CompareGPT-5.6 Luna
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Amazon Bedrockamazon-bedrock/us-east-1 | Healthy | 100% | 99.94% | 99.97% | 99.97% | 1.50s | 18.3s | 102 tps | 1.1M | $0.220 / $1.32 |
Azureazure/eu | Healthy | 100% | 100% | 99.94% | 99.94% | 1.40s | 8.01s | 49 tps | 1.1M | $0.220 / $1.32 |
Azureazure | Healthy | 99.95% | 97.75% | 96.46% | 96.46% | 4.60s | 20.2s | 60 tps | 1.1M | $0.200 / $1.20 |
OpenAIopenai | Healthy | 99.06% | 99.77% | 99.64% | 99.64% | 597ms | 9.13s | 78 tps | 1.1M | $0.200 / $1.20 |
OpenAIopenai/flex | Healthy | 99.06% | 99.77% | 99.64% | 99.64% | 2.51s | 70.1s | 38 tps | 1.1M | $0.100 / $0.600 |
OpenAIopenai/priority | Healthy | 99.06% | 99.77% | 99.64% | 99.64% | 1.17s | 3.64s | 26 tps | 1.1M | $0.400 / $2.40 |
Azureazure/us | No data | — | 92.13% | 95.74% | 95.74% | 4.96s | 30.7s | 48 tps | 1.1M | $0.220 / $1.32 |
- Amazon Bedrock100%Healthy24h 99.94%
- 7d
- 99.97%
- 30d
- 99.97%
- p50
- 1.50s
- p99
- 18.3s
- Throughput
- 102 tps
- Context
- 1.1M
- $/Mtok
- $0.220 / $1.32
amazon-bedrock/us-east-1 - Azure100%Healthy24h 100%
- 7d
- 99.94%
- 30d
- 99.94%
- p50
- 1.40s
- p99
- 8.01s
- Throughput
- 49 tps
- Context
- 1.1M
- $/Mtok
- $0.220 / $1.32
azure/eu - Azure99.95%Healthy24h 97.75%
- 7d
- 96.46%
- 30d
- 96.46%
- p50
- 4.60s
- p99
- 20.2s
- Throughput
- 60 tps
- Context
- 1.1M
- $/Mtok
- $0.200 / $1.20
azure - OpenAI99.06%Healthy24h 99.77%
- 7d
- 99.64%
- 30d
- 99.64%
- p50
- 597ms
- p99
- 9.13s
- Throughput
- 78 tps
- Context
- 1.1M
- $/Mtok
- $0.200 / $1.20
openai - OpenAI99.06%Healthy24h 99.77%
- 7d
- 99.64%
- 30d
- 99.64%
- p50
- 2.51s
- p99
- 70.1s
- Throughput
- 38 tps
- Context
- 1.1M
- $/Mtok
- $0.100 / $0.600
openai/flex - OpenAI99.06%Healthy24h 99.77%
- 7d
- 99.64%
- 30d
- 99.64%
- p50
- 1.17s
- p99
- 3.64s
- Throughput
- 26 tps
- Context
- 1.1M
- $/Mtok
- $0.400 / $2.40
openai/priority - No data24h 92.13%
- 7d
- 95.74%
- 30d
- 95.74%
- p50
- 4.96s
- p99
- 30.7s
- Throughput
- 48 tps
- Context
- 1.1M
- $/Mtok
- $0.220 / $1.32
azure/us
Measured 3m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
History
1 endpoint reporting no data is omitted from the charts.
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.
Daily availability
One row per endpoint · one dot per day · last 90 days.
worst hour ≥ 95%90–95%< 90%no data
Colour by each endpoint's worst hour of each UTC day · 7 endpoints · 4 days with data, 10 endpoint-days below 90%.
Price changes
- GPT-5.6 LunaOpenAIopenai/priority$0.400 / $2.402026-08-21 23:40 UTC