Virtual poolant:ocr

ANT OCR

Document text extraction via the OCR bridge.

Try in Playground
OCR bridge: Bypasses chat routing

How this pool routes

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.

Best For

Document extractionScanned PDFsReceipt and form parsing

Where requests went

Live routing over the last 30 days

Requests

83

Success rate

0%

Avg latency

1ms

ant:ocrUnknown100% · 83

Quick Start

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)

Routing weights

Speed50/100
Quality90/100
Cost50/100

Selection criteria

OCR bridgerequiredBypasses chat routing
Speed weight50/100
Quality weight90/100
Cost weight50/100
Model IDant:ocr

Other pools

Every virtual pool accepts the same request shape — swap the model id to change the routing policy.

Browse all virtual models →