Inkling
thinkingmachines/inkling
Compare with Inkling Small, Inkling (batch), GLM 5.2
CompareInkling
- BaseTen100%Healthy24h 99.94%
- 7d
- 99.99%
- 30d
- 99.99%
- p50
- 349ms
- p99
- 2.80s
- Throughput
- 95 tps
- Context
- 1.0M
- $/Mtok
- $1.00 / $4.05
baseten/fp8fp8 - DeepInfra100%Healthy24h 99.50%
- 7d
- 98.81%
- 30d
- 98.81%
- p50
- 2.94s
- p99
- 32.7s
- Throughput
- 11 tps
- Context
- 524K
- $/Mtok
- $0.950 / $4.05
deepinfra/fp8fp8 - Together98.11%Healthy24h 98.61%
- 7d
- 99.28%
- 30d
- 99.28%
- p50
- 1.32s
- p99
- 9.78s
- Throughput
- 33 tps
- Context
- 524K
- $/Mtok
- $1.00 / $4.05
together
Measured 2m 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.