Inkling Small (free): providers compared
Every endpoint serving this model, side by side. ◆ marks the best value in each column — per model, never fleet-wide.
Current state
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 99.77% | 99.97% | 99.97% | 99.61% | 1.30s | 7.40s | 97 tps | 1.0M | free / free◆ (best) | |
| No data | — | — | — | — | — | — | — | 1.0M | free / free◆ (best) |
- Thinking Machines99.77%Healthy24h 99.97%
- 7d
- 99.97%
- 30d
- 99.61%
- p50
- 1.30s
- p99
- 7.40s
- Throughput
- 97 tps
- Context
- 1.0M
- $/Mtok
- free / free◆ (best)
thinkingmachines/nvfp4nvfp4 - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- free / free◆ (best)
baseten/fp8fp8
Measured 2m ago. Latency and throughput are OpenRouter's rolling 30-minute windows. ◆ marks the best value in each column among these endpoints.
Price vs latency
One dot per endpoint at the latest round · further left = faster, lower = cheaper · hover a dot for its tag
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.