GPT-5.6 Sol
openai/gpt-5.6-sol
Compare with GPT-5.6 Luna, GPT-5.6 Terra, GPT-5.6 Luna Pro
CompareGPT-5.6 Sol
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
Azureazure/eu | Healthy | 100% | 99.99% | 4.45s | 32.7s | 40 tps | 1.1M | $5.50 / $33.00 |
Azureazure | Healthy | 99.93% | 99.25% | 3.52s | 34.3s | 36 tps | 1.1M | $5.00 / $30.00 |
OpenAIopenai | Healthy | 99.27% | 99.44% | 3.16s | 74.5s | 40 tps | 1.1M | $2.50 / $15.00 |
OpenAIopenai/flex | Healthy | 99.27% | 99.44% | 4.14s | 126s | 60 tps | 1.1M | $1.25 / $7.50 |
OpenAIopenai/priority | Healthy | 99.27% | 99.44% | 2.47s | 17.8s | 74 tps | 1.1M | $5.00 / $30.00 |
Azureazure/us | Down | 67.80% | 89.88% | 3.39s | 24.1s | 42 tps | 1.1M | $5.50 / $33.00 |
Amazon Bedrockamazon-bedrock/us-east-1 | No data | — | 100% | 8.22s | 12.3s | 20 tps | 1.1M | $5.50 / $33.00 |
- Azure100%Healthy24h 99.99%
- p50
- 4.45s
- p99
- 32.7s
- Throughput
- 40 tps
- Context
- 1.1M
- $/Mtok
- $5.50 / $33.00
azure/eu - Azure99.93%Healthy24h 99.25%
- p50
- 3.52s
- p99
- 34.3s
- Throughput
- 36 tps
- Context
- 1.1M
- $/Mtok
- $5.00 / $30.00
azure - OpenAI99.27%Healthy24h 99.44%
- p50
- 3.16s
- p99
- 74.5s
- Throughput
- 40 tps
- Context
- 1.1M
- $/Mtok
- $2.50 / $15.00
openai - OpenAI99.27%Healthy24h 99.44%
- p50
- 4.14s
- p99
- 126s
- Throughput
- 60 tps
- Context
- 1.1M
- $/Mtok
- $1.25 / $7.50
openai/flex - OpenAI99.27%Healthy24h 99.44%
- p50
- 2.47s
- p99
- 17.8s
- Throughput
- 74 tps
- Context
- 1.1M
- $/Mtok
- $5.00 / $30.00
openai/priority - Azure67.80%Down24h 89.88%
- p50
- 3.39s
- p99
- 24.1s
- Throughput
- 42 tps
- Context
- 1.1M
- $/Mtok
- $5.50 / $33.00
azure/us - Amazon Bedrock—No data24h 100%
- p50
- 8.22s
- p99
- 12.3s
- Throughput
- 20 tps
- Context
- 1.1M
- $/Mtok
- $5.50 / $33.00
amazon-bedrock/us-east-1
Measured 4m 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.