GPT-5.6 Luna
openai/gpt-5.6-luna
Compare with GPT-5.6 Sol, GPT-5.6 Terra, GPT-5.6 Luna Pro
CompareGPT-5.6 Luna
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
Amazon Bedrockamazon-bedrock/us-east-1 | Healthy | 100% | 100% | 1.08s | 19.3s | 108 tps | 1.1M | $0.220 / $1.32 |
Azureazure/eu | Healthy | 100% | 99.75% | 2.98s | 20.3s | 45 tps | 1.1M | $0.220 / $1.32 |
Azureazure/us | Degraded | 100% | 89.17% | 3.97s | 24.3s | 44 tps | 1.1M | $0.220 / $1.32 |
Azureazure | Healthy | 99.94% | 94.41% | 3.49s | 20.0s | 41 tps | 1.1M | $0.200 / $1.20 |
OpenAIopenai | Healthy | 99.85% | 99.85% | 2.37s | 18.5s | 54 tps | 1.1M | $0.200 / $1.20 |
OpenAIopenai/flex | Healthy | 99.85% | 99.85% | 1.90s | 34.9s | 38 tps | 1.1M | $0.100 / $0.600 |
OpenAIopenai/priority | Healthy | 99.85% | 99.85% | 1.79s | 9.49s | 88 tps | 1.1M | $0.400 / $2.40 |
- Amazon Bedrock100%Healthy24h 100%
- p50
- 1.08s
- p99
- 19.3s
- Throughput
- 108 tps
- Context
- 1.1M
- $/Mtok
- $0.220 / $1.32
amazon-bedrock/us-east-1 - Azure100%Healthy24h 99.75%
- p50
- 2.98s
- p99
- 20.3s
- Throughput
- 45 tps
- Context
- 1.1M
- $/Mtok
- $0.220 / $1.32
azure/eu - Azure100%Degraded24h 89.17%
- p50
- 3.97s
- p99
- 24.3s
- Throughput
- 44 tps
- Context
- 1.1M
- $/Mtok
- $0.220 / $1.32
azure/us - Azure99.94%Healthy24h 94.41%
- p50
- 3.49s
- p99
- 20.0s
- Throughput
- 41 tps
- Context
- 1.1M
- $/Mtok
- $0.200 / $1.20
azure - OpenAI99.85%Healthy24h 99.85%
- p50
- 2.37s
- p99
- 18.5s
- Throughput
- 54 tps
- Context
- 1.1M
- $/Mtok
- $0.200 / $1.20
openai - OpenAI99.85%Healthy24h 99.85%
- p50
- 1.90s
- p99
- 34.9s
- Throughput
- 38 tps
- Context
- 1.1M
- $/Mtok
- $0.100 / $0.600
openai/flex - OpenAI99.85%Healthy24h 99.85%
- p50
- 1.79s
- p99
- 9.49s
- Throughput
- 88 tps
- Context
- 1.1M
- $/Mtok
- $0.400 / $2.40
openai/priority
Measured 3m 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 and p99 are OpenRouter's rolling 30-minute windows, averaged over the hour.
Throughput
Median tokens per second.