GPT-5.5
openai/gpt-5.5
Compare with GPT-5.5 Pro, GPT Audio, GPT Audio Mini
CompareGPT-5.5
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Azureazure | Healthy | 100% | 99.90% | 99.91% | 99.91% | 12.6s | 68.4s | 45 tps | 1.1M | $5.00 / $30.00 |
OpenAIopenai | Healthy | 99.28% | 99.08% | 99.02% | 99.02% | 2.43s | 27.8s | 47 tps | 1.1M | $5.00 / $30.00 |
OpenAIopenai/flex | Healthy | 99.28% | 99.08% | 99.02% | 99.02% | 31.1s | 68.9s | 83 tps | 1.1M | $2.50 / $15.00 |
OpenAIopenai/priority | Healthy | 99.28% | 99.08% | 99.02% | 99.02% | 738ms | 3.31s | 68 tps | 1.1M | $12.50 / $75.00 |
Amazon Bedrockamazon-bedrock/us-east-1 | No data | — | — | — | — | — | — | — | 1.1M | $5.50 / $33.00 |
Azureazure/eu | No data | — | 100% | — | — | — | — | — | 1.1M | $5.50 / $33.00 |
Azureazure/us | No data | — | 99.84% | 99.86% | 99.86% | 7.44s | 11.7s | 27 tps | 1.1M | $5.50 / $33.00 |
- Azure100%Healthy24h 99.90%
- 7d
- 99.91%
- 30d
- 99.91%
- p50
- 12.6s
- p99
- 68.4s
- Throughput
- 45 tps
- Context
- 1.1M
- $/Mtok
- $5.00 / $30.00
azure - OpenAI99.28%Healthy24h 99.08%
- 7d
- 99.02%
- 30d
- 99.02%
- p50
- 2.43s
- p99
- 27.8s
- Throughput
- 47 tps
- Context
- 1.1M
- $/Mtok
- $5.00 / $30.00
openai - OpenAI99.28%Healthy24h 99.08%
- 7d
- 99.02%
- 30d
- 99.02%
- p50
- 31.1s
- p99
- 68.9s
- Throughput
- 83 tps
- Context
- 1.1M
- $/Mtok
- $2.50 / $15.00
openai/flex - OpenAI99.28%Healthy24h 99.08%
- 7d
- 99.02%
- 30d
- 99.02%
- p50
- 738ms
- p99
- 3.31s
- Throughput
- 68 tps
- Context
- 1.1M
- $/Mtok
- $12.50 / $75.00
openai/priority - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.1M
- $/Mtok
- $5.50 / $33.00
amazon-bedrock/us-east-1 - No data24h 100%
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.1M
- $/Mtok
- $5.50 / $33.00
azure/eu - No data24h 99.84%
- 7d
- 99.86%
- 30d
- 99.86%
- p50
- 7.44s
- p99
- 11.7s
- Throughput
- 27 tps
- Context
- 1.1M
- $/Mtok
- $5.50 / $33.00
azure/us
Measured 1m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
History
3 endpoints reporting no data are omitted from the charts.
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.