Extract Text From Image
extract_text_from_imageExtract text from images with OCR: screenshots, documents, terminal output, logs, code snippets, forms, and UI text.
Instructions
OCR for screenshots, documents, terminal output, logs, code snippets, forms, and UI text.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"image": "<image>"
},
"name": "extract_text_from_image"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| image | Yes | Image source. Supports local file path, http(s) URL, or data:image/...;base64,... Data URL. | |
| model | No | Optional StepFun vision model override. | |
| detail | No | StepFun vision detail level. Use high for OCR, screenshots, UI, diagrams, and charts. | |
| question | No | Optional user question or task for this image. If omitted, the tool uses its scenario-specific default task. | |
| max_tokens | No | Optional maximum output tokens. |