/ Models

Language models

Qwen: Qwen3 VL 235B A22B Thinking

Qwen3-VL-235B-A22B Thinking is a multimodal model that unifies strong text generation with visual understanding across images and video. The Thinking model is optimized for multimodal reasoning in STEM and math....

Maker
Qwen
Context window
131K
Max output
33K
Input / 1M
$0.4
Output / 1M
$4
1M in + 1M out
$4.40

Everything else

Max output33K
Input / 1M$0.4
Output / 1M$4
Cache read / 1M
Cache write / 1M
1M in + 1M out$4.40
Takestext, image
Returnstext
Toolsyes
Reasoningalways on
Open weightsyes
Released2025-09-23
Knowledge cutoff2025-03-31
Retires
Catalog idqwen/qwen3-vl-235b-a22b-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