GPT-5.1: providers compared
Every endpoint serving this model, side by side. ◆ marks the best value in each column — per model, never fleet-wide.
Current state
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
OpenAIopenai | Healthy | 100% | 99.99% | 99.90% | 99.94% | 1.28s | 9.04s | 50 tps | 400K | $1.25 / $10.00 |
Azureazure | No data | — | 99.99% | 99.98% | 99.98% | 948ms | 7.12s | 61 tps | 400K | $1.25 / $10.00 |
Azureazure/swedencentral | No data | — | — | 100%◆ (best) | 100%◆ (best) | — | — | — | 400K | $1.38 / $11.00 |
OpenAIopenai/default | No data | — | — | — | — | — | — | — | 400K | $1.25 / $10.00 |
OpenAIopenai/default/flex | No data | — | — | — | — | — | — | — | 400K | $0.625 / $5.00◆ (best) |
OpenAIopenai/default/priority | No data | — | — | — | — | — | — | — | 400K | $2.50 / $20.00 |
OpenAIopenai/fast | No data | — | — | — | — | — | — | — | 400K | $2.50 / $20.00 |
OpenAIopenai/flex | No data | — | 100% | 99.99% | 99.99% | 749ms◆ (best) | 1.88s◆ (best) | 150 tps◆ (best) | 400K | $0.625 / $5.00◆ (best) |
OpenAIopenai/priority | No data | — | — | — | — | — | — | — | 400K | $2.50 / $20.00 |
- OpenAI100%Healthy24h 99.99%
- 7d
- 99.90%
- 30d
- 99.94%
- p50
- 1.28s
- p99
- 9.04s
- Throughput
- 50 tps
- Context
- 400K
- $/Mtok
- $1.25 / $10.00
openai - No data24h 99.99%
- 7d
- 99.98%
- 30d
- 99.98%
- p50
- 948ms
- p99
- 7.12s
- Throughput
- 61 tps
- Context
- 400K
- $/Mtok
- $1.25 / $10.00
azure - No data24h —
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 400K
- $/Mtok
- $1.38 / $11.00
azure/swedencentral - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 400K
- $/Mtok
- $1.25 / $10.00
openai/default - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 400K
- $/Mtok
- $0.625 / $5.00◆ (best)
openai/default/flex - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 400K
- $/Mtok
- $2.50 / $20.00
openai/default/priority - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 400K
- $/Mtok
- $2.50 / $20.00
openai/fast - No data24h 100%
- 7d
- 99.99%
- 30d
- 99.99%
- p50
- 749ms◆ (best)
- p99
- 1.88s◆ (best)
- Throughput
- 150 tps◆ (best)
- Context
- 400K
- $/Mtok
- $0.625 / $5.00◆ (best)
openai/flex - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 400K
- $/Mtok
- $2.50 / $20.00
openai/priority
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.