GPT-6 Astra 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% | 99.85% | 99.75% | 99.63% | 8.50s◆ (best) | 204s | 52 tps | 1.1M | $10.00 / $50.00 |
Azureazure | No data | — | 99.47% | 98.65% | 98.39% | 31.3s | 301s | 47 tps | 1.1M | $10.00 / $50.00 |
Azureazure/us | No data | — | 100% | 94.66% | 94.90% | 9.28s | 80.2s◆ (best) | 60 tps◆ (best) | 1.1M | $11.00 / $55.00 |
OpenAIopenai/fast | No data | — | 100% | 100%◆ (best) | 100%◆ (best) | — | — | — | 1.1M | $20.00 / $100.00 |
OpenAIopenai/flex | No data | — | 99.90% | 100%◆ (best) | 100% | — | — | — | 1.1M | $5.00 / $25.00◆ (best) |
- OpenAI100%Healthy24h 99.85%
- 7d
- 99.75%
- 30d
- 99.63%
- p50
- 8.50s◆ (best)
- p99
- 204s
- Throughput
- 52 tps
- Context
- 1.1M
- $/Mtok
- $10.00 / $50.00
openai - No data24h 99.47%
- 7d
- 98.65%
- 30d
- 98.39%
- p50
- 31.3s
- p99
- 301s
- Throughput
- 47 tps
- Context
- 1.1M
- $/Mtok
- $10.00 / $50.00
azure - No data24h 100%
- 7d
- 94.66%
- 30d
- 94.90%
- p50
- 9.28s
- p99
- 80.2s◆ (best)
- Throughput
- 60 tps◆ (best)
- Context
- 1.1M
- $/Mtok
- $11.00 / $55.00
azure/us - No data24h 100%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.1M
- $/Mtok
- $20.00 / $100.00
openai/fast - No data24h 99.90%
- 7d
- 100%◆ (best)
- 30d
- 100%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.1M
- $/Mtok
- $5.00 / $25.00◆ (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.
Throughput
Median tokens per second.