GPT-5.6 Luna
openai/gpt-5.6-luna
Compare with gpt-oss-120b, gpt-oss-20b, GPT-5.4
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
Amazon Bedrockamazon-bedrock/us-east-1 | Healthy | 100% | 100% | 995ms | 13.0s | 108 tps | 1.1M | $0.220 / $1.32 |
Azureazure/eu | Healthy | 100% | 99.79% | 3.90s | 27.3s | 44 tps | 1.1M | $0.220 / $1.32 |
OpenAIopenai | Healthy | 99.77% | 99.84% | 2.20s | 16.4s | 53 tps | 1.1M | $0.200 / $1.20 |
OpenAIopenai/flex | Healthy | 99.77% | 99.84% | 1.47s | 29.4s | 35 tps | 1.1M | $0.100 / $0.600 |
OpenAIopenai/priority | Healthy | 99.77% | 99.84% | 1.32s | 8.93s | 31 tps | 1.1M | $0.400 / $2.40 |
Azureazure | Degraded | 93.31% | 93.68% | 3.12s | 23.9s | 36 tps | 1.1M | $0.200 / $1.20 |
Azureazure/us | Down | 86.76% | 87.96% | 3.25s | 24.1s | 38 tps | 1.1M | $0.220 / $1.32 |
- Amazon Bedrock100%Healthy24h 100%
- p50
- 995ms
- p99
- 13.0s
- Throughput
- 108 tps
- Context
- 1.1M
- $/Mtok
- $0.220 / $1.32
amazon-bedrock/us-east-1 - Azure100%Healthy24h 99.79%
- p50
- 3.90s
- p99
- 27.3s
- Throughput
- 44 tps
- Context
- 1.1M
- $/Mtok
- $0.220 / $1.32
azure/eu - OpenAI99.77%Healthy24h 99.84%
- p50
- 2.20s
- p99
- 16.4s
- Throughput
- 53 tps
- Context
- 1.1M
- $/Mtok
- $0.200 / $1.20
openai - OpenAI99.77%Healthy24h 99.84%
- p50
- 1.47s
- p99
- 29.4s
- Throughput
- 35 tps
- Context
- 1.1M
- $/Mtok
- $0.100 / $0.600
openai/flex - OpenAI99.77%Healthy24h 99.84%
- p50
- 1.32s
- p99
- 8.93s
- Throughput
- 31 tps
- Context
- 1.1M
- $/Mtok
- $0.400 / $2.40
openai/priority - Azure93.31%Degraded24h 93.68%
- p50
- 3.12s
- p99
- 23.9s
- Throughput
- 36 tps
- Context
- 1.1M
- $/Mtok
- $0.200 / $1.20
azure - Azure86.76%Down24h 87.96%
- p50
- 3.25s
- p99
- 24.1s
- Throughput
- 38 tps
- Context
- 1.1M
- $/Mtok
- $0.220 / $1.32
azure/us
Measured 2m 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.
Throughput
Median tokens per second.