Ask questions about a JPEG image using AI-powered vision.
Supported formats: .jpg, .jpeg
Workflow:
/ingest/v1/api/documentfile_id with this endpointBearer token authentication using an API key
The file_id returned from ingest endpoint
"abc123-def456-ghi789"
Your question about the content
"What are the main points discussed in this document?"
Whether to stream the response (SSE format)
AI model to use
gpt-4, gpt-4o, gpt-4o-mini, gpt-3.5-turbo, claude-3-opus, claude-3-sonnet, claude-3.5-sonnet, gemini-1.5-pro, gemini-1.5-flash "gpt-4"
Model provider
openai, anthropic, gemini "openai"
Type of conversation
single, group Maximum output tokens
2000
Successful response
Server-Sent Events stream (when streaming=true)