Alibaba · Qwen
Qwen3.8 2.4T A95B
alibaba/qwen3.8-2.4t-a95b
Qwen's first open Max-class text model, a sparse 2.4T-parameter MoE with 95B active parameters for generation, coding and agent work.
Open weightsReasoningTool callingStructured outputTemperature
Model specifications
- Context window
- 262K tokens
- Output limit
- 131K tokens
- Release date
- 2026-08-12
- Input modalities
- text
- Output modalities
- text
- Last updated
- 2026-08-12
Provider pricing
USD per 1M tokens. Limits may differ from the underlying model.
Checked 2026-08-17
Self-hosted
Qwen/Qwen3.8-2.4T-A95B
- Input
- -
- Output
- -
- Context
- 262K
Promotions, plan quotas, cache pricing and regional taxes are not included. Recheck the provider before purchase.