GPT-5 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 | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Azureazure | Healthy | 100%◆ (best) | 99.94% | 99.98% | 99.98% | 3.91s | 23.1s | 88 tps | 400K | $0.250 / $2.00 |
OpenAIopenai | Healthy | 100%◆ (best) | 99.99% | 99.92% | 99.92% | 3.68s | 17.8s | 98 tps | 400K | $0.250 / $2.00 |
OpenAIopenai/flex | Healthy | 100%◆ (best) | 100% | 99.97% | 99.97% | 1.08s◆ (best) | 8.78s | 116 tps | 400K | $0.125 / $1.00◆ (best) |
Azureazure/swedencentral | No data | — | 100% | 100%◆ (best) | 100%◆ (best) | 5.61s | 8.78s◆ (best) | 132 tps◆ (best) | 400K | $0.275 / $2.20 |
- Azure100%◆ (best)Healthy24h 99.94%
- 7d
- 99.98%
- 30d
- 99.98%
- p50
- 3.91s
- p99
- 23.1s
- Throughput
- 88 tps
- Context
- 400K
- $/Mtok
- $0.250 / $2.00
azure - OpenAI100%◆ (best)Healthy24h 99.99%
- 7d
- 99.92%
- 30d
- 99.92%
- p50
- 3.68s
- p99
- 17.8s
- Throughput
- 98 tps
- Context
- 400K
- $/Mtok
- $0.250 / $2.00
openai - OpenAI100%◆ (best)Healthy24h 100%
- 7d
- 99.97%
- 30d
- 99.97%
- p50
- 1.08s◆ (best)
- p99
- 8.78s
- Throughput
- 116 tps
- Context
- 400K
- $/Mtok
- $0.125 / $1.00◆ (best)
openai/flex - No data24h 100%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- 5.61s
- p99
- 8.78s◆ (best)
- Throughput
- 132 tps◆ (best)
- Context
- 400K
- $/Mtok
- $0.275 / $2.20
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.