Skip to content

Images

Image input supports PNG, JPEG, and WebP: at most four images per prompt, with a 10 MB source-file limit and decoded Base64 limited to 5 MiB. Use startup --image (repeatable) or TUI image paste:

Terminal window
one run "describe this diagram" --image diagram.png
one --mode text "describe this diagram" --image diagram.png

Images are transient for the current turn and are not persisted in session JSONL. Errors and events use only source basenames. Vision-incapable models reject images before an HTTP request. ChatGPT/Codex vision-capable models send native Responses API input_image parts; invalid or missing blobs fail explicitly.

TUI, text/json, and one run accept startup --image; RPC accepts startup images and prompt attachments. read_image is a runtime tool the agent can call during its turn to inspect a file; it is not a startup image-input channel for --mode text or one run. Steering and follow-up messages are text-only.