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/eu | Healthy | 100% | 99.99% | 3.73s | 23.5s | 61 tps | 1.1M | $2.20 / $13.20 |
Azureazure/us | Healthy | 100% | 96.75% | 3.72s | 24.7s | 58 tps | 1.1M | $2.20 / $13.20 |
OpenAIopenai | Healthy | 99.91% | 99.93% | 2.19s | 16.5s | 43 tps | 1.1M | $2.00 / $12.00 |
OpenAIopenai/flex | Healthy | 99.91% | 99.93% | 1.73s | 15.4s | 88 tps | 1.1M | $1.00 / $6.00 |
OpenAIopenai/priority | Healthy | 99.91% | 99.93% | 1.60s | 8.61s | 77 tps | 1.1M | $4.00 / $24.00 |
Azureazure | Healthy | 99.56% | 99.93% | 2.05s | 21.1s | 47 tps | 1.1M | $2.00 / $12.00 |
Amazon Bedrockamazon-bedrock/us-east-1 | No data | — | 100% | 704ms | 721ms | 29 tps | 1.1M | $2.20 / $13.20 |
- Azure100%Healthy24h 99.99%
- p50
- 3.73s
- p99
- 23.5s
- Throughput
- 61 tps
- Context
- 1.1M
- $/Mtok
- $2.20 / $13.20
azure/eu - Azure100%Healthy24h 96.75%
- p50
- 3.72s
- p99
- 24.7s
- Throughput
- 58 tps
- Context
- 1.1M
- $/Mtok
- $2.20 / $13.20
azure/us - OpenAI99.91%Healthy24h 99.93%
- p50
- 2.19s
- p99
- 16.5s
- Throughput
- 43 tps
- Context
- 1.1M
- $/Mtok
- $2.00 / $12.00
openai - OpenAI99.91%Healthy24h 99.93%
- p50
- 1.73s
- p99
- 15.4s
- Throughput
- 88 tps
- Context
- 1.1M
- $/Mtok
- $1.00 / $6.00
openai/flex - OpenAI99.91%Healthy24h 99.93%
- p50
- 1.60s
- p99
- 8.61s
- Throughput
- 77 tps
- Context
- 1.1M
- $/Mtok
- $4.00 / $24.00
openai/priority - Azure99.56%Healthy24h 99.93%
- p50
- 2.05s
- p99
- 21.1s
- Throughput
- 47 tps
- Context
- 1.1M
- $/Mtok
- $2.00 / $12.00
azure - Amazon Bedrock—No data24h 100%
- p50
- 704ms
- p99
- 721ms
- Throughput
- 29 tps
- Context
- 1.1M
- $/Mtok
- $2.20 / $13.20
amazon-bedrock/us-east-1
Measured 1m 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, averaged over the hour.
Throughput
Median tokens per second.