Context
256K
Input
$1.20/M
Output
$6.00/M
Aliases:qwen3maxalibaba-qwen3-max
Alibaba's flagship Qwen3 Max model with a 256K-token context window. Non-thinking instruct model tuned for agent programming and tool invocation, supporting structured output and web search.
deepinfra/qwen3-maxQuantUnspecified
- Input
- $1.20/M
- Output
- $6.00/M
- Context
- 256K
- Max out
- 33K
- Cache read
- $0.24/M
- Cache write
- $1.20/M
- Thinking out
- $6.00/M