AlibabaQwen2.5-VL 72B Instruct
Not yet ranked: too few independent results so far. Released 25 Mar 2025.
- Blended price
- $3.44/M
- $2.29 in · $6.88 out
- Output speed
- 3 tok/s
- First answer
- 0.69 s
- Context
- 131k
- Reasoning35
- Multimodal43
Benchmark results
One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Reasoning
| Benchmark | default | Source |
|---|---|---|
| Kagi LLM Benchmark | 36.0%#115 | Kagi LLM Benchmark |
Multimodal
| Benchmark | default | Source |
|---|---|---|
| LMArena Vision | 1107#106 | LMArena |
| MMMU (validation) | 64.5%#28 | MMMU |
| MMMU-Pro (official)not in index | 46.2%#18 | MMMU |
Where to run it
Every provider serving this model through OpenRouter, with throughput and first-token latency measured on live traffic over the last 30 minutes and each provider’s own price. Purple marks the best in each column.
| Provider | Speed | First token | Input $/M | Output $/M | Context | Quantisation |
|---|---|---|---|---|---|---|
| Parasail | 3 tok/s | 0.69 s | $0.800 | $1.00 | 128k | fp8 |
What a task costs
Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0030 | – | 1.7 min |
| Summarise a 30-page report | 12,000 / 600 | $0.032 | – | 3.3 min |
| Code edit | 6,000 / 1,500 | $0.024 | – | 8.3 min |
| Agentic coding session | 60,000 / 4,000 | $0.165 | – | 22.2 min |
| Structured extraction | 2,000 / 200 | $0.0060 | – | 1.1 min |
See also
Data as of 9 Sept 2026. Compare with another model.