---
id: "qwen/qwen3-max-thinking"
also: ["qwen/qwen3-max-thinking-20260123", "vercel/alibaba/qwen3-max-thinking"]
cheapest_list_usd_per_m: "0.78 in, 3.9 out, at alibaba on openrouter"
cheapest_effective_usd_per_m: "1.2 in, 6.0 out, at alibaba on vercel"
context: 262144
max_output: 65536
input: ["text"]
output: ["text"]
released: "2026-02-09"
params: ["frequency_penalty", "include_reasoning", "logprobs", "max_tokens", "presence_penalty", "reasoning", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p"]
endpoints: 2
gateways: "openrouter (1), vercel (1)"
no_training: 2
trains: 0
retains_prompts: 1
intelligence: 21.3000
---
# Qwen: Qwen3 Max Thinking

Compared with the snapshot as of September 23, 2025, the Qwen-3 series Max model in this release achieves an effective integration of thinking and non-thinking modes, resulting in a comprehensive and substantial improvement in the model’s overall performance. In thinking mode, the model simultaneously supports web search, web information extraction, and a code interpreter tool, enabling it to tackle more complex and challenging problems with greater accuracy by leveraging external tools while engaging in slow, deliberative reasoning. This version is based on a snapshot taken on January 23, 2026.