Inkling
thinkingmachines/inkling
Compare with Inkling Small, Inkling (batch), GLM 5.2
CompareInkling
- BaseTen100%Healthy24h 99.98%
- p50
- 379ms
- p99
- 1.34s
- Throughput
- 152 tps
- Context
- 1.0M
- $/Mtok
- $1.00 / $4.05
baseten/fp8fp8 - Together100%Healthy24h 99.45%
- p50
- 361ms
- p99
- 3.57s
- Throughput
- 105 tps
- Context
- 524K
- $/Mtok
- $1.00 / $4.05
together - DeepInfra98.75%Healthy24h 99.69%
- p50
- 749ms
- p99
- 13.0s
- Throughput
- 45 tps
- Context
- 524K
- $/Mtok
- $0.950 / $4.05
deepinfra/fp8fp8
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, averaged over the hour.
Throughput
Median tokens per second.