Context
256K
Input
$1.20/M
Output
$6.00/M
Aliases:qwen3maxthinkingalibaba-qwen3-max-thinking
Alibaba's flagship Qwen3 Max with a 256K-token context window, tuned for extended reasoning on hard math, coding and agentic tasks. Text-only, with tool invocation and JSON object output.
deepinfra/qwen3-max-thinkingQuantUnspecified
- 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