GPT-6 Sol Pro: 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 | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
OpenAIopenai | Healthy | 100% | 100% | 99.98% | 99.98% | 6.00s | 83.7s | 72 tps | 1.1M | $2.00 / $10.00 |
Azureazure | No data | — | 100% | 100%◆ (best) | 100%◆ (best) | 5.68s◆ (best) | 6.27s◆ (best) | 79 tps | 1.1M | $2.00 / $10.00 |
Azureazure/eu | No data | — | — | — | — | 8.57s | 22.9s | 91 tps | 1.1M | $2.20 / $11.00 |
Azureazure/us | No data | — | — | — | — | — | — | — | 1.1M | $2.20 / $11.00 |
OpenAIopenai/fast | No data | — | — | — | — | — | — | — | 1.1M | $4.00 / $20.00 |
OpenAIopenai/flex | No data | — | 100% | — | — | 14.1s | 14.4s | 160 tps◆ (best) | 1.1M | $1.00 / $5.00◆ (best) |
- OpenAI100%Healthy24h 100%
- 7d
- 99.98%
- 30d
- 99.98%
- p50
- 6.00s
- p99
- 83.7s
- Throughput
- 72 tps
- Context
- 1.1M
- $/Mtok
- $2.00 / $10.00
openai - No data24h 100%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- 5.68s◆ (best)
- p99
- 6.27s◆ (best)
- Throughput
- 79 tps
- Context
- 1.1M
- $/Mtok
- $2.00 / $10.00
azure - No data24h —
- 7d
- —
- 30d
- —
- p50
- 8.57s
- p99
- 22.9s
- Throughput
- 91 tps
- Context
- 1.1M
- $/Mtok
- $2.20 / $11.00
azure/eu - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.1M
- $/Mtok
- $2.20 / $11.00
azure/us - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.1M
- $/Mtok
- $4.00 / $20.00
openai/fast - No data24h 100%
- 7d
- —
- 30d
- —
- p50
- 14.1s
- p99
- 14.4s
- Throughput
- 160 tps◆ (best)
- Context
- 1.1M
- $/Mtok
- $1.00 / $5.00◆ (best)
openai/flex
Measured 4m 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, averaged over the hour.
Throughput
Median tokens per second.