ant:ocrDocument text extraction via the OCR bridge.
ant:ocr does not route through chat completions at all. It bridges to a dedicated OCR backend, extracts the image or document, and returns the result as markdown in an assistant message — so an OpenAI-compatible client gets OCR without a separate integration.
Live routing over the last 30 days
Requests
83
Success rate
0%
Avg latency
1ms
from openai import OpenAI
client = OpenAI(
base_url="https://api.antbase.ai/v1",
api_key="YOUR_ANT_API_KEY",
)
response = client.chat.completions.create(
model="ant:ocr",
messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)Every virtual pool accepts the same request shape — swap the model id to change the routing policy.
Browse all virtual models →