Inkling Small (free)
thinkingmachines/inkling-small:freeInputOutput
Compare its 2 providersIncident RSSCompare with Inkling, Inkling Small, Inkling (free)
Showing only the thinkingmachines/nvfp4 provider · show all 2
CompareInkling Small (free)
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 99.74% | 99.97% | 99.97% | 99.61% | 1.30s | 7.27s | 96 tps | 1.0M | free / free |
- Thinking Machines99.74%Healthy24h 99.97%
- 7d
- 99.97%
- 30d
- 99.61%
- p50
- 1.30s
- p99
- 7.27s
- Throughput
- 96 tps
- Context
- 1.0M
- $/Mtok
- free / free
thinkingmachines/nvfp4nvfp4
Measured 4m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
History
Availability
Axis starts at 90% so small differences stay visible; it expands to 0 when an endpoint falls below.
Time to first token
Logarithmic axis — the fleet spans two orders of magnitude. P50 is OpenRouter's rolling 30-minute window.
Throughput
Median tokens per second.
Daily availability
One row per endpoint · one dot per day · last 90 days.
worst hour ≥ 95%90–95%< 90%no data
Colour by each endpoint's worst hour of each UTC day · 1 endpoint · 46 days with data, 3 endpoint-days below 90%. Tables and charts above are filtered to thinkingmachines/nvfp4.