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% | 2.24s | 23.7s | 56 tps | 1.1M | $2.00 / $10.00 |
OpenAIopenai | Healthy | 100%◆ (best) | 100% | 100%◆ (best) | 100%◆ (best) | 1.73s | 13.0s | 71 tps | 1.1M | $2.00 / $10.00 |
OpenAIopenai/flex | Healthy | 100%◆ (best) | 99.92% | 99.93% | 99.86% | 1.61s | 17.4s | 61 tps | 1.1M | $1.00 / $5.00◆ (best) |
Amazon Bedrockamazon-bedrock/global | No data | — | 100% | 98.55% | 98.74% | 3.69s | 6.56s | 82 tps◆ (best) | 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% | 1.27s◆ (best) | 8.74s | 82 tps◆ (best) | 1.1M | $4.00 / $20.00 |
- Azure100%◆ (best)Healthy24h 99.92%
- 7d
- 99.91%
- 30d
- 99.78%
- p50
- 2.24s
- p99
- 23.7s
- Throughput
- 56 tps
- Context
- 1.1M
- $/Mtok
- $2.00 / $10.00
azure - OpenAI100%◆ (best)Healthy24h 100%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- 1.73s
- p99
- 13.0s
- Throughput
- 71 tps
- Context
- 1.1M
- $/Mtok
- $2.00 / $10.00
openai - OpenAI100%◆ (best)Healthy24h 99.92%
- 7d
- 99.93%
- 30d
- 99.86%
- p50
- 1.61s
- p99
- 17.4s
- Throughput
- 61 tps
- Context
- 1.1M
- $/Mtok
- $1.00 / $5.00◆ (best)
openai/flex - No data24h 100%
- 7d
- 98.55%
- 30d
- 98.74%
- p50
- 3.69s
- p99
- 6.56s
- Throughput
- 82 tps◆ (best)
- 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
- 1.27s◆ (best)
- p99
- 8.74s
- Throughput
- 82 tps◆ (best)
- Context
- 1.1M
- $/Mtok
- $4.00 / $20.00
openai/fast
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.
Throughput
Median tokens per second.