Step 3.7 Flash
stepfun/step-3.7-flash
Compare with Step 3.5 Flash, GLM 5.2, DeepSeek V4 Flash 0731
CompareStep 3.7 Flash
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
DeepInfradeepinfra | Healthy | 100% | 99.19% | 223ms | 2.21s | 92 tps | 262K | $0.200 / $1.15 |
StepFunstepfun/fp8fp8 | Healthy | 98.71% | 93.88% | 4.93s | 19.3s | 45 tps | 256K | $0.200 / $1.15 |
Novitanovita/fp8fp8 | Healthy | 98.31% | 96.61% | 2.18s | 8.17s | 8.0 tps | 262K | $0.200 / $1.15 |
- DeepInfra100%Healthy24h 99.19%
- p50
- 223ms
- p99
- 2.21s
- Throughput
- 92 tps
- Context
- 262K
- $/Mtok
- $0.200 / $1.15
deepinfra - StepFun98.71%Healthy24h 93.88%
- p50
- 4.93s
- p99
- 19.3s
- Throughput
- 45 tps
- Context
- 256K
- $/Mtok
- $0.200 / $1.15
stepfun/fp8fp8 - Novita98.31%Healthy24h 96.61%
- p50
- 2.18s
- p99
- 8.17s
- Throughput
- 8.0 tps
- Context
- 262K
- $/Mtok
- $0.200 / $1.15
novita/fp8fp8
Measured 1m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
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 and p99 are OpenRouter's rolling 30-minute windows, averaged over the hour.
Throughput
Median tokens per second.