Qwen3 30B A3B Instruct 2507
Alibaba · Released Jul 2025
A 30.5B-parameter mixture-of-experts model from Alibaba's Qwen3 that activates 3.3B parameters per token, designed for instruction following and multilingual tasks.
- Strengths
- Delivers strong instruction-following and reasoning performance while maintaining efficient inference through its sparse mixture-of-experts architecture.
- Best for
- General-purpose tasks requiring multilingual support and instruction following where computational efficiency matters.
- Limitations
- As a sparse model with only 3.3B active parameters per token, it may underperform on tasks requiring deep reasoning or specialized domain knowledge compared to denser architectures of similar total parameter size.
Input / 1M
$0.0482
Output / 1M
$0.193
Cached input / 1M
—
Context window
128K
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 |
|---|---|---|---|---|---|
| 25 Jul 2026 | $0.0482 | $0.193 | — | Imported from OpenRouter | openrouter.ai |
| 15 Jul 2026 | $0.1 | $0.3 | — | Imported from OpenRouter | openrouter.ai |
| 11 Jun 2026 | $0.0482 | $0.193 | — | Imported from OpenRouter | openrouter.ai |