GPT-4
openai/gpt-4InputOutput
Compare its 2 providersIncident RSSCompare with GPT-4o-mini, GPT-4o, GPT-4o (2024-05-13)
Showing only the azure provider · show all 2
CompareGPT-4
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Azureazure | Healthy | 100% | 99.96% | 99.99% | 99.97% | 948ms | 1.86s | 51 tps | 8K | $30.00 / $60.00 |
- Azure100%Healthy24h 99.96%
- 7d
- 99.99%
- 30d
- 99.97%
- p50
- 948ms
- p99
- 1.86s
- Throughput
- 51 tps
- Context
- 8K
- $/Mtok
- $30.00 / $60.00
azure
Measured 4m 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 dot per day · last 90 days.