/ Models

Language models

Qwen: 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...

Maker
Qwen
Context window
262K
Max output
33K
Input / 1M
$0.3
Output / 1M
$3
1M in + 1M out
$3.30

Everything else

Max output33K
Input / 1M$0.3
Output / 1M$3
Cache read / 1M
Cache write / 1M
1M in + 1M out$3.30
Takestext
Returnstext
Toolsyes
Reasoningalways on
Open weightsyes
Released2025-07-25
Knowledge cutoff2025-06-30
Retires
Catalog idqwen/qwen3-235b-a22b-thinking-2507

Benchmarks

sourceepoch
gpqa0.801
gpqaStderr0.026
aime0.867
aimeStderr0.0512
simpleQA0.501
simpleQAStderr0.0158

Benchmark scores by Epoch AI, CC BY 4.0.

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