GPT-5.2
GPT-5.2 is an earlier professional-work release that remains available in the catalog. It has a December 2025 snapshot and a 400,000-token context window.
An earlier model can remain available
OpenAI recommends a newer flagship for new work but still documents GPT-5.2 API access. Reasoning ranges from none to xhigh, with none as default. It supports text and image input, tool calls, structured output and Batch processing.GPT-5.2 official model documentation
Evaluate a migration against saved work
Practical guidance. For an existing application, compare representative tasks using the same inputs and review conditions. Check tool behavior and output formatting as well as answer quality. Preserve the model version in operational records so changes can be understood later.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Access | API |
| Model identifiers | gpt-5.2gpt-5.2-2025-12-11 |
| Context window | 400,000 tokens Published model context; input and output share this budget GPT-5.2 official model documentation |
| Maximum output | 128,000 tokens Published maximum output; bounded by the remaining context GPT-5.2 official model documentation |
| Input price | 1.75 USD per million tokens Standard text processing at the reviewed date GPT-5.2 official model documentation |
| Output price | 14 USD per million tokens Standard text processing at the reviewed date GPT-5.2 official model documentation |
| Input and output | text, image in; text outGPT-5.2 official model documentation |
| API routes | Chat Completions (v1/chat/completions); Responses (v1/responses); Batch (v1/batch)GPT-5.2 official model documentation |
Related models
- GPT-5.2 Pro
OpenAI ยท GPT-5.2
A higher-compute GPT-5.2 model accessed through the Responses API.
Launch date not confirmedAPI