GPT-4.1 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) | 99.97% | 99.96% | 99.96% | 923ms | 3.47s | 88 tps | 1.0M | $0.400 / $1.60◆ (best) |
OpenAIopenai | Healthy | 99.98% | 99.98% | 99.82% | 99.76% | 807ms◆ (best) | 3.25s | 84 tps | 1.0M | $0.400 / $1.60◆ (best) |
Azureazure/swedencentral | No data | — | 100% | 99.99%◆ (best) | 99.99%◆ (best) | 1.01s | 1.57s◆ (best) | 100 tps◆ (best) | 1.0M | $0.440 / $1.76 |
- Azure100%◆ (best)Healthy24h 99.97%
- 7d
- 99.96%
- 30d
- 99.96%
- p50
- 923ms
- p99
- 3.47s
- Throughput
- 88 tps
- Context
- 1.0M
- $/Mtok
- $0.400 / $1.60◆ (best)
azure - OpenAI99.98%Healthy24h 99.98%
- 7d
- 99.82%
- 30d
- 99.76%
- p50
- 807ms◆ (best)
- p99
- 3.25s
- Throughput
- 84 tps
- Context
- 1.0M
- $/Mtok
- $0.400 / $1.60◆ (best)
openai - No data24h 100%
- 7d
- 99.99%◆ (best)
- 30d
- 99.99%◆ (best)
- p50
- 1.01s
- p99
- 1.57s◆ (best)
- Throughput
- 100 tps◆ (best)
- Context
- 1.0M
- $/Mtok
- $0.440 / $1.76
azure/swedencentral
Measured 5m 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.