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 | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
DeepInfradeepinfra | Healthy | 100%◆ (best) | 99.82% | 99.50%◆ (best) | 99.50%◆ (best) | 401ms◆ (best) | 3.85s◆ (best) | 105 tps◆ (best) | 262K | $0.200 / $1.15◆ (best) |
| Healthy | 98.95% | 99.39% | 98.87% | 98.87% | 4.81s | 17.8s | 47 tps | 256K | $0.200 / $1.15◆ (best) | |
| Healthy | 98.16% | 98.04% | 97.73% | 97.73% | 1.98s | 7.66s | 94 tps | 262K | $0.200 / $1.15◆ (best) |
- DeepInfra100%◆ (best)Healthy24h 99.82%
- 7d
- 99.50%◆ (best)
- 30d
- 99.50%◆ (best)
- p50
- 401ms◆ (best)
- p99
- 3.85s◆ (best)
- Throughput
- 105 tps◆ (best)
- Context
- 262K
- $/Mtok
- $0.200 / $1.15◆ (best)
deepinfra - StepFun98.95%Healthy24h 99.39%
- 7d
- 98.87%
- 30d
- 98.87%
- p50
- 4.81s
- p99
- 17.8s
- Throughput
- 47 tps
- Context
- 256K
- $/Mtok
- $0.200 / $1.15◆ (best)
stepfun/fp8fp8 - Novita98.16%Healthy24h 98.04%
- 7d
- 97.73%
- 30d
- 97.73%
- p50
- 1.98s
- p99
- 7.66s
- Throughput
- 94 tps
- Context
- 262K
- $/Mtok
- $0.200 / $1.15◆ (best)
novita/fp8fp8
Measured 3m 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.