QQwen · Released Aug 12, 2026
Qwen3.8 2.4T A95B
Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of [Qwen3.8 Max](/qwen/qwen3.8-max), with 95 billion active parameters out of 2.4 trillion total. It is...
- Released
- Aug 12 2026
- Context window
- 1M 909K out
- Input / 1M tokens
- $2.00 from $1.95
- Output / 1M tokens
- $6.00 from $5.70
Where to run it
26 providers compared
Cheapest: IteraCompute at $1.95 / $5.70 per 1M input / output tokens — 39% less than the priciest option.
| Provider | Input | Output | Cache read | Context | Max output | Uptime | vs. best |
|---|---|---|---|---|---|---|---|
| IteraCompute | $1.95 | $5.70 | $0.25 | 1M | 131K | — | Cheapest |
| Novita | $2.00 | $6.00 | $0.25 | 1M | 131K | 100%24h | +4% |
| Alibaba | $2.00 | $6.00 | $0.25 | 1M | 131K | 100%24h | +4% |
| SiliconFlowFP8 | $2.00 | $6.00 | $0.25 | 1M | 131K | 100%24h | +4% |
| Together | $2.00 | $6.00 | $0.25 | 1.01M | 909K | 99.8%24h | +4% |
| Venice | $2.00 | $6.00 | $0.25 | 262K | 66K | 99.5%24h | +4% |
| Modal | $2.00 | $6.00 | $0.25 | 1.01M | 131K | — | +4% |
| Kilo Gateway | $2.00 | $6.00 | $0.25 | 1.01M | 909K | — | +4% |
| Vercel AI Gateway | $2.00 | $6.00 | $0.25 | 262K | 128K | — | +4% |
| LLM Gateway | $2.00 | $6.00 | $0.25 | 1M | 131K | — | +4% |
| AIHubMix | $2.00 | $6.00 | $0.50 | 262K | 131K | — | +4% |
| Fireworks AI | $2.00 | $6.00 | $0.25 | 262K | 131K | — | +4% |
| Charm Hyper | $2.00 | $6.00 | $0.25 | 1M | 128K | — | +4% |
| Novita AI | $2.00 | $6.00 | $0.25 | 1M | 131K | — | +4% |
| DevPass (LLM Gateway) | $2.00 | $6.00 | $0.25 | 1.01M | 131K | — | +4% |
| RunInfra | $2.00 | $6.00 | $0.20 | 262K | 33K | — | +4% |
| Deep Infra | $2.00 | $6.00 | $0.20 | 262K | 131K | — | +4% |
| Eden AI | $2.00 | $6.00 | $0.25 | 1M | 131K | — | +4% |
| Cortecs | $2.50 | $6.00 | $0.63 | 262K | 262K | — | +17% |
| Requesty | $2.50 | $6.00 | $0.63 | 1M | 262K | — | +17% |
| TensorX | $2.50 | $6.00 | $0.63 | 262K | 64K | — | +17% |
| Opper | $2.50 | $6.00 | $0.63 | 262K | 131K | — | +17% |
| Hugging Face | $2.50 | $6.25 | — | 262K | 131K | — | +19% |
| Merge Gatewayno tool calling | $2.50 | $6.25 | $0.50 | 262K | 1.01M | — | +19% |
| Venice AI | $2.50 | $7.50 | $0.31 | 262K | 66K | — | +30% |
| AI/ML API | $3.44 | $8.60 | $0.69 | 262K | 52K | — | +64% |
Benchmarks
Benchmark scores
No benchmark scores yet — Epoch AI hasn't evaluated Qwen3.8 2.4T A95B. Scores appear here automatically once it does.
Specs
Details
- Model ID
qwen/qwen3.8-2.4t-a95b- Developer
- Qwen
- Release date
- Aug 12, 2026 ·
- Context window
- 1,048,576 tokens
- Max output
- 909,000 tokens
- API price
- $2.00 / $6.00 per 1M input / output tokens
- Providers
- 26
- Input types
- text
- Reasoning
- Yes
- Tool calling
- Yes
- Open weights
- Yes
- Free tier
- No
Release date and prices from OpenRouter's catalog; providers from OpenRouter and models.dev. Buying directly from a provider can cost a little differently. Speed, latency and uptime are measured on OpenRouter only; uptime is the share of OpenRouter requests each provider served over the last day. Benchmark scores are the best result per benchmark from Epoch AI, licensed CC BY 4.0. Rank counts every model tracked here with a score.