GPT-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) | 99.92% | 99.91% | 99.78% | 2.22s | 23.9s | 57 tps | 1.1M | $2.00 / $10.00 |
OpenAIopenai | Healthy | 100%◆ (best) | 100% | 100%◆ (best) | 100%◆ (best) | 1.60s | 12.4s | 70 tps | 1.1M | $2.00 / $10.00 |
OpenAIopenai/flex | Healthy | 100%◆ (best) | 99.92% | 99.93% | 99.86% | 1.58s◆ (best) | 15.6s | 60 tps | 1.1M | $1.00 / $5.00◆ (best) |
Amazon Bedrockamazon-bedrock/global | No data | — | 100% | 98.54% | 98.74% | 3.51s | 6.19s | 77 tps | 1.1M | $2.00 / $10.00 |
Amazon Bedrockamazon-bedrock/us-east-1 | No data | — | — | 100%◆ (best) | 100%◆ (best) | — | — | — | 1.1M | $2.20 / $11.00 |
Azureazure/eu | No data | — | 100% | 100%◆ (best) | 100%◆ (best) | 1.64s | 4.58s◆ (best) | 61 tps | 1.1M | $2.20 / $11.00 |
Azureazure/us | No data | — | 100% | 100%◆ (best) | 100%◆ (best) | — | — | — | 1.1M | $2.20 / $11.00 |
OpenAIopenai/fast | No data | — | 100% | 100%◆ (best) | 99.98% | 2.42s | 6.64s | 131 tps◆ (best) | 1.1M | $4.00 / $20.00 |
- Azure100%◆ (best)Healthy24h 99.92%
- 7d
- 99.91%
- 30d
- 99.78%
- p50
- 2.22s
- p99
- 23.9s
- Throughput
- 57 tps
- Context
- 1.1M
- $/Mtok
- $2.00 / $10.00
azure - OpenAI100%◆ (best)Healthy24h 100%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- 1.60s
- p99
- 12.4s
- Throughput
- 70 tps
- Context
- 1.1M
- $/Mtok
- $2.00 / $10.00
openai - OpenAI100%◆ (best)Healthy24h 99.92%
- 7d
- 99.93%
- 30d
- 99.86%
- p50
- 1.58s◆ (best)
- p99
- 15.6s
- Throughput
- 60 tps
- Context
- 1.1M
- $/Mtok
- $1.00 / $5.00◆ (best)
openai/flex - No data24h 100%
- 7d
- 98.54%
- 30d
- 98.74%
- p50
- 3.51s
- p99
- 6.19s
- Throughput
- 77 tps
- Context
- 1.1M
- $/Mtok
- $2.00 / $10.00
amazon-bedrock/global - No data24h —
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.1M
- $/Mtok
- $2.20 / $11.00
amazon-bedrock/us-east-1 - No data24h 100%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- 1.64s
- p99
- 4.58s◆ (best)
- Throughput
- 61 tps
- Context
- 1.1M
- $/Mtok
- $2.20 / $11.00
azure/eu - No data24h 100%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.1M
- $/Mtok
- $2.20 / $11.00
azure/us - No data24h 100%
- 7d
- 100%◆ (best)
- 30d
- 99.98%
- p50
- 2.42s
- p99
- 6.64s
- Throughput
- 131 tps◆ (best)
- Context
- 1.1M
- $/Mtok
- $4.00 / $20.00
openai/fast
Measured 1m 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.