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 | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Azureazure | Healthy | 100%◆ (best) | 99.57% | 99.54% | 99.54% | 14.7s | 112s | 88 tps | 1.1M | $0.200 / $1.20 |
Azureazure/eu | Healthy | 100%◆ (best) | 100% | 100%◆ (best) | 100%◆ (best) | 7.63s | 25.8s◆ (best) | 96 tps | 1.1M | $0.220 / $1.32 |
OpenAIopenai | Healthy | 99.87% | 99.98% | 99.79% | 99.79% | 7.75s | 105s | 120 tps | 1.1M | $0.200 / $1.20 |
OpenAIopenai/flex | Healthy | 99.87% | 99.98% | 99.79% | 99.79% | 25.1s | 44.0s | 192 tps◆ (best) | 1.1M | $0.100 / $0.600◆ (best) |
OpenAIopenai/priority | Healthy | 99.87% | 99.98% | 99.79% | 99.79% | 6.13s◆ (best) | 207s | 188 tps | 1.1M | $0.400 / $2.40 |
- Azure100%◆ (best)Healthy24h 99.57%
- 7d
- 99.54%
- 30d
- 99.54%
- p50
- 14.7s
- p99
- 112s
- Throughput
- 88 tps
- Context
- 1.1M
- $/Mtok
- $0.200 / $1.20
azure - Azure100%◆ (best)Healthy24h 100%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- 7.63s
- p99
- 25.8s◆ (best)
- Throughput
- 96 tps
- Context
- 1.1M
- $/Mtok
- $0.220 / $1.32
azure/eu - OpenAI99.87%Healthy24h 99.98%
- 7d
- 99.79%
- 30d
- 99.79%
- p50
- 7.75s
- p99
- 105s
- Throughput
- 120 tps
- Context
- 1.1M
- $/Mtok
- $0.200 / $1.20
openai - OpenAI99.87%Healthy24h 99.98%
- 7d
- 99.79%
- 30d
- 99.79%
- p50
- 25.1s
- p99
- 44.0s
- Throughput
- 192 tps◆ (best)
- Context
- 1.1M
- $/Mtok
- $0.100 / $0.600◆ (best)
openai/flex - OpenAI99.87%Healthy24h 99.98%
- 7d
- 99.79%
- 30d
- 99.79%
- p50
- 6.13s◆ (best)
- p99
- 207s
- Throughput
- 188 tps
- Context
- 1.1M
- $/Mtok
- $0.400 / $2.40
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.