Qwen3.8-2.4T-A95B: API Pricing, Context Window & Benchmarks
Qwen3.8-2.4T-A95B is a language model from Qwen, released in August 2026.
Qwen3.8-2.4T-A95B is the open-weight checkpoint of Qwen3.8-Max: a text-only Mixture-of-Experts model with 2.4 trillion total parameters and 95 billion active parameters. Thinking is always on. Native context length is 262,144 tokens,
Qwen3.8-2.4T-A95B latency
Qwen3.8-2.4T-A95B time to first token, sustained output throughput, and failed-request rate from live API traffic over the trailing 7 days.
Qwen3.8-2.4T-A95B examples
Recent arena outputs from Qwen3.8-2.4T-A95B, picked from the highest-ranked matchups.
Qwen3.8-2.4T-A95B license
Qwen3.8-2.4T-A95B is a proprietary model available under its provider's product and API terms, has 2.4T parameters.
- License
- Qwen3.8-Max License
- Hosted access
- Parameters
- 2.4T
Open-weights license permitting use, modification, distribution, sublicensing, sale, deployment, hosting, and fine-tuning. Commercial products or services with more than 100M monthly active users or more than US$20M monthly revenue must prominently display the model name. Model-as-a-Service or AI Work Assistant businesses whose aggregate revenue exceeds US$50M in any consecutive 12-month period require a separate Qwen license (internal use that does not expose the model, outputs, or capabilities to third parties is excepted). Contact [email protected] for licensing questions.
Qwen3.8-2.4T-A95B resources
Official sources for Qwen3.8-2.4T-A95B: official playground, official launch post, source repository.
FAQ
Common questions about Qwen3.8-2.4T-A95B.