Qwen vision-language model for visual reasoning, documents, and agent tasks
Qwen3-VL 235B-A22B by alibaba is offered by 5 providers on this page. Its official list price is $0.70 per 1M input tokens and $2.80 per 1M output tokens. The lowest paid channel is Alibaba (China) at $0.287 / $1.15 per 1M, about 8.4× below the list price.
Artificial Analysis rates it 13.4 on the Intelligence Index. Against its lowest blended price of $0.502 per 1M, that is roughly 27 index points per dollar, which is the value ratio the leaderboards rank on. Median output speed is 58 tokens per second, with 2.93s to the first token.
The context window is 131,072 tokens at the reference host, but hosts report different limits, from 128,000 to 256,000, so the usable window depends on the provider you pick. It supports reasoning, tool use, and structured output. Accepted input modalities are Text and Image. The weights are open, so it can also be self-hosted or served through a gateway of your choice. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use. Its training knowledge cuts off at 2025-04.
Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| Alibaba (China)Official | First-party | $0.29 | $1.15 | — | — | 131,072 | 32,768 | |
| Venice AI | Gateway | $0.21 | $1.90 | $0.10 | — | 128,000 ⚠ | 16,384 | |
| AlibabaOfficial | First-party | $0.70 | $2.80 | — | — | 131,072 | 32,768 | |
| Cortecs | Gateway | $0.62 | $3.12 | $0.052 | — | 256,000 ⚠ | 256,000 | |
| STACKIT Qwen/Qwen3-VL-235B-A22B-Instruct-FP8 | Cloud | $1.76 | $2.05 | — | — | 218,000 ⚠ | 16,384 |
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.
2 / 5 providers expose no reasoning control (reasoning_options: []).
Individual evaluations run by Artificial Analysis, on the same reasoning tier as the intelligence score above. Each benchmark has its own task set and harness, so rows are not comparable with one another. The Intelligence Index above draws on a different, newer set of evaluations.