GPT-5 Mini
openai/gpt-5-mini
Compare with GPT-5 Nano, GPT-5, GPT Audio
CompareGPT-5 Mini
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
Azureazure | Healthy | 100% | 100% | 2.09s | 17.8s | 47 tps | 400K | $0.250 / $2.00 |
OpenAIopenai | Healthy | 99.94% | 99.97% | 3.70s | 18.2s | 89 tps | 400K | $0.250 / $2.00 |
OpenAIopenai/flex | Healthy | 99.94% | 99.97% | 5.59s | 53.4s | 99 tps | 400K | $0.125 / $1.00 |
Azureazure/swedencentral | No data | — | 100% | 3.44s | 5.11s | 86 tps | 400K | $0.275 / $2.20 |
- Azure100%Healthy24h 100%
- p50
- 2.09s
- p99
- 17.8s
- Throughput
- 47 tps
- Context
- 400K
- $/Mtok
- $0.250 / $2.00
azure - OpenAI99.94%Healthy24h 99.97%
- p50
- 3.70s
- p99
- 18.2s
- Throughput
- 89 tps
- Context
- 400K
- $/Mtok
- $0.250 / $2.00
openai - OpenAI99.94%Healthy24h 99.97%
- p50
- 5.59s
- p99
- 53.4s
- Throughput
- 99 tps
- Context
- 400K
- $/Mtok
- $0.125 / $1.00
openai/flex - Azure—No data24h 100%
- p50
- 3.44s
- p99
- 5.11s
- Throughput
- 86 tps
- Context
- 400K
- $/Mtok
- $0.275 / $2.20
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, averaged over the hour.
Throughput
Median tokens per second.