Alibaba
Qwen 3 235b A22B 2507
Qwen instruction model for multilingual chat, reasoning, and tool use
Model facts
- Context window
- 262K tokens
- Maximum output
- 262K tokens
- Cheapest paid input
- $0.072 per 1M tokens
- Cheapest paid output
- $0.464 per 1M tokens
- Open weights
- yes
- Providers
- 3
Capabilities and modalities
tool calling, structured output, temperature control, open weights, text.
Artificial Analysis benchmarks
Compare this model on the full LLM benchmark leaderboard.
| Configuration | AAI | Coding | Math | Output tokens/s |
|---|---|---|---|---|
| Reasoning | 19.9 | 22.1 | 91.0 | not measured |
Observed price history
- 2026-08-24: $0.072 input / $0.464 output per 1M tokens
API providers
- TensorX — model id qwen/qwen3-235b-a22b-2507; $0.072 input / $0.464 output per 1M tokens; provider documentation
- NanoGPT — model id qwen/Qwen3-235B-A22B-Instruct-2507; $0.13 input / $0.5 output per 1M tokens; provider documentation
- Amazon Bedrock — model id qwen.qwen3-235b-a22b-2507-v1:0; $0.22 input / $0.88 output per 1M tokens; provider documentation