Qwen3 30B A3B Thinking 2507

Qwen · qwen/qwen3-30b-a3b-thinking-2507

← Back to leaderboard

Qwen3-30B-A3B-Thinking-2507 is a 30B parameter Mixture-of-Experts reasoning model optimized for complex tasks requiring extended multi-step thinking. The model is designed specifically for “thinking mode,” where internal reasoning traces are separated...

Qwen3 30B A3B Thinking 2507 ranks #223 of 348 models in the default AI Benchmark Hub order (quality first, then cost). At $1.30 blended per million tokens, it is cheaper than 45% of models with published API pricing. Its 81,920-token context window is 3.2× smaller than the catalog median (262,144 tokens).

open weightstexttext->text

Context

Max context: 81920
Max output: 32768

Pricing

Input / 1M: 0.20
Output / 1M: 2.40
Blend / 1M: 1.30

Quality

Quality index:

Provider

Provider: Qwen
Moderated: no

Monthly cost at this blended rate

Estimated API spend if every token is billed at $1.30per 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$1.30
10,000,000$13.00
100,000,000$130.00

Related models

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

More from Qwen

Closest API price