Inkling: 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 | 100%◆ (best) | 99.17% | 98.82% | 98.82% | 935ms | 4.44s | 29 tps | 524K | $0.950 / $4.05◆ (best) | |
Togethertogether | Healthy | 100%◆ (best) | 98.62% | 99.14% | 99.14% | 339ms◆ (best) | 10.5s | 72 tps | 524K | $1.00 / $4.05 |
| No data | — | 99.96% | 99.99%◆ (best) | 99.99%◆ (best) | 409ms | 823ms◆ (best) | 155 tps◆ (best) | 1.0M | $1.00 / $4.05 |
- DeepInfra100%◆ (best)Healthy24h 99.17%
- 7d
- 98.82%
- 30d
- 98.82%
- p50
- 935ms
- p99
- 4.44s
- Throughput
- 29 tps
- Context
- 524K
- $/Mtok
- $0.950 / $4.05◆ (best)
deepinfra/fp8fp8 - Together100%◆ (best)Healthy24h 98.62%
- 7d
- 99.14%
- 30d
- 99.14%
- p50
- 339ms◆ (best)
- p99
- 10.5s
- Throughput
- 72 tps
- Context
- 524K
- $/Mtok
- $1.00 / $4.05
together - No data24h 99.96%
- 7d
- 99.99%◆ (best)
- 30d
- 99.99%◆ (best)
- p50
- 409ms
- p99
- 823ms◆ (best)
- Throughput
- 155 tps◆ (best)
- Context
- 1.0M
- $/Mtok
- $1.00 / $4.05
baseten/fp8fp8
Measured 4m 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, averaged over the hour.
Throughput
Median tokens per second.