GPT-5.6 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/us-east-1 | Healthy | 100%◆ (best) | 100% | 100%◆ (best) | 100%◆ (best) | 1.29s | 7.50s◆ (best) | 90 tps◆ (best) | 1.1M | $0.220 / $1.32 |
Azureazure/eu | Healthy | 100%◆ (best) | 100% | 99.92% | 99.92% | 1.33s | 11.6s | 46 tps | 1.1M | $0.220 / $1.32 |
Azureazure | Healthy | 99.79% | 94.19% | 95.55% | 95.55% | 3.53s | 20.9s | 51 tps | 1.1M | $0.200 / $1.20 |
OpenAIopenai | Healthy | 99.58% | 99.64% | 99.70% | 99.70% | 2.44s | 15.2s | 62 tps | 1.1M | $0.200 / $1.20 |
OpenAIopenai/flex | Healthy | 99.58% | 99.64% | 99.70% | 99.70% | 5.80s | 76.2s | 34 tps | 1.1M | $0.100 / $0.600◆ (best) |
OpenAIopenai/priority | Healthy | 99.58% | 99.64% | 99.70% | 99.70% | 1.25s◆ (best) | 8.05s | 33 tps | 1.1M | $0.400 / $2.40 |
Azureazure/us | Healthy | 96.43% | 89.66% | 95.03% | 95.03% | 4.44s | 30.9s | 46 tps | 1.1M | $0.220 / $1.32 |
- Amazon Bedrock100%◆ (best)Healthy24h 100%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- 1.29s
- p99
- 7.50s◆ (best)
- Throughput
- 90 tps◆ (best)
- Context
- 1.1M
- $/Mtok
- $0.220 / $1.32
amazon-bedrock/us-east-1 - Azure100%◆ (best)Healthy24h 100%
- 7d
- 99.92%
- 30d
- 99.92%
- p50
- 1.33s
- p99
- 11.6s
- Throughput
- 46 tps
- Context
- 1.1M
- $/Mtok
- $0.220 / $1.32
azure/eu - Azure99.79%Healthy24h 94.19%
- 7d
- 95.55%
- 30d
- 95.55%
- p50
- 3.53s
- p99
- 20.9s
- Throughput
- 51 tps
- Context
- 1.1M
- $/Mtok
- $0.200 / $1.20
azure - OpenAI99.58%Healthy24h 99.64%
- 7d
- 99.70%
- 30d
- 99.70%
- p50
- 2.44s
- p99
- 15.2s
- Throughput
- 62 tps
- Context
- 1.1M
- $/Mtok
- $0.200 / $1.20
openai - OpenAI99.58%Healthy24h 99.64%
- 7d
- 99.70%
- 30d
- 99.70%
- p50
- 5.80s
- p99
- 76.2s
- Throughput
- 34 tps
- Context
- 1.1M
- $/Mtok
- $0.100 / $0.600◆ (best)
openai/flex - OpenAI99.58%Healthy24h 99.64%
- 7d
- 99.70%
- 30d
- 99.70%
- p50
- 1.25s◆ (best)
- p99
- 8.05s
- Throughput
- 33 tps
- Context
- 1.1M
- $/Mtok
- $0.400 / $2.40
openai/priority - Azure96.43%Healthy24h 89.66%
- 7d
- 95.03%
- 30d
- 95.03%
- p50
- 4.44s
- p99
- 30.9s
- Throughput
- 46 tps
- Context
- 1.1M
- $/Mtok
- $0.220 / $1.32
azure/us
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.
Throughput
Median tokens per second.