GPT-5.6 Sol: providers compared
Every endpoint serving this model, side by side. ◆ marks the best value in each column — per model, never fleet-wide.
Current state
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Azureazure | Healthy | 100%◆ (best) | 99.49% | 99.14% | 99.14% | 4.06s | 36.6s | 50 tps◆ (best) | 1.1M | $5.00 / $30.00 |
Azureazure/us | Healthy | 100%◆ (best) | 93.82% | 94.45% | 94.45% | 3.06s | 26.8s | 40 tps | 1.1M | $5.50 / $33.00 |
OpenAIopenai | Healthy | 99.96% | 98.95% | 98.95% | 98.95% | 3.27s | 58.5s | 46 tps | 1.1M | $2.50 / $15.00 |
OpenAIopenai/flex | Healthy | 99.96% | 98.95% | 98.95% | 98.95% | 6.50s | 42.0s | 38 tps | 1.1M | $1.25 / $7.50◆ (best) |
OpenAIopenai/priority | Healthy | 99.96% | 98.95% | 98.95% | 98.95% | 823ms◆ (best) | 5.13s◆ (best) | 39 tps | 1.1M | $5.00 / $30.00 |
Amazon Bedrockamazon-bedrock/us-east-1 | No data | — | 100% | 100%◆ (best) | 100%◆ (best) | — | — | — | 1.1M | $5.50 / $33.00 |
Azureazure/eu | No data | — | 100% | 100%◆ (best) | 100%◆ (best) | 3.50s | 6.06s | 33 tps | 1.1M | $5.50 / $33.00 |
- Azure100%◆ (best)Healthy24h 99.49%
- 7d
- 99.14%
- 30d
- 99.14%
- p50
- 4.06s
- p99
- 36.6s
- Throughput
- 50 tps◆ (best)
- Context
- 1.1M
- $/Mtok
- $5.00 / $30.00
azure - Azure100%◆ (best)Healthy24h 93.82%
- 7d
- 94.45%
- 30d
- 94.45%
- p50
- 3.06s
- p99
- 26.8s
- Throughput
- 40 tps
- Context
- 1.1M
- $/Mtok
- $5.50 / $33.00
azure/us - OpenAI99.96%Healthy24h 98.95%
- 7d
- 98.95%
- 30d
- 98.95%
- p50
- 3.27s
- p99
- 58.5s
- Throughput
- 46 tps
- Context
- 1.1M
- $/Mtok
- $2.50 / $15.00
openai - OpenAI99.96%Healthy24h 98.95%
- 7d
- 98.95%
- 30d
- 98.95%
- p50
- 6.50s
- p99
- 42.0s
- Throughput
- 38 tps
- Context
- 1.1M
- $/Mtok
- $1.25 / $7.50◆ (best)
openai/flex - OpenAI99.96%Healthy24h 98.95%
- 7d
- 98.95%
- 30d
- 98.95%
- p50
- 823ms◆ (best)
- p99
- 5.13s◆ (best)
- Throughput
- 39 tps
- Context
- 1.1M
- $/Mtok
- $5.00 / $30.00
openai/priority - No data24h 100%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.1M
- $/Mtok
- $5.50 / $33.00
amazon-bedrock/us-east-1 - No data24h 100%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- 3.50s
- p99
- 6.06s
- Throughput
- 33 tps
- Context
- 1.1M
- $/Mtok
- $5.50 / $33.00
azure/eu
Measured 2m ago. Latency and throughput are OpenRouter's rolling 30-minute windows. ◆ marks the best value in each column among these endpoints.
Price vs latency
One dot per endpoint at the latest round · further left = faster, lower = cheaper · hover a dot for its tag
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 is OpenRouter's rolling 30-minute window.
Throughput
Median tokens per second.