GPT-6 Luna: 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 | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Amazon Bedrockamazon-bedrock/global | Healthy | 100%◆ (best) | 100% | 99.51% | 99.51% | 1.12s | 3.88s◆ (best) | 150 tps◆ (best) | 1.1M | $0.100 / $0.500 |
Amazon Bedrockamazon-bedrock/us-east-1 | Healthy | 100%◆ (best) | 100% | 100%◆ (best) | 99.97% | 941ms | 6.30s | 119 tps | 1.1M | $0.110 / $0.550 |
Azureazure | Healthy | 100%◆ (best) | 100% | 100%◆ (best) | 99.36% | 2.67s | 29.4s | 85 tps | 1.1M | $0.100 / $0.500 |
Azureazure/eu | Healthy | 100%◆ (best) | 100% | 100%◆ (best) | 100%◆ (best) | 1.28s | 14.1s | 79 tps | 1.1M | $0.110 / $0.550 |
Azureazure/us | Healthy | 100%◆ (best) | 100% | 100%◆ (best) | 99.50% | 1.70s | 10.4s | 117 tps | 1.1M | $0.110 / $0.550 |
OpenAIopenai | Healthy | 100%◆ (best) | 100% | 100%◆ (best) | 100%◆ (best) | 2.29s | 33.7s | 74 tps | 1.1M | $0.100 / $0.500 |
OpenAIopenai/fast | Healthy | 100%◆ (best) | 100% | 100%◆ (best) | 100%◆ (best) | 777ms◆ (best) | 5.48s | 125 tps | 1.1M | $0.200 / $1.00 |
OpenAIopenai/flex | Healthy | 100%◆ (best) | 100% | 80.35% | 89.35% | 5.46s | 32.1s | 38 tps | 1.1M | $0.050 / $0.250◆ (best) |
- Amazon Bedrock100%◆ (best)Healthy24h 100%
- 7d
- 99.51%
- 30d
- 99.51%
- p50
- 1.12s
- p99
- 3.88s◆ (best)
- Throughput
- 150 tps◆ (best)
- Context
- 1.1M
- $/Mtok
- $0.100 / $0.500
amazon-bedrock/global - Amazon Bedrock100%◆ (best)Healthy24h 100%
- 7d
- 100%◆ (best)
- 30d
- 99.97%
- p50
- 941ms
- p99
- 6.30s
- Throughput
- 119 tps
- Context
- 1.1M
- $/Mtok
- $0.110 / $0.550
amazon-bedrock/us-east-1 - Azure100%◆ (best)Healthy24h 100%
- 7d
- 100%◆ (best)
- 30d
- 99.36%
- p50
- 2.67s
- p99
- 29.4s
- Throughput
- 85 tps
- Context
- 1.1M
- $/Mtok
- $0.100 / $0.500
azure - Azure100%◆ (best)Healthy24h 100%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- 1.28s
- p99
- 14.1s
- Throughput
- 79 tps
- Context
- 1.1M
- $/Mtok
- $0.110 / $0.550
azure/eu - Azure100%◆ (best)Healthy24h 100%
- 7d
- 100%◆ (best)
- 30d
- 99.50%
- p50
- 1.70s
- p99
- 10.4s
- Throughput
- 117 tps
- Context
- 1.1M
- $/Mtok
- $0.110 / $0.550
azure/us - OpenAI100%◆ (best)Healthy24h 100%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- 2.29s
- p99
- 33.7s
- Throughput
- 74 tps
- Context
- 1.1M
- $/Mtok
- $0.100 / $0.500
openai - OpenAI100%◆ (best)Healthy24h 100%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- 777ms◆ (best)
- p99
- 5.48s
- Throughput
- 125 tps
- Context
- 1.1M
- $/Mtok
- $0.200 / $1.00
openai/fast - OpenAI100%◆ (best)Healthy24h 100%
- 7d
- 80.35%
- 30d
- 89.35%
- p50
- 5.46s
- p99
- 32.1s
- Throughput
- 38 tps
- Context
- 1.1M
- $/Mtok
- $0.050 / $0.250◆ (best)
openai/flex
Measured 3m 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.