modelstatus.dev

GPT-5 Nano

openai/gpt-5-nanoInputOutput

Compare its 4 providers Incident RSSCompare with GPT-5.4 Nano, GPT-5 Nano (batch), GPT-4.1 Nano

CompareGPT-5 Nano

	State
Azureazure	Healthy	100%	100%	99.97%	99.98%	1.55s	6.61s	81 tps	400K	$0.050 / $0.400
OpenAIopenai/flex	Healthy	100%	100%	100%	100%	1.07s	4.02s	128 tps	400K	$0.025 / $0.200
OpenAIopenai	Healthy	99.96%	99.98%	99.91%	99.01%	2.56s	14.3s	105 tps	400K	$0.050 / $0.400
Azureazure/swedencentral	No data	—	100%	100%	100%	—	—	—	400K	$0.055 / $0.440

Azure100%
Healthy24h 100%
7d
99.97%
30d
99.98%
p50
1.55s
p99
6.61s
Throughput
81 tps
Context
400K
$/Mtok
$0.050 / $0.400
azure
OpenAI100%
Healthy24h 100%
7d
100%
30d
100%
p50
1.07s
p99
4.02s
Throughput
128 tps
Context
400K
$/Mtok
$0.025 / $0.200
openai/flex
OpenAI99.96%
Healthy24h 99.98%
7d
99.91%
30d
99.01%
p50
2.56s
p99
14.3s
Throughput
105 tps
Context
400K
$/Mtok
$0.050 / $0.400
openai
Azure—
No data24h 100%
7d
100%
30d
100%
p50
—
p99
—
Throughput
—
Context
400K
$/Mtok
$0.055 / $0.440
azure/swedencentral

Measured 3m 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.

Jul

Aug

Sep

Oct

azure/swedencentral

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, 1 endpoint-day below 90%.