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 | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Azureazure | No data | — | 100% | 93.47% | 97.82% | 7.01s◆ (best) | 169s◆ (best) | 46 tps | 1.1M | $10.00 / $50.00 |
Azureazure/us | No data | — | — | — | 100%◆ (best) | — | — | — | 1.1M | $11.00 / $55.00 |
OpenAIopenai | No data | — | 100% | 100%◆ (best) | 99.94% | 26.2s | 228s | 64 tps◆ (best) | 1.1M | $10.00 / $50.00 |
OpenAIopenai/fast | No data | — | — | 100%◆ (best) | 100%◆ (best) | — | — | — | 1.1M | $20.00 / $100.00 |
OpenAIopenai/flex | No data | — | — | 100%◆ (best) | 100%◆ (best) | — | — | — | 1.1M | $5.00 / $25.00◆ (best) |
OpenAIopenai/ultrafast | No data | — | — | — | — | — | — | — | 1.1M | $60.00 / $300.00 |
- No data24h 100%
- 7d
- 93.47%
- 30d
- 97.82%
- p50
- 7.01s◆ (best)
- p99
- 169s◆ (best)
- Throughput
- 46 tps
- Context
- 1.1M
- $/Mtok
- $10.00 / $50.00
azure - No data24h —
- 7d
- —
- 30d
- 100%◆ (best)
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.1M
- $/Mtok
- $11.00 / $55.00
azure/us - No data24h 100%
- 7d
- 100%◆ (best)
- 30d
- 99.94%
- p50
- 26.2s
- p99
- 228s
- Throughput
- 64 tps◆ (best)
- Context
- 1.1M
- $/Mtok
- $10.00 / $50.00
openai - No data24h —
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.1M
- $/Mtok
- $20.00 / $100.00
openai/fast - No data24h —
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.1M
- $/Mtok
- $5.00 / $25.00◆ (best)
openai/flex - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.1M
- $/Mtok
- $60.00 / $300.00
openai/ultrafast
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.
Throughput
Median tokens per second.