Step 3.7 Flash: 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 | 99.50%◆ (best) | 99.84% | 99.82% | 99.44% | 3.23s | 11.1s◆ (best) | 61 tps | 262K | $0.200 / $1.15 | |
| Healthy | 98.87% | 99.56% | 99.67% | 99.42% | 2.22s◆ (best) | 12.8s | 132 tps◆ (best) | 256K | $0.200 / $1.15 | |
DeepInfradeepinfra | No data | — | — | — | 99.93% | — | — | — | 262K | $0.160 / $0.920◆ (best) |
DeepInfradeepinfra/us | No data | — | — | 100%◆ (best) | 99.95%◆ (best) | — | — | — | 262K | $0.160 / $0.920◆ (best) |
- Novita99.50%◆ (best)Healthy24h 99.84%
- 7d
- 99.82%
- 30d
- 99.44%
- p50
- 3.23s
- p99
- 11.1s◆ (best)
- Throughput
- 61 tps
- Context
- 262K
- $/Mtok
- $0.200 / $1.15
novita/fp8fp8 - StepFun98.87%Healthy24h 99.56%
- 7d
- 99.67%
- 30d
- 99.42%
- p50
- 2.22s◆ (best)
- p99
- 12.8s
- Throughput
- 132 tps◆ (best)
- Context
- 256K
- $/Mtok
- $0.200 / $1.15
stepfun/fp8fp8 - No data24h —
- 7d
- —
- 30d
- 99.93%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 262K
- $/Mtok
- $0.160 / $0.920◆ (best)
deepinfra - No data24h —
- 7d
- 100%◆ (best)
- 30d
- 99.95%◆ (best)
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 262K
- $/Mtok
- $0.160 / $0.920◆ (best)
deepinfra/us
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, averaged over the hour.
Throughput
Median tokens per second.