GPT-5.6 Luna Pro
openai/gpt-5.6-luna-proInputOutput
Compare its 6 providersIncident RSSCompare with GPT-5.6 Sol Pro, GPT-5.6 Terra Pro, GPT-5.5 Pro
CompareGPT-5.6 Luna Pro
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Azureazure | Healthy | 100% | 99.87% | 99.89% | 95.51% | 11.0s | 41.7s | 158 tps | 1.1M | $0.200 / $1.20 |
OpenAIopenai | Healthy | 100% | 99.94% | 99.94% | 99.96% | 7.61s | 67.6s | 109 tps | 1.1M | $0.200 / $1.20 |
Azureazure/eu | No data | — | 100% | 100% | 99.76% | 7.21s | 15.7s | 172 tps | 1.1M | $0.220 / $1.32 |
OpenAIopenai/fast | No data | — | 99.79% | 99.16% | 99.96% | 5.87s | 18.4s | 220 tps | 1.1M | $0.400 / $2.40 |
OpenAIopenai/flex | No data | — | 100% | 100% | 99.99% | 27.0s | 114s | 148 tps | 1.1M | $0.100 / $0.600 |
OpenAIopenai/priority | No data | — | — | — | — | — | — | — | 1.1M | $0.400 / $2.40 |
- Azure100%Healthy24h 99.87%
- 7d
- 99.89%
- 30d
- 95.51%
- p50
- 11.0s
- p99
- 41.7s
- Throughput
- 158 tps
- Context
- 1.1M
- $/Mtok
- $0.200 / $1.20
azure - OpenAI100%Healthy24h 99.94%
- 7d
- 99.94%
- 30d
- 99.96%
- p50
- 7.61s
- p99
- 67.6s
- Throughput
- 109 tps
- Context
- 1.1M
- $/Mtok
- $0.200 / $1.20
openai - No data24h 100%
- 7d
- 100%
- 30d
- 99.76%
- p50
- 7.21s
- p99
- 15.7s
- Throughput
- 172 tps
- Context
- 1.1M
- $/Mtok
- $0.220 / $1.32
azure/eu - No data24h 99.79%
- 7d
- 99.16%
- 30d
- 99.96%
- p50
- 5.87s
- p99
- 18.4s
- Throughput
- 220 tps
- Context
- 1.1M
- $/Mtok
- $0.400 / $2.40
openai/fast - No data24h 100%
- 7d
- 100%
- 30d
- 99.99%
- p50
- 27.0s
- p99
- 114s
- Throughput
- 148 tps
- Context
- 1.1M
- $/Mtok
- $0.100 / $0.600
openai/flex - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.1M
- $/Mtok
- $0.400 / $2.40
openai/priority
Measured 2m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
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.
Daily availability
One row per endpoint · one dot per day · last 90 days.
worst hour ≥ 95%90–95%< 90%no data
Colour by each endpoint's worst hour of each UTC day · 6 endpoints · 49 days with data, 28 endpoint-days below 90%.
Price changes
- GPT-5.6 Luna ProOpenAIopenai/priority$0.400 / $2.402026-08-21 23:40 UTC