Extract text from images using OCR-capable vision models.
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
The OCR-specialized vision model to use for text extraction.
"Hunyuan/Hunyuan-OCR-1B"
Chat-style input containing text instructions and image content for OCR processing.
Maximum number of tokens to generate in the OCR response.
Sampling temperature for text extraction (lower = more deterministic).
Nucleus sampling parameter for OCR output.
Whether to stream OCR output incrementally.