GPT-5.2: providers compared
Every endpoint serving this model, side by side. ◆ marks the best value in each column — per model, never fleet-wide.
Current state
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Azureazure | Healthy | 100%◆ (best) | 99.94% | 99.97% | 99.89% | 6.42s | 49.4s | 76 tps | 400K | $1.75 / $14.00 |
OpenAIopenai | Healthy | 100%◆ (best) | 99.99% | 99.93% | 99.45% | 1.96s | 13.4s | 46 tps | 400K | $1.75 / $14.00 |
OpenAIopenai/fast | No data | — | 100% | 100%◆ (best) | 100%◆ (best) | 4.41s | 6.67s | 103 tps | 400K | $3.50 / $28.00 |
OpenAIopenai/flex | No data | — | 99.89% | 100%◆ (best) | 100%◆ (best) | 1.13s◆ (best) | 1.42s◆ (best) | 177 tps◆ (best) | 400K | $0.875 / $7.00◆ (best) |
OpenAIopenai/priority | No data | — | — | — | — | — | — | — | 400K | $3.50 / $28.00 |
- Azure100%◆ (best)Healthy24h 99.94%
- 7d
- 99.97%
- 30d
- 99.89%
- p50
- 6.42s
- p99
- 49.4s
- Throughput
- 76 tps
- Context
- 400K
- $/Mtok
- $1.75 / $14.00
azure - OpenAI100%◆ (best)Healthy24h 99.99%
- 7d
- 99.93%
- 30d
- 99.45%
- p50
- 1.96s
- p99
- 13.4s
- Throughput
- 46 tps
- Context
- 400K
- $/Mtok
- $1.75 / $14.00
openai - No data24h 100%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- 4.41s
- p99
- 6.67s
- Throughput
- 103 tps
- Context
- 400K
- $/Mtok
- $3.50 / $28.00
openai/fast - No data24h 99.89%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- 1.13s◆ (best)
- p99
- 1.42s◆ (best)
- Throughput
- 177 tps◆ (best)
- Context
- 400K
- $/Mtok
- $0.875 / $7.00◆ (best)
openai/flex - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 400K
- $/Mtok
- $3.50 / $28.00
openai/priority
Measured 2m ago. Latency and throughput are OpenRouter's rolling 30-minute windows. ◆ marks the best value in each column among these endpoints.
Price vs latency
One dot per endpoint at the latest round · further left = faster, lower = cheaper · hover a dot for its tag
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.