Qwen3 235B A22B Thinking 2507

Qwen · qwen/qwen3-235b-a22b-thinking-2507

← Back to leaderboard

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...

Qwen3 235B A22B Thinking 2507 ranks #221 of 348 models in the default AI Benchmark Hub order (quality first, then cost). At $1.26 blended per million tokens, it is cheaper than 45% of models with published API pricing. Its 131,072-token context window is 2.0× smaller than the catalog median (262,144 tokens).

open weightstexttext->text

Context

Max context: 131072
Max output: 117964

Pricing

Input / 1M: 0.23
Output / 1M: 2.30
Blend / 1M: 1.26

Quality

Quality index:

Provider

Provider: Qwen
Moderated: no

Monthly cost at this blended rate

Estimated API spend if every token is billed at $1.26per million (the blend of this model's input and output prices). Real bills depend on the input/output mix.

Tokens / monthEst. cost (USD)
1,000,000$1.26
10,000,000$12.65
100,000,000$126.50

Related models

Same lab, similar price, or similar quality — useful next comparisons.

More from Qwen

Closest API price