AI Observatory / Model Radar Qwen / qwen/qwen3-30b-a3b-thinking-2507

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...

131,072 Context
131,072 Max output
$0.08 / 1M Prompt price
2025-08-28 Created
01 / Snapshot

Pricing, context, modalities, and parameters.

Model Radar detail pages stay neutral and operator-readable: core metadata first, then workflow fit.

Provider Qwen Input modalities text
Output modalities text Prompt price $0.08 / 1M
Completion price $0.40 / 1M Request price N/A
Context length 131,072 Max completion tokens 131,072
Supported parameters frequency_penalty, include_reasoning, logit_bias, max_tokens, min_p, presence_penalty, reasoning, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_p
Best for qwen/qwen3-30b-a3b-thinking-2507

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...

Deep analysis High-volume usage Coding workflows tool-capable low-cost
03 / Colophon

Routes and exits.

Each model page stays simple: overview, compare, related models, then back to the public hub.