modelstatus.dev

GPT-5

openai/gpt-5InputOutput

Compare its 3 providers Incident RSSCompare with GPT-5 Mini, GPT-5 Nano, GPT Audio

CompareGPT-5

	State
Azureazure	Healthy	100%	99.96%	99.93%	99.93%	17.1s	50.5s	116 tps	400K	$1.25 / $10.00
OpenAIopenai/default	Healthy	100%	99.99%	99.91%	99.92%	4.76s	76.9s	61 tps	400K	$1.25 / $10.00
Azureazure/swedencentral	No data	—	100%	100%	100%	—	—	—	400K	$1.38 / $11.00

Azure100%
Healthy24h 99.96%
7d
99.93%
30d
99.93%
p50
17.1s
p99
50.5s
Throughput
116 tps
Context
400K
$/Mtok
$1.25 / $10.00
azure
OpenAI100%
Healthy24h 99.99%
7d
99.91%
30d
99.92%
p50
4.76s
p99
76.9s
Throughput
61 tps
Context
400K
$/Mtok
$1.25 / $10.00
openai/default
Azure—
No data24h 100%
7d
100%
30d
100%
p50
—
p99
—
Throughput
—
Context
400K
$/Mtok
$1.38 / $11.00
azure/swedencentral

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.

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 · 3 endpoints · 48 days with data, 2 endpoint-days below 90%.