GPT-5 Nano: 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) | 100% | 99.97% | 99.98% | 1.95s | 8.36s | 115 tps | 400K | $0.050 / $0.400 |
Azureazure/swedencentral | Healthy | 100%◆ (best) | 100% | 100%◆ (best) | 100%◆ (best) | 2.80s | 6.05s | 112 tps | 400K | $0.055 / $0.440 |
OpenAIopenai | Healthy | 100%◆ (best) | 99.99% | 99.91% | 98.91% | 2.15s | 14.0s | 117 tps | 400K | $0.050 / $0.400 |
OpenAIopenai/flex | Healthy | 100%◆ (best) | 100% | 100% | 100% | 1.03s◆ (best) | 3.50s◆ (best) | 135 tps◆ (best) | 400K | $0.025 / $0.200◆ (best) |
- Azure100%◆ (best)Healthy24h 100%
- 7d
- 99.97%
- 30d
- 99.98%
- p50
- 1.95s
- p99
- 8.36s
- Throughput
- 115 tps
- Context
- 400K
- $/Mtok
- $0.050 / $0.400
azure - Azure100%◆ (best)Healthy24h 100%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- 2.80s
- p99
- 6.05s
- Throughput
- 112 tps
- Context
- 400K
- $/Mtok
- $0.055 / $0.440
azure/swedencentral - OpenAI100%◆ (best)Healthy24h 99.99%
- 7d
- 99.91%
- 30d
- 98.91%
- p50
- 2.15s
- p99
- 14.0s
- Throughput
- 117 tps
- Context
- 400K
- $/Mtok
- $0.050 / $0.400
openai - OpenAI100%◆ (best)Healthy24h 100%
- 7d
- 100%
- 30d
- 100%
- p50
- 1.03s◆ (best)
- p99
- 3.50s◆ (best)
- Throughput
- 135 tps◆ (best)
- Context
- 400K
- $/Mtok
- $0.025 / $0.200◆ (best)
openai/flex
Measured 2m 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.