GPT-5 Nano
openai/gpt-5-nano
Compare with GPT-5.4 Nano, GPT-5 Nano (batch), GPT-4.1 Nano
CompareGPT-5 Nano
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
Azureazure | Healthy | 100% | 100% | 3.28s | 32.3s | 70 tps | 400K | $0.050 / $0.400 |
OpenAIopenai | Healthy | 98.22% | 97.86% | 2.73s | 15.3s | 109 tps | 400K | $0.050 / $0.400 |
OpenAIopenai/flex | Healthy | 98.22% | 97.86% | 962ms | 4.31s | 76 tps | 400K | $0.025 / $0.200 |
Azureazure/swedencentral | No data | — | 100% | — | — | — | 400K | $0.055 / $0.440 |
- Azure100%Healthy24h 100%
- p50
- 3.28s
- p99
- 32.3s
- Throughput
- 70 tps
- Context
- 400K
- $/Mtok
- $0.050 / $0.400
azure - OpenAI98.22%Healthy24h 97.86%
- p50
- 2.73s
- p99
- 15.3s
- Throughput
- 109 tps
- Context
- 400K
- $/Mtok
- $0.050 / $0.400
openai - OpenAI98.22%Healthy24h 97.86%
- p50
- 962ms
- p99
- 4.31s
- Throughput
- 76 tps
- Context
- 400K
- $/Mtok
- $0.025 / $0.200
openai/flex - Azure—No data24h 100%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 400K
- $/Mtok
- $0.055 / $0.440
azure/swedencentral
Measured 1m 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.