Qwen3-VL 235B-A22B
Qwen vision-language model for visual reasoning, documents, and agent tasks
Sources
Same model, different sources. Our first-party rate is listed first, then router and aggregator rows stay separate so you can see the spread instead of a single blended number.
| Source | Provider | Input | Output | Cache read | Context |
|---|---|---|---|---|---|
| models.devcheapestqwen3-vl-235b-a22b | Venice AI | $0.21 | $1.90 | $0.1 | 128K |
| LiteLLMaccounts/fireworks/models/qwen3-vl-235b-a22b-thinking | N/A | $0.22 | $0.88 | $0.022 | N/A |
| LiteLLMfireworks_ai/accounts/fireworks/models/qwen3-vl-235b-a22b-thinking | N/A | $0.22 | $0.88 | $0.022 | N/A |
| models.devqwen3-vl-235b-a22b | Alibaba / Qwen | $0.2867 | $1.15 | $0 | 131K |
| models.devqwen/qwen3-vl-235b-a22b-thinking | Merge Gateway | $0.287 | $2.87 | $0.0574 | 131K |
| models.devqwen/qwen3-vl-235b-a22b-thinking | OrcaRouter | $0.4 | $4 | $0 | 131K |
| LiteLLMqwen3-vl-235b-a22b-thinking | N/A | $0.4 | $4 | $0.04 | N/A |
| LiteLLMdashscope/qwen3-vl-235b-a22b-thinking | N/A | $0.4 | $4 | $0.04 | N/A |
| LiteLLMqwen_ai_platform/qwen3-vl-235b-a22b-thinking | N/A | $0.4 | $4 | $0.04 | N/A |
| LiteLLMqwencloud/qwen3-vl-235b-a22b-thinking | N/A | $0.4 | $4 | $0.04 | N/A |
| models.devqwen/qwen3-vl-235b-a22b-thinking | NanoGPT | $0.5 | $6 | $0.25 | 131K |
| models.devqwen.qwen3-vl-235b-a22b | Amazon Bedrock | $0.53 | $2.66 | $0 | 262K |
| LiteLLMqwen3-vl-235b-a22b | N/A | $0.53 | $2.66 | $0.053 | N/A |
| LiteLLMqwen.qwen3-vl-235b-a22b | N/A | $0.53 | $2.66 | $0.053 | N/A |
| models.devqwen3-vl-235b-a22b | Cortecs | $0.617 | $3.12 | $0.052 | 256K |
| models.devqwen3-vl-235b-a22b | Alibaba / Qwen | $0.7 | $2.80 | $0 | 131K |
| models.devQwen/Qwen3-VL-235B-A22B-Thinking | Hugging Face | $0.98 | $3.95 | $0 | 131K |
| models.devQwen3-VL-235B-A22B-Thinking | Jalapeno Cloud | $0.98 | $3.95 | $0 | 131K |
| LiteLLMqwen/qwen3-vl-235b-a22b-thinking | N/A | $0.98 | $3.95 | $0.098 | N/A |
| LiteLLMnovita/qwen/qwen3-vl-235b-a22b-thinking | N/A | $0.98 | $3.95 | $0.098 | N/A |
Capabilities
- Reasoning
- Tool calling
- Structured output
- Attachments
- Open weights
- In: text
- In: image
- Out: text
Scores
Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Hover or tap the i next to any score for its source. Full boards on /benchmarks.
Arena rows are community-vote Elo from Arena AI, Artificial Analysis indices arrive via OpenRouter, and launch-eval figures are collected from vendor announcements, analyst writeups, and community benchmarks. Full boards and credits on /benchmarks.
See what this model costs you
The app reads the sessions your tools already wrote and prices this model's tokens at the published API rate. Free on your computer.