Context
1.0M
Input
$2.00/M
Output
$6.00/M
Open-weight sparse mixture-of-experts text model with 2.4T total and 95B active parameters, best at coding, research, complex reasoning and agentic workflows.
novita/qwen3.8-2.4t-a95bQuantUnspecified
- Input
- $2.00/M
- Output
- $6.00/M
- Context
- 1.0M
- Max out
- 131K
- Cache read
- $0.25/M
- Cache write
- $2.00/M
- Thinking out
- $6.00/M