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
Price changes
Cheapest list input/output only. Rates move rarely, so this is an event log. Down means cheaper. Showing the 8 latest changes.
- ↓ lowerOutput $5.95 → $5.70
- ↓ lowerOutput $6 → $5.95
- ↓ lowerInput $2 → $1.95
- ↑ higherOutput $5.40 → $6
- ↑ higherInput $1.80 → $2
Sources
Same model, different sources. Our first-party rate is listed first, then router and aggregator rows stay separate so you can see the spread instead of a single blended number.
| Source | Provider | Input | Output | Cache read | Context |
|---|---|---|---|---|---|
| models.devcheapestqwen/qwen3.8-2.4t-a95b | IteraCompute | $1.95 | $5.70 | $0.25 | 1.0M |
| models.devQwen/Qwen3.8-2.4T-A95B | DeepInfra | $2 | $6 | $0.2 | 262K |
| models.devqwen/qwen3.8-2.4t-a95b | Eden AI | $2 | $6 | $0.25 | 1M |
| models.devqwen/qwen3.8-2.4t-a95b | Kilo Gateway | $2 | $6 | $0.25 | 1M |
| models.devQwen/Qwen3.8-2.4T-A95B | Modal | $2 | $6 | $0.25 | 1.0M |
| models.devqwen/qwen3.8-2.4t-a95b | Novita AI | $2 | $6 | $0.25 | 1M |
| OpenRouterqwen/qwen3.8-2.4t-a95b | OpenRouter | $2 | $6 | $0.25 | 1.0M |
| models.devQwen/Qwen3.8-2.4T-A95B | SiliconFlow | $2 | $6 | $0.25 | 1.0M |
| models.devalibaba/qwen3.8-2.4t-a95b | Vercel AI Gateway | $2 | $6 | $0.25 | 262K |
| models.devqwen3.8-2.4t-a95b | AIHubMix | $2 | $6 | $0.5 | 262K |
| models.devqwen3.8-2.4t-a95b | Charm Hyper | $2 | $6 | $0.25 | 1M |
| models.devqwen3.8-2.4t-a95b | DevPass (LLM Gateway) | $2 | $6 | $0.25 | 1.0M |
| models.devqwen3.8-2.4T-A95B | Requesty | $2 | $6 | $0.2 | 262K |
| models.devaccounts/fireworks/models/qwen3p8-2p4t-a95b | Fireworks AI | $2 | $6 | $0.25 | 262K |
| models.devnovita/qwen3.8-2.4t-a95b | LLM Gateway | $2 | $6 | $0.25 | 1M |
| LiteLLMQwen/Qwen3.8-2.4T-A95B | N/A | $2 | $6 | $0.25 | N/A |
| LiteLLMQwen3.8-2.4T-A95B | N/A | $2 | $6 | $0.25 | N/A |
| LiteLLMstreamlake/qwen3.8-2.4t-a95b | N/A | $2 | $6 | $0.25 | N/A |
| LiteLLMtogether_ai/Qwen/Qwen3.8-2.4T-A95B | N/A | $2 | $6 | $0.25 | N/A |
| models.devqwen/qwen3.8-2.4t-a95b | TensorX | $2.50 | $6 | $0.63 | 262K |
| models.devqwen3.8-2.4t-a95b | Cortecs | $2.50 | $6 | $0.625 | 262K |
| models.devqwen3.8-2.4t-a95b | Opper | $2.50 | $6 | $0.63 | 262K |
| models.devQwen/Qwen3.8-2.4T-A95B | Hugging Face | $2.50 | $6.25 | $0 | 262K |
| models.devqwen/qwen3.8-2.4t-a95b | Merge Gateway | $2.50 | $6.25 | $0.5 | 262K |
| models.devalibaba/qwen3.8-2.4t-a95b | AI/ML API | $2.65 | $6.61 | $0.529 | 262K |
Capabilities
- Reasoning
- Tool calling
- Structured output
- Attachments
- Open weights
- In: text
- In: image
- Out: text
Scores
Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Hover or tap the i next to any score for its source. Full boards on /benchmarks.
- AA intelligence39.9i
- AA coding71.9i
- AA agentic50.1i
Arena rows are community-vote Elo from Arena AI, Artificial Analysis indices arrive via OpenRouter, and launch-eval figures are collected from vendor announcements, analyst writeups, and community benchmarks. Full boards and credits on /benchmarks.
See what this model costs you
The app reads the sessions your tools already wrote and prices this model's tokens at the published API rate. Free on your computer.