GPT-5
openai/gpt-5
Compare with GPT-5 Mini, GPT-5 Nano, GPT Audio
Compare its 3 providers · Incident RSS
Showing only the openai/default provider · show all 3
CompareGPT-5
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
OpenAIopenai/default | Healthy | 97.35% | 99.19% | 99.30% | 99.30% | 3.24s | 39.5s | 73 tps | 400K | $1.25 / $10.00 |
- OpenAI97.35%Healthy24h 99.19%
- 7d
- 99.30%
- 30d
- 99.30%
- p50
- 3.24s
- p99
- 39.5s
- Throughput
- 73 tps
- Context
- 400K
- $/Mtok
- $1.25 / $10.00
openai/default
Measured 5m 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.
Throughput
Median tokens per second.
Daily availability
One row per endpoint · one cell per week · up to a year.
worst hour ≥ 95%90–95%< 90%no data
Colour by each endpoint's worst hour of each UTC week · 3 endpoints · 24 weeks with data, none below the red threshold.