GPT-6 Luna Pro
openai/gpt-6-luna-proInputOutput
Compare its 6 providersIncident RSSCompare with GPT-6 Sol Pro, GPT-6 Astra Pro, GPT-5.6 Luna Pro
CompareGPT-6 Luna Pro
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
OpenAIopenai | Healthy | 100% | 99.96% | 99.90% | 99.90% | 11.1s | 164s | 118 tps | 1.1M | $0.100 / $0.500 |
OpenAIopenai/flex | Healthy | 100% | 100% | 100% | 100% | 7.28s | 58.5s | 136 tps | 1.1M | $0.050 / $0.250 |
Azureazure | No data | — | 98.16% | 95.21% | 95.21% | 8.09s | 146s | 60 tps | 1.1M | $0.100 / $0.500 |
Azureazure/eu | No data | — | — | — | — | 1.70s | 5.16s | 110 tps | 1.1M | $0.110 / $0.550 |
Azureazure/us | No data | — | — | — | — | 410ms | 530ms | 57 tps | 1.1M | $0.110 / $0.550 |
OpenAIopenai/fast | No data | — | 100% | 100% | 100% | 3.84s | 7.46s | 242 tps | 1.1M | $0.200 / $1.00 |
- OpenAI100%Healthy24h 99.96%
- 7d
- 99.90%
- 30d
- 99.90%
- p50
- 11.1s
- p99
- 164s
- Throughput
- 118 tps
- Context
- 1.1M
- $/Mtok
- $0.100 / $0.500
openai - OpenAI100%Healthy24h 100%
- 7d
- 100%
- 30d
- 100%
- p50
- 7.28s
- p99
- 58.5s
- Throughput
- 136 tps
- Context
- 1.1M
- $/Mtok
- $0.050 / $0.250
openai/flex - No data24h 98.16%
- 7d
- 95.21%
- 30d
- 95.21%
- p50
- 8.09s
- p99
- 146s
- Throughput
- 60 tps
- Context
- 1.1M
- $/Mtok
- $0.100 / $0.500
azure - No data24h —
- 7d
- —
- 30d
- —
- p50
- 1.70s
- p99
- 5.16s
- Throughput
- 110 tps
- Context
- 1.1M
- $/Mtok
- $0.110 / $0.550
azure/eu - No data24h —
- 7d
- —
- 30d
- —
- p50
- 410ms
- p99
- 530ms
- Throughput
- 57 tps
- Context
- 1.1M
- $/Mtok
- $0.110 / $0.550
azure/us - No data24h 100%
- 7d
- 100%
- 30d
- 100%
- p50
- 3.84s
- p99
- 7.46s
- Throughput
- 242 tps
- Context
- 1.1M
- $/Mtok
- $0.200 / $1.00
openai/fast
Measured 1m 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.
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 · 1 day with data, none below the red threshold.