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% | 1.13s | 13.8s | 113 tps | 1.1M | $0.220 / $1.32 |
Azureazure | Degraded | 100% | 94.71% | 3.25s | 22.5s | 32 tps | 1.1M | $0.200 / $1.20 |
Azureazure/eu | Healthy | 100% | 99.74% | 3.17s | 23.2s | 39 tps | 1.1M | $0.220 / $1.32 |
Azureazure/us | Degraded | 100% | 89.60% | 3.51s | 26.0s | 34 tps | 1.1M | $0.220 / $1.32 |
OpenAIopenai | Healthy | 99.92% | 99.85% | 2.19s | 18.2s | 59 tps | 1.1M | $0.200 / $1.20 |
OpenAIopenai/flex | Healthy | 99.92% | 99.85% | 1.32s | 24.4s | 39 tps | 1.1M | $0.100 / $0.600 |
OpenAIopenai/priority | Healthy | 99.92% | 99.85% | 1.39s | 10.6s | 33 tps | 1.1M | $0.400 / $2.40 |
- Amazon Bedrock100%Healthy24h 100%
- p50
- 1.13s
- p99
- 13.8s
- Throughput
- 113 tps
- Context
- 1.1M
- $/Mtok
- $0.220 / $1.32
amazon-bedrock/us-east-1 - Azure100%Degraded24h 94.71%
- p50
- 3.25s
- p99
- 22.5s
- Throughput
- 32 tps
- Context
- 1.1M
- $/Mtok
- $0.200 / $1.20
azure - Azure100%Healthy24h 99.74%
- p50
- 3.17s
- p99
- 23.2s
- Throughput
- 39 tps
- Context
- 1.1M
- $/Mtok
- $0.220 / $1.32
azure/eu - Azure100%Degraded24h 89.60%
- p50
- 3.51s
- p99
- 26.0s
- Throughput
- 34 tps
- Context
- 1.1M
- $/Mtok
- $0.220 / $1.32
azure/us - OpenAI99.92%Healthy24h 99.85%
- p50
- 2.19s
- p99
- 18.2s
- Throughput
- 59 tps
- Context
- 1.1M
- $/Mtok
- $0.200 / $1.20
openai - OpenAI99.92%Healthy24h 99.85%
- p50
- 1.32s
- p99
- 24.4s
- Throughput
- 39 tps
- Context
- 1.1M
- $/Mtok
- $0.100 / $0.600
openai/flex - OpenAI99.92%Healthy24h 99.85%
- p50
- 1.39s
- p99
- 10.6s
- Throughput
- 33 tps
- Context
- 1.1M
- $/Mtok
- $0.400 / $2.40
openai/priority
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 and p99 are OpenRouter's rolling 30-minute windows, averaged over the hour.
Throughput
Median tokens per second.