Skip to content
LLMs
Qwen logo

Qwen: Qwen3 30B A3B Thinking 2507

by Qwen

Qwen: Qwen3 30B A3B Thinking 2507 is a large language model from Qwen. It costs $0.200 per million input tokens and $2.40 per million output tokens. Its context window is 82K tokens.

ReasoningTool callingStructured outputOpen weights
Input / 1M tokens
$0.200
Output / 1M tokens
$2.40
Cached input / 1M
-

Not supported

Context window
82K

tokens

Who serves it cheapest

1 hosts serve Qwen3 30B A3B Thinking 2507. Same weights, same API - the price difference is pure margin and routing.

Providers serving Qwen: Qwen3 30B A3B Thinking 2507, cheapest first
ProviderInput / 1MOutput / 1MContextThroughputUptime 24h
AlibabaCheapest$0.200$2.4082K-100.0%

Benchmarks

Independent scores published alongside the catalogue.

Intelligence index
9.8
Coding index
12.1
Agentic index
0.9

About 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...

Specifications

Qwen: Qwen3 30B A3B Thinking 2507 specifications
Model IDqwen/qwen3-30b-a3b-thinking-2507
ProviderQwen
Context window82K tokens
Max output33K tokens
Input modalitiestext
Output modalitiestext
Knowledge cutoff2025-06-30
Open weightsYes - Qwen/Qwen3-30B-A3B-Thinking-2507
ReleasedAugust 28, 2025

Cheaper alternatives

Models that cost less than Qwen3 30B A3B Thinking 2507 while keeping at least half its context window and every input modality it supports.

Frequently asked

How much does Qwen: Qwen3 30B A3B Thinking 2507 cost?

$0.200 per million input tokens and $2.40 per million output tokens.

What is the context window of Qwen: Qwen3 30B A3B Thinking 2507?

82K tokens, with up to 33K tokens of output per request.

Confirm against the source: Qwen official pricing.