Context
1.0M
Input
$1.20/M
Output
$5.00/M
Aliases:inkling-nvfp4tm-inklingthinking-machines-inkling
Thinking Machines Lab's sparse mixture-of-experts flagship: 975B total parameters with 41B active per token across 66 layers, and a 1M-token context window. Built for reasoning, coding, tool use, and multimodal work.
modal/inklingQuantUnspecified
- Input
- $1.20/M
- Output
- $5.00/M
- Context
- 1.0M
- Max out
- 262K
- Cache read
- $0.27/M
- Cache write
- $1.20/M
- Thinking out
- $5.00/M