GPT-5.2
openai/gpt-5.2
Compare with GPT Audio, GPT Audio Mini, GPT Chat Latest
CompareGPT-5.2
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
Azureazure | Healthy | 100% | 99.99% | 2.70s | 46.9s | 18 tps | 400K | $1.75 / $14.00 |
OpenAIopenai | Healthy | 99.44% | 99.31% | 2.40s | 18.0s | 35 tps | 400K | $1.75 / $14.00 |
OpenAIopenai/flex | Healthy | 99.44% | 99.31% | — | — | — | 400K | $0.875 / $7.00 |
OpenAIopenai/priority | Healthy | 99.44% | 99.31% | 5.86s | 12.2s | 85 tps | 400K | $3.50 / $28.00 |
- Azure100%Healthy24h 99.99%
- p50
- 2.70s
- p99
- 46.9s
- Throughput
- 18 tps
- Context
- 400K
- $/Mtok
- $1.75 / $14.00
azure - OpenAI99.44%Healthy24h 99.31%
- p50
- 2.40s
- p99
- 18.0s
- Throughput
- 35 tps
- Context
- 400K
- $/Mtok
- $1.75 / $14.00
openai - OpenAI99.44%Healthy24h 99.31%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 400K
- $/Mtok
- $0.875 / $7.00
openai/flex - OpenAI99.44%Healthy24h 99.31%
- p50
- 5.86s
- p99
- 12.2s
- Throughput
- 85 tps
- Context
- 400K
- $/Mtok
- $3.50 / $28.00
openai/priority
Measured 4m 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 and p99 are OpenRouter's rolling 30-minute windows, averaged over the hour.
Throughput
Median tokens per second.