Qwen3 235B A22B Thinking 2507

Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively supports up to 262,144 tokens of context. This "thinking-only" variant enhances structured logical reasoning, mathematics, science, and long-form generation, showing strong benchmark performance across AIME, SuperGPQA, LiveCodeBench, and MMLU-Redux. It enforces a special reasoning mode (</think>) and is designed for high-token outputs (up to 81,920 tokens) in challenging domains. The model is instruction-tuned and excels at step-by-step reasoning, tool use, agentic workflows, and multilingual tasks. This release represents the most capable open-source variant in the Qwen3-235B series, surpassing many closed models in structured reasoning use cases.

ChatQwen262k tokens$0.2507 / $2.5071 · 1M

qwen/qwen3-235b-a22b-thinking-2507

Context
262k tokens
Completion cap
—
Tools
Yes
JSON
Yes
Released
2025-07-25

Call it from Geek Hub

Same OpenAI SDK. Change the base URL and the model id.

curl https://api.geekhub.mx/v1/chat/completions \
  -H "Authorization: Bearer $GEEKHUB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen/qwen3-235b-a22b-thinking-2507",
    "messages": [{"role": "user", "content": "Hola"}]
  }'
Get an API key

Frequently asked questions

What is Qwen3 235B A22B Thinking 2507?
Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively supports up to 262,144 tokens of context. This "thinking-only" variant enhances structured logical reasoning, mathematics, science, and long-form generation, showing strong benchmark performance across AIME, SuperGPQA, LiveCodeBench, and MMLU-Redux. It enforces a special reasoning mode (</think>) and is designed for high-token outputs (up to 81,920 tokens) in challenging domains. The model is instruction-tuned and excels at step-by-step reasoning, tool use, agentic workflows, and multilingual tasks. This release represents the most capable open-source variant in the Qwen3-235B series, surpassing many closed models in structured reasoning use cases. Qwen3 235B A22B Thinking 2507 runs on the Geek Hub API (OpenAI-compatible). Model id: qwen/qwen3-235b-a22b-thinking-2507.
Is Qwen3 235B A22B Thinking 2507 free?
No. Input is $0.2507 per 1M tokens and output is $2.5071 per 1M tokens on Geek Hub (markup included).
What is the context length of Qwen3 235B A22B Thinking 2507?
Qwen3 235B A22B Thinking 2507 has a 262k tokens context window.
Does Qwen3 235B A22B Thinking 2507 support tool calling and structured outputs?
Qwen3 235B A22B Thinking 2507 accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.
When was Qwen3 235B A22B Thinking 2507 released?
Qwen3 235B A22B Thinking 2507 was released on 2025-07-25.

More models from Qwen