GPT-6 Astra
openai/gpt-6-astraInputOutput
Compare its 5 providersIncident RSSCompare with GPT-6 Astra Pro, GPT Audio, GPT Audio Mini
CompareGPT-6 Astra
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Azureazure | Healthy | 100% | 99.27% | 97.22% | 97.22% | 6.84s | 111s | 33 tps | 1.1M | $10.00 / $50.00 |
OpenAIopenai/fast | Healthy | 100% | 100% | 99.99% | 99.99% | 1.74s | 25.4s | 27 tps | 1.1M | $20.00 / $100.00 |
OpenAIopenai/flex | Healthy | 100% | 99.97% | 99.96% | 99.97% | 8.46s | 27.6s | 24 tps | 1.1M | $5.00 / $25.00 |
OpenAIopenai | Healthy | 99.99% | 99.86% | 99.53% | 99.61% | 15.3s | 98.4s | 34 tps | 1.1M | $10.00 / $50.00 |
Azureazure/us | No data | — | 100% | 94.21% | 94.40% | 6.21s | 7.80s | 24 tps | 1.1M | $11.00 / $55.00 |
- Azure100%Healthy24h 99.27%
- 7d
- 97.22%
- 30d
- 97.22%
- p50
- 6.84s
- p99
- 111s
- Throughput
- 33 tps
- Context
- 1.1M
- $/Mtok
- $10.00 / $50.00
azure - OpenAI100%Healthy24h 100%
- 7d
- 99.99%
- 30d
- 99.99%
- p50
- 1.74s
- p99
- 25.4s
- Throughput
- 27 tps
- Context
- 1.1M
- $/Mtok
- $20.00 / $100.00
openai/fast - OpenAI100%Healthy24h 99.97%
- 7d
- 99.96%
- 30d
- 99.97%
- p50
- 8.46s
- p99
- 27.6s
- Throughput
- 24 tps
- Context
- 1.1M
- $/Mtok
- $5.00 / $25.00
openai/flex - OpenAI99.99%Healthy24h 99.86%
- 7d
- 99.53%
- 30d
- 99.61%
- p50
- 15.3s
- p99
- 98.4s
- Throughput
- 34 tps
- Context
- 1.1M
- $/Mtok
- $10.00 / $50.00
openai - No data24h 100%
- 7d
- 94.21%
- 30d
- 94.40%
- p50
- 6.21s
- p99
- 7.80s
- Throughput
- 24 tps
- Context
- 1.1M
- $/Mtok
- $11.00 / $55.00
azure/us
Measured 1m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
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.
Daily availability
One row per endpoint · one dot per day · last 90 days.
worst hour ≥ 95%90–95%< 90%no data
Colour by each endpoint's worst hour of each UTC day · 5 endpoints · 13 days with data, 17 endpoint-days below 90%.