modelstatus.dev

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

	State
DeepInfradeepinfra	Healthy	100%	99.78%	99.44%	99.44%	303ms	4.24s	112 tps	262K	$0.200 / $1.15
StepFunstepfun/fp8fp8	Healthy	99.58%	99.05%	98.78%	98.78%	5.13s	20.7s	43 tps	256K	$0.200 / $1.15
Novitanovita/fp8fp8	Healthy	97.80%	97.74%	97.70%	97.70%	2.75s	12.7s	32 tps	262K	$0.200 / $1.15

DeepInfra100%
Healthy24h 99.78%
7d
99.44%
30d
99.44%
p50
303ms
p99
4.24s
Throughput
112 tps
Context
262K
$/Mtok
$0.200 / $1.15
deepinfra
StepFun99.58%
Healthy24h 99.05%
7d
98.78%
30d
98.78%
p50
5.13s
p99
20.7s
Throughput
43 tps
Context
256K
$/Mtok
$0.200 / $1.15
stepfun/fp8fp8
Novita97.80%
Healthy24h 97.74%
7d
97.70%
30d
97.70%
p50
2.75s
p99
12.7s
Throughput
32 tps
Context
262K
$/Mtok
$0.200 / $1.15
novita/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 is OpenRouter's rolling 30-minute window.

Throughput

Median tokens per second.