialViz-BenchDesign & visual · Mental rotation, folding and other spatial puzzles | 33.3% | #5of 5 | Gemini 2.5 Pro44.7% |
| GeoBenchDesign & visual · Guess the country a photo was taken in | 62.0% | #14of 15 | Gemini 3 Flash Preview88.0% |
Specs
Details
- Model ID
qwen/qwen2.5-vl-72b-instruct- Developer
- Qwen
- Release date
- Feb 1, 2025 ·
- Context window
- 128,000 tokens
- Max output
- 115,200 tokens
- API price
- $0.80 / $1.00 per 1M input / output tokens
- Providers
- 8
- Input types
- text, image
- Reasoning
- No
- Tool calling
- No
- Open weights
- Yes
- Free tier
- No
Release date and prices from OpenRouter's catalog; providers from OpenRouter and models.dev. Buying directly from a provider can cost a little differently. Speed, latency and uptime are measured on OpenRouter only; uptime is the share of OpenRouter requests each provider served over the last day. Benchmark scores are the best result per benchmark from Epoch AI, licensed CC BY 4.0. Rank counts every model tracked here with a score.