← all models

Qwen3 235B A22B Thinking 2507

qwen · 22B active

openrouter
Parameters 235B openrouter api · from the model id
Context 125K 128000 tokens
Input $0.45 OpenRouter
Output $3.50 OpenRouter
Cache read — OpenRouter

Accepts

text

Capabilities

frequency_penalty include_reasoning max_tokens presence_penalty reasoning stop temperature tool_choice tools top_k top_p

Description

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...

The OpenRouter API truncates descriptions — read the full text at the source

Also known as

Every id and name this model has been seen under — for matching it against another catalogue.

openrouter qwen/qwen3-235b-a22b-thinking-2507 huggingface Qwen/Qwen3-235B-A22B-Thinking-2507 name Qwen: Qwen3 235B A22B Thinking 2507 display name Qwen3 235B A22B Thinking 2507

Identifiers

Vendor
qwen
OpenRouter
qwen/qwen3-235b-a22b-thinking-2507
Hugging Face
Qwen/Qwen3-235B-A22B-Thinking-2507
Active parameters
22B
Released
2025-07-25T13:19:17.000Z
First seen
59 d ago
Last crawled
1 h ago