- Documentation
- Advanced
Query API
The /query
endpoint enables you to ask natural language questions about images and receive detailed answers. This is also known as Visual Question Answering (VQA).
Endpoint
POST https://api.moondream.ai/v1/query
Request Format
Parameter | Type | Required | Description |
---|---|---|---|
image_url | string | Yes | Base64 encoded image with data URI prefix (e.g., "data:image/jpeg;base64,..." ) |
question | string | Yes | The natural language question to ask about the image |
stream | boolean | No | Whether to stream the response token by token (default: false ) |
Response Format
For non-streaming responses:
{
"request_id": "2025-03-25_query_2025-03-25-21:00:39-715d03",
"answer": "Detailed text answer to your question..."
}
For streaming responses, you'll receive a series of data events:
{data: {"chunk": "Part of the", "completed": false, "request_id": "2025-03-25_query_123456"}
{data: {"chunk": " answer being", "completed": false, "request_id": "2025-03-25_query_123456"}
{data: {"chunk": " generated.", "completed": false, "request_id": "2025-03-25_query_123456"}
{data: {"completed": true, "chunk": "", "org_id": "a349504c-8006-54f3-8862-ba0c41d2b4d7", "request_id": "2025-03-25_query_123456"}
Examples
import moondream as md
from PIL import Image
# Initialize with API key
model = md.vl(api_key="your-api-key")
# Load an image
image = Image.open("path/to/image.jpg")
# Ask a question
result = model.query(image, "What's in this image?")
answer = result["answer"]
request_id = result["request_id"]
print(f"Answer: {answer}")
print(f"Request ID: {request_id}")
# Stream the response
stream_result = model.query(image, "What's in this image?", stream=True)
for chunk in stream_result["chunk"]:
print(chunk, end="", flush=True)
Tips for Effective Questions
Best Practices
- Ask specific questions rather than general ones
- One question at a time yields better results than multiple questions
- For complex scenes, try to focus on particular areas or objects
- If you want detailed answers, explicitly ask for details in your question
Error Handling
Common error responses:
Status Code | Description |
---|---|
400 | Bad Request - Invalid parameters or image format |
401 | Unauthorized - Invalid or missing API key |
413 | Payload Too Large - Image size exceeds limits |
429 | Too Many Requests - Rate limit exceeded |
500 | Internal Server Error - Server-side issue |
Error Response Format
Error responses are returned in the following format:
{
"error": {
"message": "Detailed error description",
"type": "error_type",
"param": "parameter_name",
"code": "error_code"
}
}
Limitations
- Maximum image size: 10MB
- Supported image formats: JPEG, PNG, GIF (first frame only)
- Maximum question length: 512 characters
- Rate limits apply based on your plan