Qwen3.8 2.4T A95B
Alibaba · Released Aug 2026
An open-weight sparse mixture-of-experts model from Alibaba with 95 billion active parameters drawn from a 2.4 trillion total parameter pool.
- Strengths
- Scales reasoning capability across a large parameter space while activating only a fraction of parameters per inference, enabling efficient handling of complex tasks.
- Best for
- Batch processing and cost-sensitive deployments where model capacity and reasoning depth matter but latency constraints are relaxed.
- Limitations
- Designed as a batch-oriented variant; the sparse mixture-of-experts architecture trades inference speed for model scale, making it less suitable for latency-critical applications.
Input / 1M
$2.00
Output / 1M
$6.00
Cached input / 1M
$0.25
Context window
1M
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 |
|---|---|---|---|---|---|
| 3 Sep 2026 | $2.00 | $6.00 | $0.25 | Imported from OpenRouter | openrouter.ai |
| 2 Sep 2026 | $2.00 | $6.00 | $0.2 | Imported from OpenRouter | openrouter.ai |
| 1 Sep 2026 | $2.00 | $6.00 | $0.25 | Imported from OpenRouter | openrouter.ai |
| 31 Aug 2026 | $2.00 | $6.00 | $0.2 | Imported from OpenRouter | openrouter.ai |
| 29 Aug 2026 | $2.00 | $6.00 | $0.25 | Imported from OpenRouter | openrouter.ai |
| 28 Aug 2026 | $2.00 | $6.00 | $0.2 | Imported from OpenRouter | openrouter.ai |
| 13 Aug 2026 | $2.00 | $6.00 | $0.25 | Imported from OpenRouter | openrouter.ai |
| 12 Aug 2026 | $2.00 | $6.00 | $0.2 | Imported from OpenRouter | openrouter.ai |