OpenAI-compatible — swap the base URL and it works with your existing SDK.
| Type | Price |
|---|---|
| Input | |
| Output | |
| Benchmark | Score | What it measures | Source | Retrieved |
|---|---|---|---|---|
| Intelligence | 9.5 | Composite score across standardised reasoning, knowledge and problem-solving evaluations, measured independently by Artificial Analysis | Source | September 12, 2026 |
| Math | 82 | Composite score across standardised mathematics evaluations, measured independently by Artificial Analysis | Source | September 12, 2026 |
| Model | Input | Output | Context | Best for |
|---|---|---|---|---|
Qwen3 235B A22B Thinking This page | ||||
| Reasoning + agents | ||||
| Balanced coding + agents | ||||
| Long-context, multimodal & agentic workflows | ||||
| Reasoning + agents |
Yes, Qwen3 235B A22B Thinking can stream responses as they are generated.
Yes, Qwen3 235B A22B Thinking supports both function calling and structured outputs.
Qwen3 235B A22B Thinking was built by Alibaba Cloud.
Yes, it is built with reasoning capability as one of its core features.
It is accessed via the v1/chat/completions endpoint.
