GPT-4o: providers compared
Every endpoint serving this model, side by side. ◆ marks the best value in each column — per model, never fleet-wide.
Current state
- Azure100%◆ (best)Healthy24h 99.77%
- 7d
- 99.87%
- 30d
- 99.88%◆ (best)
- p50
- 1.04s
- p99
- 4.86s
- Throughput
- 56 tps
- Context
- 128K
- $/Mtok
- $2.50 / $10.00◆ (best)
azure - OpenAI100%◆ (best)Healthy24h 99.97%
- 7d
- 99.87%◆ (best)
- 30d
- 99.84%
- p50
- 566ms◆ (best)
- p99
- 2.63s◆ (best)
- Throughput
- 80 tps◆ (best)
- Context
- 128K
- $/Mtok
- $2.50 / $10.00◆ (best)
openai
Measured 2m ago. Latency and throughput are OpenRouter's rolling 30-minute windows. ◆ marks the best value in each column among these endpoints.
Price vs latency
One dot per endpoint at the latest round · further left = faster, lower = cheaper · hover a dot for its tag
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.