Inkling Small
thinkingmachines/inkling-small
Compare with Inkling, Inkling (batch), GLM 5.2
Showing only the deepinfra/fp8 provider · show all 3
CompareInkling Small
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 100% | 98.04% | 98.39% | 98.39% | 396ms | 1.38s | 104 tps | 524K | $0.450 / $1.20 |
- DeepInfra100%Healthy24h 98.04%
- 7d
- 98.39%
- 30d
- 98.39%
- p50
- 396ms
- p99
- 1.38s
- Throughput
- 104 tps
- Context
- 524K
- $/Mtok
- $0.450 / $1.20
deepinfra/fp8fp8
Measured 1m 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, averaged over the hour.
Throughput
Median tokens per second.