Qwen3 30B A3B Thinking 2507
Alibaba · Released Aug 2025
A 30B parameter mixture-of-experts model from Alibaba designed for reasoning tasks with extended thinking capabilities and internal reasoning traces.
- Strengths
- Excels at multi-step reasoning and complex problem-solving through its internal thinking mechanism that separates reasoning from output.
- Best for
- Tasks requiring detailed step-by-step reasoning, mathematical problem-solving, and complex logical inference where the model's intermediate thinking process is valuable.
- Limitations
- The extended thinking approach increases latency and token consumption; may be overkill for straightforward queries that don't benefit from explicit reasoning traces.
Input / 1M
$0.13
Output / 1M
$1.56
Cached input / 1M
—
Context window
81K
Price history
Input (solid)Output (dashed)
Price change
- 30d
- in increased 62.5% out increased 290.0%
- 90d
- in increased 62.5% out increased 290.0%
- 1y
- in increased 62.5% out increased 290.0%
- Since launch
- in increased 62.5% out increased 290.0%
Snapshots
| Effective | Input | Output | Cached in | Note | Source |
|---|---|---|---|---|---|
| 2 Jul 2026 | $0.13 | $1.56 | — | Imported from OpenRouter | openrouter.ai |
| 11 Jun 2026 | $0.08 | $0.4 | $0.08 | Imported from OpenRouter | openrouter.ai |