GPT-5.6 Terra
openai/gpt-5.6-terra
Compare with GPT-5.6 Luna, GPT-5.6 Sol, GPT-5.6 Luna Pro
CompareGPT-5.6 Terra
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
Azureazure | Healthy | 100% | 99.92% | 1.26s | 15.3s | 47 tps | 1.1M | $2.00 / $12.00 |
Azureazure/eu | Healthy | 100% | 99.99% | 3.89s | 26.6s | 60 tps | 1.1M | $2.20 / $13.20 |
Azureazure/us | Healthy | 100% | 96.19% | 3.53s | 24.6s | 55 tps | 1.1M | $2.20 / $13.20 |
OpenAIopenai | Healthy | 99.84% | 99.93% | 2.09s | 14.1s | 48 tps | 1.1M | $2.00 / $12.00 |
OpenAIopenai/flex | Healthy | 99.84% | 99.93% | 1.49s | 20.5s | 119 tps | 1.1M | $1.00 / $6.00 |
OpenAIopenai/priority | Healthy | 99.84% | 99.93% | 2.14s | 18.5s | 59 tps | 1.1M | $4.00 / $24.00 |
Amazon Bedrockamazon-bedrock/us-east-1 | No data | — | 100% | 474ms | 557ms | 38 tps | 1.1M | $2.20 / $13.20 |
- Azure100%Healthy24h 99.92%
- p50
- 1.26s
- p99
- 15.3s
- Throughput
- 47 tps
- Context
- 1.1M
- $/Mtok
- $2.00 / $12.00
azure - Azure100%Healthy24h 99.99%
- p50
- 3.89s
- p99
- 26.6s
- Throughput
- 60 tps
- Context
- 1.1M
- $/Mtok
- $2.20 / $13.20
azure/eu - Azure100%Healthy24h 96.19%
- p50
- 3.53s
- p99
- 24.6s
- Throughput
- 55 tps
- Context
- 1.1M
- $/Mtok
- $2.20 / $13.20
azure/us - OpenAI99.84%Healthy24h 99.93%
- p50
- 2.09s
- p99
- 14.1s
- Throughput
- 48 tps
- Context
- 1.1M
- $/Mtok
- $2.00 / $12.00
openai - OpenAI99.84%Healthy24h 99.93%
- p50
- 1.49s
- p99
- 20.5s
- Throughput
- 119 tps
- Context
- 1.1M
- $/Mtok
- $1.00 / $6.00
openai/flex - OpenAI99.84%Healthy24h 99.93%
- p50
- 2.14s
- p99
- 18.5s
- Throughput
- 59 tps
- Context
- 1.1M
- $/Mtok
- $4.00 / $24.00
openai/priority - Amazon Bedrock—No data24h 100%
- p50
- 474ms
- p99
- 557ms
- Throughput
- 38 tps
- Context
- 1.1M
- $/Mtok
- $2.20 / $13.20
amazon-bedrock/us-east-1
Measured 5m 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 and p99 are OpenRouter's rolling 30-minute windows.
Throughput
Median tokens per second.