GPT-6.1 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/us | Healthy | 100%◆ (best) | 99.35% | 98.95% | 98.95% | 2.34s | 15.0s | 25 tps | 1.1M | $2.20 / $11.00 |
OpenAIopenai/fast | Healthy | 100%◆ (best) | 99.98% | 100%◆ (best) | 100%◆ (best) | 3.07s | 55.9s | 56 tps◆ (best) | 1.1M | $4.00 / $20.00 |
OpenAIopenai | Healthy | 99.97% | 99.87% | 99.81% | 99.81% | 4.22s | 76.9s | 33 tps | 1.1M | $2.00 / $10.00 |
Azureazure | Healthy | 99.91% | 99.94% | 99.87% | 99.87% | 4.78s | 41.4s | 38 tps | 1.1M | $2.00 / $10.00 |
OpenAIopenai/flex | Healthy | 99.78% | 99.95% | 99.99% | 99.99% | 8.45s | 84.2s | 48 tps | 1.1M | $1.00 / $5.00◆ (best) |
Azureazure/eu | No data | — | 99.96% | 99.99% | 99.99% | 1.93s◆ (best) | 7.92s◆ (best) | 48 tps | 1.1M | $2.20 / $11.00 |
- Azure100%◆ (best)Healthy24h 99.35%
- 7d
- 98.95%
- 30d
- 98.95%
- p50
- 2.34s
- p99
- 15.0s
- Throughput
- 25 tps
- Context
- 1.1M
- $/Mtok
- $2.20 / $11.00
azure/us - OpenAI100%◆ (best)Healthy24h 99.98%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- 3.07s
- p99
- 55.9s
- Throughput
- 56 tps◆ (best)
- Context
- 1.1M
- $/Mtok
- $4.00 / $20.00
openai/fast - OpenAI99.97%Healthy24h 99.87%
- 7d
- 99.81%
- 30d
- 99.81%
- p50
- 4.22s
- p99
- 76.9s
- Throughput
- 33 tps
- Context
- 1.1M
- $/Mtok
- $2.00 / $10.00
openai - Azure99.91%Healthy24h 99.94%
- 7d
- 99.87%
- 30d
- 99.87%
- p50
- 4.78s
- p99
- 41.4s
- Throughput
- 38 tps
- Context
- 1.1M
- $/Mtok
- $2.00 / $10.00
azure - OpenAI99.78%Healthy24h 99.95%
- 7d
- 99.99%
- 30d
- 99.99%
- p50
- 8.45s
- p99
- 84.2s
- Throughput
- 48 tps
- Context
- 1.1M
- $/Mtok
- $1.00 / $5.00◆ (best)
openai/flex - No data24h 99.96%
- 7d
- 99.99%
- 30d
- 99.99%
- p50
- 1.93s◆ (best)
- p99
- 7.92s◆ (best)
- Throughput
- 48 tps
- Context
- 1.1M
- $/Mtok
- $2.20 / $11.00
azure/eu
Measured 3m 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.