modelstatus.dev

← Step 3.7 Flash

Step 3.7 Flash: providers compared

Every endpoint serving this model, side by side. ◆ marks the best value in each column — per model, never fleet-wide.

Current state

	State
DeepInfradeepinfra	No data	—	—	—	99.93%	—	—	—	262K	$0.160 / $0.920◆ (best)
DeepInfradeepinfra/us	No data	—	—	99.99%◆ (best)	99.95%◆ (best)	—	—	—	262K	$0.160 / $0.920◆ (best)
Novitanovita/fp8fp8	No data	—	—	99.82%	99.38%	—	—	—	262K	$0.200 / $1.15
StepFunstepfun/fp8fp8	No data	—	—	99.74%	99.38%	—	—	—	256K	$0.200 / $1.15

DeepInfra—
No data24h —
7d
—
30d
99.93%
p50
—
p99
—
Throughput
—
Context
262K
$/Mtok
$0.160 / $0.920◆ (best)
deepinfra
DeepInfra—
No data24h —
7d
99.99%◆ (best)
30d
99.95%◆ (best)
p50
—
p99
—
Throughput
—
Context
262K
$/Mtok
$0.160 / $0.920◆ (best)
deepinfra/us
Novita—
No data24h —
7d
99.82%
30d
99.38%
p50
—
p99
—
Throughput
—
Context
262K
$/Mtok
$0.200 / $1.15
novita/fp8fp8
StepFun—
No data24h —
7d
99.74%
30d
99.38%
p50
—
p99
—
Throughput
—
Context
256K
$/Mtok
$0.200 / $1.15
stepfun/fp8fp8

No recent measurement. ◆ marks the best value in each column among these endpoints.

Price vs latency

No endpoint currently reports both a price and a latency.

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.