Context
256K
Input
$1.65/M
Output
$4.95/M
Aliases:qwen3-8-maxqwen3.8maxqwen3-8max
Alibaba's 2.4-trillion-parameter MoE flagship with a 1M-token context window. Deep-thinking model tuned for coding, professional work, and long-horizon agentic execution, with native visual understanding of documents and video.
deepinfra/qwen3.8-maxQuantUnspecified
- Input
- $1.65/M
- Output
- $4.95/M
- Context
- 256K
- Max out
- 33K
- Cache read
- $0.21/M
- Cache write
- $1.65/M
- Thinking out
- $4.95/M