qwentext → text
Qwen: Qwen3 235B A22B Thinking 2507
Canonical ID: 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...
Artificial Analysis Benchmarks
VerifiedNo standardized Artificial Analysis benchmark scores recorded for this variant yet.
Token Pricing & Economics
Prompt Input (1M Tokens)
Input$0.45
Completion Output (1M Tokens)
Output$3.50
Prompt KV-Cache Read (1M Tokens)
Cached$0.00
Context Window Capacity
Context125k tokens
Supported Parameters & Features
frequency_penaltyinclude_reasoningmax_tokenspresence_penaltyreasoningstoptemperaturetool_choicetoolstop_ktop_p