AGENTKERNEL
- Home
- All models
- Qwen3.8 2.4T A95B
Qwen3.8 2.4T A95B: price, performance and context
Open Qwen3.8 2.4T A95B by Qwen costs $2.00 per 1M input and $6.00 per 1M output tokens, handles up to 1M tokens in one request (≈ 3,100 pages of text) and scores 39.9 points on the AgentKernel performance index, rank 24 of 212.
Privacy: zero data retention with 6 providers, not in the EU. Availability over the last 24 h: 100%.
Open in the interactive comparisonKey facts
- Licence
- Open weights: free to download and self-host
- Input / 1M tokens
- $2.00
- Output / 1M tokens
- $6.00
- Context window
- 1M tokens
- Max. output
- 131.1K tokens
- Performance index
- 39.9 points · rank 24 of 212
- Coding index
- 71.9 points · rank 18 of 119
- Agentic index
- 50.1 points · rank 11 of 91
- Cost at your usage
- $3.50 / month
- Knowledge cutoff
- n/a
- In the catalog since
- Aug 12, 2026
- Capabilities
- Reasoning, Tool Calling
What do you get for $10.00?
Rules of thumb from the cost calculator, base rates without caching or taxes.
| Task | Cost per task | For $10.00 |
|---|---|---|
| Chat repliesA question with a short history, a detailed answer | $0.004 | 2,800 |
| Email draftsBullet points in, a finished email out | $0.003 | 3,400 |
| Document summariesRead 10 pages, write a one-page summary | $0.01 | 1,000 |
| Code reviewsReview and comment on 500 lines of code | $0.017 | 590 |
| Book analysesAnalyse a 300-page book in one go | $0.212 | 47 |
Cheaper with similar performance
| Model | Licence | Performance | Your cost / month |
|---|---|---|---|
| Ling 3.1 FlashinclusionAI | Proprietary | 41.1 | $0.00 |
| MiMo-V2.6-FlashXiaomi | Open | 37.9 | $0.21 |
| Claude Haiku 5.5Anthropic | Proprietary | 43.4 | $0.225 |
Stronger models
| Model | Licence | Performance | Your cost / month |
|---|---|---|---|
| Claude Opus 4.7Anthropic | Proprietary | 40.7 | $11.25 |
| Gemini 3.8 FlashGoogle | Proprietary | 40.9 | $1.688 |
| Ling 3.1 FlashinclusionAI | Proprietary | 41.1 | $0.00 |