Qwen3 Max Thinking

Qwen3-Max-Thinking is the flagship reasoning model in the Qwen3 series, designed for high-stakes cognitive tasks that require deep, multi-step reasoning. By significantly scaling model capacity and reinforcement learning compute, it delivers major gains in factual accuracy, complex reasoning, instruction following, alignment with human preferences, and agentic behavior.

ChatQwen262k tokens$0.8502 / $4.2512 · 1M

qwen/qwen3-max-thinking

Context
262k tokens
Completion cap
65,536
Tools
Yes
JSON
Yes
Released
2026-02-09

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-max-thinking",
    "messages": [{"role": "user", "content": "Hola"}]
  }'
Get an API key

Frequently asked questions

What is Qwen3 Max Thinking?
Qwen3-Max-Thinking is the flagship reasoning model in the Qwen3 series, designed for high-stakes cognitive tasks that require deep, multi-step reasoning. By significantly scaling model capacity and reinforcement learning compute, it delivers major gains in factual accuracy, complex reasoning, instruction following, alignment with human preferences, and agentic behavior. Qwen3 Max Thinking runs on the Geek Hub API (OpenAI-compatible). Model id: qwen/qwen3-max-thinking.
Is Qwen3 Max Thinking free?
No. Input is $0.8502 per 1M tokens and output is $4.2512 per 1M tokens on Geek Hub (markup included).
What is the context length of Qwen3 Max Thinking?
Qwen3 Max Thinking has a 262k tokens context window. It supports up to 65,536 completion tokens.
Does Qwen3 Max Thinking support tool calling and structured outputs?
Qwen3 Max Thinking accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.
When was Qwen3 Max Thinking released?
Qwen3 Max Thinking was released on 2026-02-09.

More models from Qwen