Step 3.7 Flash
stepfun/step-3.7-flashInputOutput
Compare its 4 providersIncident RSSCompare with Step 3.5 Flash, GLM 5.3, GLM 5.3 Flash
CompareStep 3.7 Flash
- Novita100%Healthy24h 99.85%
- 7d
- 99.72%
- 30d
- 99.20%
- p50
- 4.60s
- p99
- 13.8s
- Throughput
- 48 tps
- Context
- 262K
- $/Mtok
- $0.200 / $1.15
novita/fp8fp8 - No data24h —
- 7d
- —
- 30d
- 99.92%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 262K
- $/Mtok
- $0.160 / $0.920
deepinfra - No data24h —
- 7d
- 99.95%
- 30d
- 99.95%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 262K
- $/Mtok
- $0.160 / $0.920
deepinfra/us - No data24h 99.76%
- 7d
- 99.59%
- 30d
- 99.19%
- p50
- 4.39s
- p99
- 18.5s
- Throughput
- 73 tps
- Context
- 256K
- $/Mtok
- $0.200 / $1.15
stepfun/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 is OpenRouter's rolling 30-minute window, averaged over the hour.
Throughput
Median tokens per second.
Daily availability
One row per endpoint · one dot per day · last 90 days.
worst hour ≥ 95%90–95%< 90%no data
Colour by each endpoint's worst hour of each UTC day · 4 endpoints · 46 days with data, 7 endpoint-days below 90%.
Price changes
- Step 3.7 FlashDeepInfradeepinfra$0.200 → $0.160 / $1.15 → $0.920cache read $0.040 → $0.0322026-09-02 03:20 UTC