GPT-5.4 Nano
openai/gpt-5.4-nano
Compare with gpt-oss-120b, gpt-oss-20b, GPT-5.4
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
Azureazure | Healthy | 100% | 99.52% | 2.02s | 19.1s | 26 tps | 400K | $0.200 / $1.25 |
OpenAIopenai | Down | 88.19% | 88.56% | 802ms | 6.43s | 61 tps | 400K | $0.200 / $1.25 |
OpenAIopenai/flex | Down | 88.19% | 88.56% | 1.66s | 7.19s | 35 tps | 400K | $0.100 / $0.625 |
Azureazure/us | No data | — | 99.64% | 1.09s | 9.37s | 44 tps | 400K | $0.220 / $1.38 |
- Azure100%Healthy24h 99.52%
- p50
- 2.02s
- p99
- 19.1s
- Throughput
- 26 tps
- Context
- 400K
- $/Mtok
- $0.200 / $1.25
azure - OpenAI88.19%Down24h 88.56%
- p50
- 802ms
- p99
- 6.43s
- Throughput
- 61 tps
- Context
- 400K
- $/Mtok
- $0.200 / $1.25
openai - OpenAI88.19%Down24h 88.56%
- p50
- 1.66s
- p99
- 7.19s
- Throughput
- 35 tps
- Context
- 400K
- $/Mtok
- $0.100 / $0.625
openai/flex - Azure—No data24h 99.64%
- p50
- 1.09s
- p99
- 9.37s
- Throughput
- 44 tps
- Context
- 400K
- $/Mtok
- $0.220 / $1.38
azure/us
Measured 2m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
History
1 endpoint reporting no data is omitted from the charts.
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 and p99 are OpenRouter's rolling 30-minute windows.
Throughput
Median tokens per second.