Qwen3 30B A3B
Alibaba · Released Apr 2025
A 30.5-billion-parameter mixture-of-experts model from Alibaba that activates 3.3 billion parameters per token.
- Strengths
- Delivers efficient inference through sparse activation while maintaining the reasoning capacity of a larger model across general tasks.
- Best for
- General-purpose workloads where you need balanced performance and computational efficiency at the 30B scale.
- Limitations
- Smaller context window (40k tokens) compared to other Qwen3 models; for extended reasoning, use the Thinking variant, and for specialized coding tasks, use Qwen3 Coder 30B A3B Instruct.
Input / 1M
$0.12
Output / 1M
$0.5
Cached input / 1M
—
Context window
40K
Price history
Input (solid)Output (dashed)
Price change
- 30d
- in decreased 0.0% out decreased 0.0%
- 90d
- in decreased 0.0% out decreased 0.0%
- 1y
- in decreased 0.0% out decreased 0.0%
- Since launch
- in decreased 0.0% out decreased 0.0%
Snapshots
| Effective | Input | Output | Cached in | Note | Source |
|---|---|---|---|---|---|
| 23 Aug 2026 | $0.12 | $0.5 | — | Imported from OpenRouter | openrouter.ai |
| 16 Aug 2026 | $0.13 | $0.52 | — | Imported from OpenRouter | openrouter.ai |
| 26 Jul 2026 | $0.12 | $0.5 | — | Imported from OpenRouter | openrouter.ai |
| 18 Jul 2026 | $0.13 | $0.52 | — | Imported from OpenRouter | openrouter.ai |
| 11 Jun 2026 | $0.12 | $0.5 | — | Imported from OpenRouter | openrouter.ai |