Inkling Small
thinkingmachines/inkling-small
Compare with Inkling, Inkling (batch), GLM 5.2
CompareInkling Small
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
DeepInfradeepinfra/fp8fp8 | No data | — | 99.05% | 677ms | 1.91s | 128 tps | 524K | $0.450 / $1.20 |
Togethertogether | No data | — | 99.17% | 2.12s | 16.3s | 27 tps | 524K | $0.500 / $1.20 |
- DeepInfra—No data24h 99.05%
- p50
- 677ms
- p99
- 1.91s
- Throughput
- 128 tps
- Context
- 524K
- $/Mtok
- $0.450 / $1.20
deepinfra/fp8fp8 - Together—No data24h 99.17%
- p50
- 2.12s
- p99
- 16.3s
- Throughput
- 27 tps
- Context
- 524K
- $/Mtok
- $0.500 / $1.20
together
Measured 1m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
History
2 endpoints reporting no data are omitted from the charts.
No endpoints with data to chart.