/ Models

Language models

Qwen: 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...

Maker
Qwen
Context window
262K
Max output
66K
Input / 1M
$0.78
Output / 1M
$3.90
1M in + 1M out
$4.68

Everything else

Max output66K
Input / 1M$0.78
Output / 1M$3.90
Cache read / 1M
Cache write / 1M
1M in + 1M out$4.68
Takestext
Returnstext
Toolsyes
Reasoningoptional
Open weightsno
Released2026-02-09
Knowledge cutoff
Retires
Catalog idqwen/qwen3-max-thinking

Using it

In 00, this model is picked per agent — and per tier, so the model that answers your customers need not be the one that writes your code. Get 00.

← all models