/ Models

Language models

Qwen: Qwen3 30B A3B Thinking 2507

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...

Maker
Qwen
Context window
82K
Max output
33K
Input / 1M
$0.2
Output / 1M
$2.40
1M in + 1M out
$2.60

Everything else

Max output33K
Input / 1M$0.2
Output / 1M$2.40
Cache read / 1M
Cache write / 1M
1M in + 1M out$2.60
Takestext
Returnstext
Toolsyes
Reasoningalways on
Open weightsyes
Released2025-08-28
Knowledge cutoff2025-06-30
Retires
Catalog idqwen/qwen3-30b-a3b-thinking-2507

Using it

In 00, this model is picked per agent — and per tier, so the model that answers your customers need not be the one that writes your code. Get 00.

← all models