GPT-5 Mini
openai/gpt-5-miniInputOutput
Compare its 4 providersIncident RSSCompare with GPT-5 Nano, GPT-5, GPT Audio
Showing only the azure provider · show all 4
CompareGPT-5 Mini
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Azureazure | Healthy | 100% | 99.94% | 99.98% | 99.98% | 3.90s | 23.5s | 88 tps | 400K | $0.250 / $2.00 |
- Azure100%Healthy24h 99.94%
- 7d
- 99.98%
- 30d
- 99.98%
- p50
- 3.90s
- p99
- 23.5s
- Throughput
- 88 tps
- Context
- 400K
- $/Mtok
- $0.250 / $2.00
azure
Measured 1m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
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.
Daily availability
One row per endpoint · one dot per day · last 90 days.
worst hour ≥ 95%90–95%< 90%no data
Colour by each endpoint's worst hour of each UTC day · 4 endpoints · 47 days with data, 1 endpoint-day below 90%. Tables and charts above are filtered to azure.