modelstatus.dev

GPT-5.4 Nano

openai/gpt-5.4-nanoInputOutput

Compare its 4 providers Incident RSSCompare with GPT-5 Nano, GPT-5.4 Nano (batch), GPT-5.4

CompareGPT-5.4 Nano

	State
Azureazure	No data	—	—	99.99%	99.98%	—	—	—	400K	$0.200 / $1.25
Azureazure/us	No data	—	—	100%	99.85%	—	—	—	400K	$0.220 / $1.38
OpenAIopenai	No data	—	—	99.94%	99.37%	—	—	—	400K	$0.200 / $1.25
OpenAIopenai/flex	No data	—	—	99.73%	99.77%	—	—	—	400K	$0.100 / $0.625

Azure—
No data24h —
7d
99.99%
30d
99.98%
p50
—
p99
—
Throughput
—
Context
400K
$/Mtok
$0.200 / $1.25
azure
Azure—
No data24h —
7d
100%
30d
99.85%
p50
—
p99
—
Throughput
—
Context
400K
$/Mtok
$0.220 / $1.38
azure/us
OpenAI—
No data24h —
7d
99.94%
30d
99.37%
p50
—
p99
—
Throughput
—
Context
400K
$/Mtok
$0.200 / $1.25
openai
OpenAI—
No data24h —
7d
99.73%
30d
99.77%
p50
—
p99
—
Throughput
—
Context
400K
$/Mtok
$0.100 / $0.625
openai/flex

No recent measurement.

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.

Jul

Aug

Sep

Oct

worst hour ≥ 95%90–95%< 90%no data

Colour by each endpoint's worst hour of each UTC day · 4 endpoints · 48 days with data, 30 endpoint-days below 90%.