modelstatus.dev

GPT-5: 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
OpenAIopenai/default	Healthy	100%	99.99%	99.91%	99.92%	5.55s◆ (best)	21.8s◆ (best)	70 tps	400K	$1.25 / $10.00◆ (best)
Azureazure	No data	—	99.94%	99.93%	99.92%	6.15s	32.7s	91 tps◆ (best)	400K	$1.25 / $10.00◆ (best)
Azureazure/swedencentral	No data	—	100%	100%◆ (best)	100%◆ (best)	—	—	—	400K	$1.38 / $11.00

OpenAI100%
Healthy24h 99.99%
7d
99.91%
30d
99.92%
p50
5.55s◆ (best)
p99
21.8s◆ (best)
Throughput
70 tps
Context
400K
$/Mtok
$1.25 / $10.00◆ (best)
openai/default
Azure—
No data24h 99.94%
7d
99.93%
30d
99.92%
p50
6.15s
p99
32.7s
Throughput
91 tps◆ (best)
Context
400K
$/Mtok
$1.25 / $10.00◆ (best)
azure
Azure—
No data24h 100%
7d
100%◆ (best)
30d
100%◆ (best)
p50
—
p99
—
Throughput
—
Context
400K
$/Mtok
$1.38 / $11.00
azure/swedencentral

Measured 1m ago. Latency and throughput are OpenRouter's rolling 30-minute windows. ◆ marks the best value in each column among these endpoints.

Price vs latency

One dot per endpoint at the latest round · further left = faster, lower = cheaper · hover a dot for its tag

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.