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% | 2.71s | 29.6s | 24 tps | 400K | $1.75 / $14.00 |
OpenAIopenai | Healthy | 98.97% | 99.30% | 2.73s | 27.2s | 39 tps | 400K | $1.75 / $14.00 |
OpenAIopenai/flex | Healthy | 98.97% | 99.30% | — | — | — | 400K | $0.875 / $7.00 |
OpenAIopenai/priority | Healthy | 98.97% | 99.30% | 5.58s | 14.1s | 75 tps | 400K | $3.50 / $28.00 |
- Azure100%Healthy24h 99.99%
- p50
- 2.71s
- p99
- 29.6s
- Throughput
- 24 tps
- Context
- 400K
- $/Mtok
- $1.75 / $14.00
azure - OpenAI98.97%Healthy24h 99.30%
- p50
- 2.73s
- p99
- 27.2s
- Throughput
- 39 tps
- Context
- 400K
- $/Mtok
- $1.75 / $14.00
openai - OpenAI98.97%Healthy24h 99.30%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 400K
- $/Mtok
- $0.875 / $7.00
openai/flex - OpenAI98.97%Healthy24h 99.30%
- p50
- 5.58s
- p99
- 14.1s
- Throughput
- 75 tps
- Context
- 400K
- $/Mtok
- $3.50 / $28.00
openai/priority
Measured 3m 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.