modelstatus.dev

GPT-4.1: 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	Healthy	100%	99.99%	99.86%	99.73%	888ms◆ (best)	3.06s	87 tps	1.0M	$2.00 / $8.00◆ (best)
Azureazure	No data	—	99.98%	99.96%	99.96%	1.58s	4.36s	57 tps	1.0M	$2.00 / $8.00◆ (best)
Azureazure/swedencentral	No data	—	100%	100%◆ (best)	100%◆ (best)	949ms	2.94s◆ (best)	134 tps◆ (best)	1.0M	$2.20 / $8.80

OpenAI100%
Healthy24h 99.99%
7d
99.86%
30d
99.73%
p50
888ms◆ (best)
p99
3.06s
Throughput
87 tps
Context
1.0M
$/Mtok
$2.00 / $8.00◆ (best)
openai
Azure—
No data24h 99.98%
7d
99.96%
30d
99.96%
p50
1.58s
p99
4.36s
Throughput
57 tps
Context
1.0M
$/Mtok
$2.00 / $8.00◆ (best)
azure
Azure—
No data24h 100%
7d
100%◆ (best)
30d
100%◆ (best)
p50
949ms
p99
2.94s◆ (best)
Throughput
134 tps◆ (best)
Context
1.0M
$/Mtok
$2.20 / $8.80
azure/swedencentral

Measured 3m 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, averaged over the hour.

Throughput

Median tokens per second.