Omni-era GPT for multimodal chat, practical coding, and general assistants
Details
| Field | Value |
|---|---|
| id | gpt-4o |
| family | gpt |
| modality | text+image+pdf->text |
| context_length | 128000 |
| max_output_tokens | 16384 |
| knowledge_cutoff | 2023-09 |
| release_date | 2024-05-13 |
| is_open_weights | no |
| supports_tool_call | yes |
| supports_reasoning | no |
| supports_structured_output | yes |
| supports_attachment | yes |
| input_modalities | text, image, pdf |
| output_modalities | text |