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% | 99.21% | 390ms | 3.30s | 111 tps | 262K | $0.200 / $1.15 |
Novitanovita/fp8fp8 | Healthy | 100% | 96.66% | 2.25s | 9.75s | 64 tps | 262K | $0.200 / $1.15 |
StepFunstepfun/fp8fp8 | Healthy | 99.47% | 93.97% | 4.92s | 18.2s | 45 tps | 256K | $0.200 / $1.15 |
- DeepInfra100%Healthy24h 99.21%
- p50
- 390ms
- p99
- 3.30s
- Throughput
- 111 tps
- Context
- 262K
- $/Mtok
- $0.200 / $1.15
deepinfra - Novita100%Healthy24h 96.66%
- p50
- 2.25s
- p99
- 9.75s
- Throughput
- 64 tps
- Context
- 262K
- $/Mtok
- $0.200 / $1.15
novita/fp8fp8 - StepFun99.47%Healthy24h 93.97%
- p50
- 4.92s
- p99
- 18.2s
- Throughput
- 45 tps
- Context
- 256K
- $/Mtok
- $0.200 / $1.15
stepfun/fp8fp8
Measured 2m 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.