GPT-5.2 pricing & benchmarks
Released Dec 10, 2025 · served by 2 providers
What GPT-5.2 is
GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1. It uses adaptive reasoning to allocate computation dynamically, responding quickly...
- Model ID:
openai/gpt-5.2 - Modality: text+image+file->text
- Tool calling: supported · Structured output: supported
Providers and prices for GPT-5.2
The same model costs different amounts depending on who serves it. Prices are per 1M tokens, cheapest first. Uptime and throughput are OpenRouter's rolling measurements, not vendor claims.
| Provider | Input | Output | Context | Quant | Uptime 24h | Throughput |
|---|---|---|---|---|---|---|
| Azurecheapest | $1.75 | $14.00 | 400K | — | 100.0% | — |
| OpenAI | $3.50 | $28.00 | 400K | — | 99.7% | — |
GPT-5.2 benchmark results
Design Arena head-to-head results, as reported through the OpenRouter model API.
| Category | Arena | Rank | Elo | Win rate |
|---|---|---|---|---|
| godotgamedev | agents | #18 | 1142 | 48.1% |
| mobileapps | agents | #24 | 1169 | 47% |
| asciiart | models | #25 | 1190 | 50.7% |
| fullstack | agents | #25 | 1091 | 44.1% |
| webapps | agents | #26 | 1140 | 45.4% |
| androidnative | agents | #28 | 1049 | 49.2% |
| gamedev | models | #34 | 1252 | 56.1% |
| svg | models | #35 | 1189 | 53.7% |
| dataviz | models | #38 | 1231 | 56.1% |
| uicomponent | models | #39 | 1226 | 51.4% |
| website | models | #41 | 1219 | 54.5% |
| codecategories | models | #52 | 1200 | 49.8% |
| 3d | models | #70 | 1136 | 41.5% |
FAQ
How much does the GPT-5.2 API cost?
$1.75 per 1M input tokens and $14.00 per 1M output tokens. A typical workload of 1M input + 300K output tokens costs about $5.95.
Is GPT-5.2 free?
No. It is a paid model starting at $1.75 per 1M input tokens, though some providers offer trial credits.
Which provider is cheapest for GPT-5.2?
Azure at $1.75 input / $14.00 output per 1M tokens.
Can I self-host GPT-5.2?
No. GPT-5.2 is closed-weight and only available through hosted APIs.