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) | 99.93% | 99.93%◆ (best) | 99.93%◆ (best) | 1.63s | 10.4s | 30 tps | 400K | $0.220 / $1.38 |
Azureazure | Healthy | 98.02% | 99.91% | 99.69% | 99.69% | 2.44s | 9.53s | 20 tps | 400K | $0.200 / $1.25 |
OpenAIopenai | Degraded | 90.87% | 88.08% | 87.14% | 87.14% | 879ms◆ (best) | 6.15s | 68 tps◆ (best) | 400K | $0.200 / $1.25 |
OpenAIopenai/flex | Degraded | 90.87% | 88.08% | 87.14% | 87.14% | 2.07s | 2.65s◆ (best) | 15 tps | 400K | $0.100 / $0.625◆ (best) |
- Azure100%◆ (best)Healthy24h 99.93%
- 7d
- 99.93%◆ (best)
- 30d
- 99.93%◆ (best)
- p50
- 1.63s
- p99
- 10.4s
- Throughput
- 30 tps
- Context
- 400K
- $/Mtok
- $0.220 / $1.38
azure/us - Azure98.02%Healthy24h 99.91%
- 7d
- 99.69%
- 30d
- 99.69%
- p50
- 2.44s
- p99
- 9.53s
- Throughput
- 20 tps
- Context
- 400K
- $/Mtok
- $0.200 / $1.25
azure - OpenAI90.87%Degraded24h 88.08%
- 7d
- 87.14%
- 30d
- 87.14%
- p50
- 879ms◆ (best)
- p99
- 6.15s
- Throughput
- 68 tps◆ (best)
- Context
- 400K
- $/Mtok
- $0.200 / $1.25
openai - OpenAI90.87%Degraded24h 88.08%
- 7d
- 87.14%
- 30d
- 87.14%
- p50
- 2.07s
- p99
- 2.65s◆ (best)
- Throughput
- 15 tps
- Context
- 400K
- $/Mtok
- $0.100 / $0.625◆ (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.