GPT-5.6 Luna Pro: 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% | 99.94% | 99.94% | 99.96% | 7.87s | 67.7s | 114 tps | 1.1M | $0.200 / $1.20 |
Azureazure | No data | — | 99.87% | 99.89% | 95.51% | 11.5s | 47.5s | 128 tps◆ (best) | 1.1M | $0.200 / $1.20 |
Azureazure/eu | No data | — | 100% | 100%◆ (best) | 99.76% | 5.11s | 6.83s◆ (best) | 112 tps | 1.1M | $0.220 / $1.32 |
OpenAIopenai/fast | No data | — | 99.79% | 99.16% | 99.96% | 3.84s◆ (best) | 16.1s | 125 tps | 1.1M | $0.400 / $2.40 |
OpenAIopenai/flex | No data | — | 100% | 100% | 99.99%◆ (best) | 3.91s | 16.5s | 123 tps | 1.1M | $0.100 / $0.600◆ (best) |
OpenAIopenai/priority | No data | — | — | — | — | — | — | — | 1.1M | $0.400 / $2.40 |
- OpenAI100%Healthy24h 99.94%
- 7d
- 99.94%
- 30d
- 99.96%
- p50
- 7.87s
- p99
- 67.7s
- Throughput
- 114 tps
- Context
- 1.1M
- $/Mtok
- $0.200 / $1.20
openai - No data24h 99.87%
- 7d
- 99.89%
- 30d
- 95.51%
- p50
- 11.5s
- p99
- 47.5s
- Throughput
- 128 tps◆ (best)
- Context
- 1.1M
- $/Mtok
- $0.200 / $1.20
azure - No data24h 100%
- 7d
- 100%◆ (best)
- 30d
- 99.76%
- p50
- 5.11s
- p99
- 6.83s◆ (best)
- Throughput
- 112 tps
- Context
- 1.1M
- $/Mtok
- $0.220 / $1.32
azure/eu - No data24h 99.79%
- 7d
- 99.16%
- 30d
- 99.96%
- p50
- 3.84s◆ (best)
- p99
- 16.1s
- Throughput
- 125 tps
- Context
- 1.1M
- $/Mtok
- $0.400 / $2.40
openai/fast - No data24h 100%
- 7d
- 100%
- 30d
- 99.99%◆ (best)
- p50
- 3.91s
- p99
- 16.5s
- Throughput
- 123 tps
- Context
- 1.1M
- $/Mtok
- $0.100 / $0.600◆ (best)
openai/flex - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.1M
- $/Mtok
- $0.400 / $2.40
openai/priority
Measured 5m 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.