GPT-4o (2024-05-13)
openai/gpt-4o-2024-05-13
Compare with GPT-4o-mini, GPT-4, GPT-4o
CompareGPT-4o (2024-05-13)
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
Azureazure | Healthy | 100% | 99.91% | 1.08s | 1.93s | 6.0 tps | 128K | $5.00 / $15.00 |
OpenAIopenai | Healthy | 100% | 99.96% | 341ms | 1.91s | 20 tps | 128K | $5.00 / $15.00 |
- Azure100%Healthy24h 99.91%
- p50
- 1.08s
- p99
- 1.93s
- Throughput
- 6.0 tps
- Context
- 128K
- $/Mtok
- $5.00 / $15.00
azure - OpenAI100%Healthy24h 99.96%
- p50
- 341ms
- p99
- 1.91s
- Throughput
- 20 tps
- Context
- 128K
- $/Mtok
- $5.00 / $15.00
openai
Measured 2m 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 and p99 are OpenRouter's rolling 30-minute windows, averaged over the hour.
Throughput
Median tokens per second.