Hub/Models/qwen/qwen3-235b-a22b-thinking-2507
qwentext → text

Qwen: Qwen3 235B A22B Thinking 2507

Canonical ID: qwen/qwen3-235b-a22b-thinking-2507

Compare ModelOpen on OpenRouter →

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...

Artificial Analysis Benchmarks

Verified
No standardized Artificial Analysis benchmark scores recorded for this variant yet.

Token Pricing & Economics

Prompt Input (1M Tokens)
$0.45
Input
Completion Output (1M Tokens)
$3.50
Output
Prompt KV-Cache Read (1M Tokens)
$0.00
Cached
Context Window Capacity
125k tokens
Context

Supported Parameters & Features

frequency_penaltyinclude_reasoningmax_tokenspresence_penaltyreasoningstoptemperaturetool_choicetoolstop_ktop_p