Qwen2.5 VL 72B Instruct
Public list price, verified 8h ago · cached input $0.40 /M
Added automatically from the public model catalog. Family and licence details are not curated yet; benchmark scores appear as upstream leaderboards list this model.
Benchmarks
vision
Massive Multi-discipline Multimodal Understanding; college-exam level questions with images across 30+ subjects.
Harder MMMU variant: text-only-answerable questions removed, ten answer options instead of four, and a vision-only setting where the question is embedded in the image.
performance
Median output speed in tokens per second over the last 14 days on the model maker's own API, measured nightly with a fixed ~800-token prompt and ~250-token answer. Models not yet probed fall back to a dated manual figure. Higher is faster.
Median time from request to first streamed token in milliseconds over the last 14 days on the model maker's own API, using the same nightly probe prompt. Lower is snappier; reasoning models are penalised here because they think before talking.
Reliability monitor
Loading drift signal…
Hosted endpoints
| Host | Input $/M | Output $/M | Context | Speed | TTFT | Uptime 24h | Quant |
|---|---|---|---|---|---|---|---|
| Host 29 | $0.80 | $1.00 | 128k | 54 tok/s | 0.34 s | 100.0% | fp8 |