Qwen3.8 2.4T A95B (batch)
Alibaba · Released Aug 2026
Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model that activates 95 billion parameters from a 2.4 trillion total parameter pool.
- Strengths
- The sparse architecture enables efficient inference with a large active parameter count, and the 1 million token context window supports long-document processing.
- Best for
- Batch inference tasks where throughput and cost efficiency matter more than latency, and applications requiring extended context for reasoning over large documents.
- Limitations
- As an open-weight model, it lacks the multimodal capabilities and higher throughput of Qwen3.8 Max Prime and does not support image or video inputs like other Qwen3.8 variants.
Input / 1M
$2.00
Output / 1M
$6.00
Cached input / 1M
$0.25
Context window
1.01M
Price history
Input (solid)Output (dashed)
Price change
- 30d
- in — out —
- 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 |
|---|---|---|---|---|---|
| 2 Sep 2026 | $2.00 | $6.00 | $0.25 | Imported from OpenRouter | openrouter.ai |
| 1 Sep 2026 | $2.50 | $6.25 | $0.5 | Imported from OpenRouter | openrouter.ai |
| 31 Aug 2026 | $2.00 | $6.00 | $0.25 | Imported from OpenRouter | openrouter.ai |
| 29 Aug 2026 | $2.50 | $6.25 | $0.5 | Imported from OpenRouter | openrouter.ai |
| 28 Aug 2026 | $2.00 | $6.00 | $0.25 | Imported from OpenRouter | openrouter.ai |