/ Models

Language models

Qwen: Qwen3 235B A22B

Qwen3-235B-A22B is a 235B parameter mixture-of-experts (MoE) model developed by Qwen, activating 22B parameters per forward pass. It supports seamless switching between a "thinking" mode for complex reasoning, math, and...

Maker
Qwen
Context window
131K
Max output
8K
Input / 1M
$0.455
Output / 1M
$1.82
1M in + 1M out
$2.27

Everything else

Max output8K
Input / 1M$0.455
Output / 1M$1.82
Cache read / 1M
Cache write / 1M
1M in + 1M out$2.27
Takestext
Returnstext
Toolsyes
Reasoningoptional
Open weightsyes
Released2025-04-28
Knowledge cutoff2025-03-31
Retires
Catalog idqwen/qwen3-235b-a22b

Benchmarks

sourceepoch
eci139.58
confidenceLikely
accessibilityOpen weights (unrestricted)
gpqa0.707
gpqaStderr0.0271
mathLevel50.689
mathLevel5Stderr0.0095

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