GPT-4o
GPT-4o is a deprecated general model with text and image input and text output. This API model is separate from the audio and Realtime preview releases that shared its family name.
Deprecated API; check access details
The omni name does not grant every output modality
The reviewed model contract lists a 128,000-token window and a 16,384-token output ceiling. Its default snapshot is from August 2024. Image understanding and structured text are part of this route; audio generation uses other model contracts.GPT-4o official model documentation
Review an existing integration
Practical guidance. Before moving an older multimodal feature, identify the exact endpoint and input types it uses. Compare document reading, image interpretation and output formatting independently. Do not assume every model with the same family name accepts the same request.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Status | Deprecated API; check access details |
| Access | API |
| Model identifiers | gpt-4ogpt-4o-2024-08-06 |
| Context window | 128,000 tokens Published context for this deprecated release GPT-4o official model documentation |
| Maximum output | 16,384 tokens Published maximum output, bounded by the remaining context GPT-4o official model documentation |
| Provider status | Deprecated in the current OpenAI model catalog; confirm remaining account access.GPT-4o official model documentation |
Related models
- GPT-4o Mini
OpenAI ยท GPT-4o
GPT-4o Mini is a deprecated small model for focused text and image tasks.
Launch date not confirmedDeprecated API; check access detailsAPI