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% | 99.16% | 172ms | 2.41s | 88 tps | 262K | $0.200 / $1.15 |
StepFunstepfun/fp8fp8 | Healthy | 99.17% | 93.73% | 5.18s | 20.1s | 42 tps | 256K | $0.200 / $1.15 |
Novitanovita/fp8fp8 | Degraded | 94.44% | 96.57% | 2.21s | 8.95s | 7.0 tps | 262K | $0.200 / $1.15 |
- DeepInfra100%Healthy24h 99.16%
- p50
- 172ms
- p99
- 2.41s
- Throughput
- 88 tps
- Context
- 262K
- $/Mtok
- $0.200 / $1.15
deepinfra - StepFun99.17%Healthy24h 93.73%
- p50
- 5.18s
- p99
- 20.1s
- Throughput
- 42 tps
- Context
- 256K
- $/Mtok
- $0.200 / $1.15
stepfun/fp8fp8 - Novita94.44%Degraded24h 96.57%
- p50
- 2.21s
- p99
- 8.95s
- Throughput
- 7.0 tps
- Context
- 262K
- $/Mtok
- $0.200 / $1.15
novita/fp8fp8
Measured 4m 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.
Throughput
Median tokens per second.