GPT-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%◆ (best) | 99.96% | 99.91% | 99.91% | 12.9s | 164s | 102 tps | 1.1M | $0.100 / $0.500 |
OpenAIopenai/fast | Healthy | 100%◆ (best) | 100% | 100%◆ (best) | 100%◆ (best) | 6.63s | 42.4s | 186 tps◆ (best) | 1.1M | $0.200 / $1.00 |
OpenAIopenai/flex | Healthy | 100%◆ (best) | 100% | 100%◆ (best) | 100%◆ (best) | 8.04s | 50.4s | 147 tps | 1.1M | $0.050 / $0.250◆ (best) |
Azureazure | No data | — | 98.61% | 98.24% | 98.24% | 5.09s◆ (best) | 73.5s | 42 tps | 1.1M | $0.100 / $0.500 |
Azureazure/eu | No data | — | 100% | — | — | 7.63s | 37.9s◆ (best) | 124 tps | 1.1M | $0.110 / $0.550 |
Azureazure/us | No data | — | — | — | — | — | — | — | 1.1M | $0.110 / $0.550 |
- OpenAI100%◆ (best)Healthy24h 99.96%
- 7d
- 99.91%
- 30d
- 99.91%
- p50
- 12.9s
- p99
- 164s
- Throughput
- 102 tps
- Context
- 1.1M
- $/Mtok
- $0.100 / $0.500
openai - OpenAI100%◆ (best)Healthy24h 100%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- 6.63s
- p99
- 42.4s
- Throughput
- 186 tps◆ (best)
- Context
- 1.1M
- $/Mtok
- $0.200 / $1.00
openai/fast - OpenAI100%◆ (best)Healthy24h 100%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- 8.04s
- p99
- 50.4s
- Throughput
- 147 tps
- Context
- 1.1M
- $/Mtok
- $0.050 / $0.250◆ (best)
openai/flex - No data24h 98.61%
- 7d
- 98.24%
- 30d
- 98.24%
- p50
- 5.09s◆ (best)
- p99
- 73.5s
- Throughput
- 42 tps
- Context
- 1.1M
- $/Mtok
- $0.100 / $0.500
azure - No data24h 100%
- 7d
- —
- 30d
- —
- p50
- 7.63s
- p99
- 37.9s◆ (best)
- Throughput
- 124 tps
- Context
- 1.1M
- $/Mtok
- $0.110 / $0.550
azure/eu - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.1M
- $/Mtok
- $0.110 / $0.550
azure/us
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.
Throughput
Median tokens per second.