GPT-5.5
openai/gpt-5.5
Compare with GPT-5.5 Pro, GPT Audio, GPT Audio Mini
CompareGPT-5.5
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
Azureazure | Healthy | 100% | 99.93% | 4.99s | 103s | 52 tps | 1.1M | $5.00 / $30.00 |
OpenAIopenai | Degraded | 94.25% | 99.51% | 3.25s | 30.1s | 44 tps | 1.1M | $5.00 / $30.00 |
OpenAIopenai/flex | Degraded | 94.25% | 99.51% | 16.3s | 58.5s | 85 tps | 1.1M | $2.50 / $15.00 |
OpenAIopenai/priority | Degraded | 94.25% | 99.51% | 1.47s | 4.90s | 69 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% | 636ms | 673ms | 6.0 tps | 1.1M | $5.50 / $33.00 |
Azureazure/us | No data | — | 97.91% | 2.12s | 2.12s | 38 tps | 1.1M | $5.50 / $33.00 |
- Azure100%Healthy24h 99.93%
- p50
- 4.99s
- p99
- 103s
- Throughput
- 52 tps
- Context
- 1.1M
- $/Mtok
- $5.00 / $30.00
azure - OpenAI94.25%Degraded24h 99.51%
- p50
- 3.25s
- p99
- 30.1s
- Throughput
- 44 tps
- Context
- 1.1M
- $/Mtok
- $5.00 / $30.00
openai - OpenAI94.25%Degraded24h 99.51%
- p50
- 16.3s
- p99
- 58.5s
- Throughput
- 85 tps
- Context
- 1.1M
- $/Mtok
- $2.50 / $15.00
openai/flex - OpenAI94.25%Degraded24h 99.51%
- p50
- 1.47s
- p99
- 4.90s
- Throughput
- 69 tps
- Context
- 1.1M
- $/Mtok
- $12.50 / $75.00
openai/priority - Amazon Bedrock—No data24h —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.1M
- $/Mtok
- $5.50 / $33.00
amazon-bedrock/us-east-1 - Azure—No data24h 100%
- p50
- 636ms
- p99
- 673ms
- Throughput
- 6.0 tps
- Context
- 1.1M
- $/Mtok
- $5.50 / $33.00
azure/eu - Azure—No data24h 97.91%
- p50
- 2.12s
- p99
- 2.12s
- Throughput
- 38 tps
- Context
- 1.1M
- $/Mtok
- $5.50 / $33.00
azure/us
Measured 3m 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 and p99 are OpenRouter's rolling 30-minute windows, averaged over the hour.
Throughput
Median tokens per second.