GPT-5.4 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/us | Healthy | 100%◆ (best) | 99.92% | 99.93%◆ (best) | 99.93%◆ (best) | 1.94s | 9.66s | 26 tps | 400K | $0.220 / $1.38 |
Azureazure | Healthy | 99.95% | 99.90% | 99.69% | 99.69% | 2.35s | 10.1s | 21 tps | 400K | $0.200 / $1.25 |
OpenAIopenai | Down | 89.84% | 87.89% | 87.18% | 87.18% | 862ms◆ (best) | 6.10s◆ (best) | 75 tps◆ (best) | 400K | $0.200 / $1.25 |
OpenAIopenai/flex | Down | 89.84% | 87.89% | 87.18% | 87.18% | — | — | — | 400K | $0.100 / $0.625◆ (best) |
- Azure100%◆ (best)Healthy24h 99.92%
- 7d
- 99.93%◆ (best)
- 30d
- 99.93%◆ (best)
- p50
- 1.94s
- p99
- 9.66s
- Throughput
- 26 tps
- Context
- 400K
- $/Mtok
- $0.220 / $1.38
azure/us - Azure99.95%Healthy24h 99.90%
- 7d
- 99.69%
- 30d
- 99.69%
- p50
- 2.35s
- p99
- 10.1s
- Throughput
- 21 tps
- Context
- 400K
- $/Mtok
- $0.200 / $1.25
azure - OpenAI89.84%Down24h 87.89%
- 7d
- 87.18%
- 30d
- 87.18%
- p50
- 862ms◆ (best)
- p99
- 6.10s◆ (best)
- Throughput
- 75 tps◆ (best)
- Context
- 400K
- $/Mtok
- $0.200 / $1.25
openai - OpenAI89.84%Down24h 87.89%
- 7d
- 87.18%
- 30d
- 87.18%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 400K
- $/Mtok
- $0.100 / $0.625◆ (best)
openai/flex
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.