GPT-6 Astra
openai/gpt-6-astraInputOutput
Compare its 8 providersIncident RSSCompare with GPT-6 Sol, GPT-6 Luna, GPT-6 Astra Pro
CompareGPT-6 Astra
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Azureazure | Healthy | 100% | 100% | 95.11% | 98.49% | 4.71s | 28.5s | 28 tps | 1.1M | $10.00 / $50.00 |
OpenAIopenai | Healthy | 100% | 98.96% | 97.72% | 99.44% | 2.31s | 126s | 38 tps | 1.1M | $10.00 / $50.00 |
OpenAIopenai/flex | Healthy | 100% | 99.89% | 98.93% | 99.74% | 2.95s | 37.8s | 37 tps | 1.1M | $5.00 / $25.00 |
Amazon Bedrockamazon-bedrock/global | No data | — | 88.89% | 93.76% | 93.76% | 7.64s | 25.3s | 59 tps | 1.1M | $10.00 / $50.00 |
Amazon Bedrockamazon-bedrock/us-west-2 | No data | — | — | 100% | 100% | — | — | — | 1.1M | $11.00 / $55.00 |
Azureazure/us | No data | — | 100% | 97.54% | 99.17% | 21.9s | 29.7s | 34 tps | 1.1M | $11.00 / $55.00 |
OpenAIopenai/fast | No data | — | 100% | 100% | 99.94% | 1.75s | 13.1s | 62 tps | 1.1M | $20.00 / $100.00 |
OpenAIopenai/ultrafast | No data | — | 100% | 99.57% | 99.86% | 2.92s | 5.59s | 132 tps | 1.1M | $60.00 / $300.00 |
- Azure100%Healthy24h 100%
- 7d
- 95.11%
- 30d
- 98.49%
- p50
- 4.71s
- p99
- 28.5s
- Throughput
- 28 tps
- Context
- 1.1M
- $/Mtok
- $10.00 / $50.00
azure - OpenAI100%Healthy24h 98.96%
- 7d
- 97.72%
- 30d
- 99.44%
- p50
- 2.31s
- p99
- 126s
- Throughput
- 38 tps
- Context
- 1.1M
- $/Mtok
- $10.00 / $50.00
openai - OpenAI100%Healthy24h 99.89%
- 7d
- 98.93%
- 30d
- 99.74%
- p50
- 2.95s
- p99
- 37.8s
- Throughput
- 37 tps
- Context
- 1.1M
- $/Mtok
- $5.00 / $25.00
openai/flex - No data24h 88.89%
- 7d
- 93.76%
- 30d
- 93.76%
- p50
- 7.64s
- p99
- 25.3s
- Throughput
- 59 tps
- Context
- 1.1M
- $/Mtok
- $10.00 / $50.00
amazon-bedrock/global - No data24h —
- 7d
- 100%
- 30d
- 100%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.1M
- $/Mtok
- $11.00 / $55.00
amazon-bedrock/us-west-2 - No data24h 100%
- 7d
- 97.54%
- 30d
- 99.17%
- p50
- 21.9s
- p99
- 29.7s
- Throughput
- 34 tps
- Context
- 1.1M
- $/Mtok
- $11.00 / $55.00
azure/us - No data24h 100%
- 7d
- 100%
- 30d
- 99.94%
- p50
- 1.75s
- p99
- 13.1s
- Throughput
- 62 tps
- Context
- 1.1M
- $/Mtok
- $20.00 / $100.00
openai/fast - No data24h 100%
- 7d
- 99.57%
- 30d
- 99.86%
- p50
- 2.92s
- p99
- 5.59s
- Throughput
- 132 tps
- Context
- 1.1M
- $/Mtok
- $60.00 / $300.00
openai/ultrafast
Measured 45s 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, averaged over the hour.
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 · 8 endpoints · 59 days with data, 32 endpoint-days below 90%.