GPT-4o-mini: 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 | 99.99%◆ (best) | 99.98% | 99.89% | 99.93% | 536ms◆ (best) | 2.26s | 67 tps | 128K | $0.150 / $0.600◆ (best) |
Azureazure | Healthy | 99.82% | 99.96% | 99.95% | 99.73% | 1.44s | 3.46s | 54 tps | 128K | $0.150 / $0.600◆ (best) |
Azureazure/swedencentral | No data | — | 100% | 99.96%◆ (best) | 99.98%◆ (best) | 740ms | 1.19s◆ (best) | 118 tps◆ (best) | 128K | $0.165 / $0.660 |
- OpenAI99.99%◆ (best)Healthy24h 99.98%
- 7d
- 99.89%
- 30d
- 99.93%
- p50
- 536ms◆ (best)
- p99
- 2.26s
- Throughput
- 67 tps
- Context
- 128K
- $/Mtok
- $0.150 / $0.600◆ (best)
openai - Azure99.82%Healthy24h 99.96%
- 7d
- 99.95%
- 30d
- 99.73%
- p50
- 1.44s
- p99
- 3.46s
- Throughput
- 54 tps
- Context
- 128K
- $/Mtok
- $0.150 / $0.600◆ (best)
azure - No data24h 100%
- 7d
- 99.96%◆ (best)
- 30d
- 99.98%◆ (best)
- p50
- 740ms
- p99
- 1.19s◆ (best)
- Throughput
- 118 tps◆ (best)
- Context
- 128K
- $/Mtok
- $0.165 / $0.660
azure/swedencentral
Measured 4m 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.