Qwen3 Max Thinking
Qwen builds the Qwen3 Max Thinking model, a chat-based AI capable of extended thinking and structured output, with notable strengths in intelligence and general problem-solving as evidenced by its top 25% scores in the Intelligence Index, GPQA, and HLE benchmarks. Its context window of 256,000 tokens allows for complex and nuanced conversations.
Input
Output
Context
256K
Max Output
66K
Parameters
-
Technical Specifications
Input Modalities
Output Modalities
Capabilities
Loading capabilities…
Benchmarks
Resources & Links
More models by Qwen
The creator's other models in the catalog, with their context, size and license where published.
Compare it, or keep browsing
Put this model beside its alternatives on the same evidence, or go back to the full catalog.
Frequently asked questions about Qwen3 Max Thinking
Answered from the entry's own fields: context, license, modalities, evidence, serving and the memory to self-host.
Qwen3 Max Thinking advertises a context window of 256,000 tokens, with a maximum output of 65,536 tokens in a single response. The figure is the creator's published maximum; a given host may serve less, and the gateway routes on what each host actually serves.
No. Qwen3 Max Thinking is a proprietary model (license: Proprietary): its weights are not distributed, and it runs only through Qwen's own API or a host with access to it.
Qwen3 Max Thinking accepts Text and produces Text. The capabilities card on this page lists which API features each deployment honours, such as function calling and structured output, with the source each was checked against.
Qwen3 Max Thinking has published results from Artificial Analysis, shown by suite in the benchmarks card above exactly as the publisher reported them. Scores are not combined across suites, and a suite that has not measured Qwen3 Max Thinking is shown as not available rather than estimated.
Yes. Qwen3 Max Thinking is served on the managed pool through the OpenAI-compatible endpoint as qwen3-max-thinking, pinned by name or chosen by routing when it is the best fit for a request. The Try in Playground button opens it directly.
Qwen3 Max Thinking cannot be self-hosted: its weights are not distributed. It is used through an API, either Qwen's own or the Inferbase gateway where it is served.
Fields collected from public registries, host APIs and benchmark publishers, each tagged with its source.
Last updated: Sep 22, 2026
Put intelligence in the middle.
One gateway in front of every model, with your policies applied and every decision on record. Start with $5 of credit and 5,000 routing decisions a month, no card required.