Models / Alibaba / Qwen3.8 2.4T A95B
Alibaba · qwen
Qwen3.8 2.4T A95B
Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows
$2.00 in · $6.00 out
per 1M tokens · provider rate closest to the median. No first-party Alibaba price was listed. The reference price is AIHubMix's rate, the provider closest to the median.
Provider input prices run from $1.95 to $3.44 per 1M tokens. Output prices run from $5.95 to $8.60.
- Context
- 262,144
- Max output
- 131,072
- Cache read
- $0.50
- Cache write
- —
- Reasoning
- Yes
- Tool calls
- Yes
- Structured output
- Yes
- Vision
- No
- Open weights
- Yes
- License
- qwen3.8-max
- Released
- Aug 12, 2026
- Updated in source
- Aug 12, 2026
- Knowledge
- —
- Providers
- 23
Providers
| Provider | Input | Output | Cache read | Cache write | Status |
|---|---|---|---|---|---|
| IteraCompute | $1.95 | $5.95 | $0.20 | — | — |
| AIHubMixreference | $2.00 | $6.00 | $0.50 | — | — |
| Charm Hyper | $2.00 | $6.00 | $0.25 | — | — |
| Deep Infra | $2.00 | $6.00 | $0.20 | — | deprecated |
| DevPass | $2.00 | $6.00 | $0.25 | — | — |
| Eden AI | $2.00 | $6.00 | $0.25 | $2.50 | — |
| Fireworks AI | $2.00 | $6.00 | $0.25 | — | — |
| Kilo Gateway | $2.00 | $6.00 | $0.25 | $2.50 | — |
| LLM Gateway | $2.00 | $6.00 | $0.25 | — | — |
| Modal | $2.00 | $6.00 | $0.25 | — | — |
| Novita AI | $2.00 | $6.00 | $0.25 | — | — |
| OpenRouter | $2.00 | $6.00 | $0.25 | — | — |
| Requesty | $2.00 | $6.00 | $0.20 | — | — |
| RunInfra | $2.00 | $6.00 | $0.20 | — | — |
| SiliconFlow | $2.00 | $6.00 | $0.25 | — | — |
| Vercel AI Gateway | $2.00 | $6.00 | $0.25 | — | — |
| Cortecs | $2.50 | $6.00 | $0.63 | — | — |
| Hugging Face | $2.50 | $6.25 | — | — | — |
| Merge Gateway | $2.50 | $6.25 | $0.50 | — | — |
| Opper | $2.50 | $6.00 | $0.63 | — | — |
| TensorX | $2.50 | $6.00 | $0.63 | — | — |
| Venice AI | $2.50 | $7.50 | $0.31 | — | — |
| AI/ML API | $3.44 | $8.60 | $0.69 | — | — |
Jobs this model qualifies for
- Coding agents — clears the bar
- Long-document Q&A — clears the bar
- Cheapest summarization — clears the bar