GPT-5: providers compared
Every endpoint serving this model, side by side. ◆ marks the best value in each column — per model, never fleet-wide.
Current state
- OpenAI100%Healthy24h 99.25%
- 7d
- 99.30%
- 30d
- 99.30%
- p50
- 2.88s◆ (best)
- p99
- 23.4s
- Throughput
- 84 tps◆ (best)
- Context
- 400K
- $/Mtok
- $1.25 / $10.00◆ (best)
openai/default - No data24h 100%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- 3.65s
- p99
- 14.0s◆ (best)
- Throughput
- 63 tps
- Context
- 400K
- $/Mtok
- $1.25 / $10.00◆ (best)
azure - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 400K
- $/Mtok
- $1.38 / $11.00
azure/swedencentral
Measured 4m 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, averaged over the hour.
Throughput
Median tokens per second.