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
- DeepInfra100%◆ (best)Healthy24h 99.85%
- 7d
- 99.58%
- 30d
- 90.17%
- p50
- 718ms
- p99
- 38.7s
- Throughput
- 73 tps◆ (best)
- Context
- 524K
- $/Mtok
- $0.950 / $4.05◆ (best)
deepinfra/fp8fp8 - Together100%◆ (best)Healthy24h 99.41%
- 7d
- 99.70%◆ (best)
- 30d
- 99.12%◆ (best)
- p50
- 664ms◆ (best)
- p99
- 5.72s◆ (best)
- Throughput
- 45 tps
- Context
- 524K
- $/Mtok
- $1.00 / $4.05
together - No data24h —
- 7d
- —
- 30d
- 96.29%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $1.00 / $4.05
baseten/fp8fp8
Measured 1m 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.
Throughput
Median tokens per second.