Inference provider
Thinking Machines
2 models served. Speed, latency and price below are medians across this provider's catalogue, not per-endpoint measurements.
Models served
2
Median output speed
64 t/s
Median latency
1.83s
Median price / 1M
Free
Catalogue
Strongest and fastest on this provider
What the catalogue looks like at the top end, on the two axes that usually decide the choice.
Highest Intelligence Index
Among models this provider serves
- Inkling Small (free)Thinking Machines25.7
- Inkling (free)Thinking Machines25.0
View as table
| Model | Intelligence |
|---|---|
| Inkling Small (free) (Thinking Machines) | 25.7 |
| Inkling (free) (Thinking Machines) | 25.0 |
Fastest output
Median tokens per second
- Inkling Small (free)Thinking Machines93 t/s
- Inkling (free)Thinking Machines34 t/s
View as table
| Model | Tokens/s |
|---|---|
| Inkling Small (free) (Thinking Machines) | 93 |
| Inkling (free) (Thinking Machines) | 34 |
Full catalogue
All 2 models on Thinking Machines
Filter by creator
2 of 2 models| Inkling Small (free) Thinking Machinesopen | 25.7 | Free |
| Inkling (free) Thinking Machinesopen | 25.0 | Free |