Prices use the model developer's current official list prices. Billing units and applicable conditions are preserved for each tier; provider quotes may differ.
| Field | ||
|---|---|---|
| Organization | Alibaba | |
| Family | Qwen 3 | |
| Released | - | |
| Context window | 262K | |
| Max output | - | |
| Input modality | TextImageVideo | |
| Output type | Text | |
| Providers | ai&, AKI.IO, Ambient, Berget.AI, Blue Claw, Cerebras, Charm Hyper, Cloudflare Workers AI, Groq, Liquid AI, Mancer, NEAR AI Cloud, Neuralwatt, Nous Research, OpenRouter, OVHcloud AI Endpoints, Regolo AI, Scaleway, TensorX, Venice AI, Wafer | |
| Input | - | |
| Output | - | |
| Cache Read | - | |
| Cache Write | - | |
| Other charges | - | |
| Weights | Open | |
| Reasoning | ||
| Tool call |
Performance
Scoring rulesText scores use the site’s full-population calibration and scoring method, on a 0–100 scale. Media results stay separate by task and configuration; they do not contribute to the text score.