modelstatus.dev

GPT-4o-mini

openai/gpt-4o-miniInputOutput

Compare its 3 providers Incident RSSCompare with GPT-4, GPT-4o, GPT-4o (2024-05-13)

CompareGPT-4o-mini

	State
OpenAIopenai	Healthy	99.99%	99.98%	99.89%	99.93%	515ms	1.99s	69 tps	128K	$0.150 / $0.600
Azureazure	Healthy	99.98%	99.96%	99.95%	99.73%	1.43s	3.17s	54 tps	128K	$0.150 / $0.600
Azureazure/swedencentral	No data	—	100%	99.96%	99.98%	719ms	1.45s	116 tps	128K	$0.165 / $0.660

OpenAI99.99%
Healthy24h 99.98%
7d
99.89%
30d
99.93%
p50
515ms
p99
1.99s
Throughput
69 tps
Context
128K
$/Mtok
$0.150 / $0.600
openai
Azure99.98%
Healthy24h 99.96%
7d
99.95%
30d
99.73%
p50
1.43s
p99
3.17s
Throughput
54 tps
Context
128K
$/Mtok
$0.150 / $0.600
azure
Azure—
No data24h 100%
7d
99.96%
30d
99.98%
p50
719ms
p99
1.45s
Throughput
116 tps
Context
128K
$/Mtok
$0.165 / $0.660
azure/swedencentral

Measured 1m 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 · 46 days with data, 2 endpoint-days below 90%.