Sandboxes and headless browse
Compute in a sandbox and fetch pages with a headless browser when the field lives behind a URL, not a scan.
Fiducial lock · deterministic inference
Highest accuracy, precision and consistency for OCR, audio understanding, and structured data extraction.
Official SDKs for TypeScript and Python, and a chat-completions API compatible with every framework out of the box.
Schema in, fields out. Zod (or JSON Schema) describes the document; the model returns typed values with optional bounds and confidence.
import { InferAPI, responseFormat } from "inferapi";
import { z } from "zod";
const client = new InferAPI({ apiKey: "<your-api-key>" });
const IDSchema = z.object({
family_name: z.string().describe("Family name on the specimen"),
given_name: z.string().describe("Given name on the specimen"),
dob: z.string().describe("Date of birth"),
doc_no: z.string().describe("Document number"),
});
const response = await client.chat.completions.create({
messages: [{
role: "user",
content: [
{ type: "text", text: "Extract the details from this ID" },
{ type: "image_url", image_url: { url: "https://inferapi.quest/examples/specimen.jpg" } },
],
}],
response_format: responseFormat(z.toJSONSchema(IDSchema), "id_schema"),
});
Verifiable fields
Every extracted field can carry a value, a confidence score, and bounding boxes — so a downstream system can accept, reject, or send a human the crop.
{
"family_name": {
"value": "QUINN",
"confidence": 0.99,
"bounds": {
"top_left": { "x": 214, "y": 154 },
"bottom_right": { "x": 346, "y": 180 }
}
}
}
Extract and understand text, audio, and images across a wide set of languages. Same schema; local glyphs.
托运单 4418 · 件重 12.4 kg · 目的地 大阪
वेबिल 4418 · वजन 12.4 किग्रा · गंतव्य ओसाका
Guía 4418 · peso 12.4 kg · destino Osaka
送り状 4418 · 重量 12.4 kg · 仕向地 大阪
Compute in a sandbox and fetch pages with a headless browser when the field lives behind a URL, not a scan.
Policy packs for text and images: crime, sexual content, self-harm, PII, and election claims — on or off per key.
Architecture
A hybrid stack: convolutional and domain nets for print, layout, and audio, with a transformer layer for language. Built so the same ID, form, or clip returns the same fields.
| Property | InferAPI |
|---|---|
| Context | Long-context prompts and files |
| Output | Structured JSON or text |
| Input modalities | Text, images, audio, file, video |
| Reasoning | Available when a field needs it |
| Caching | Included |
| Observability & logging | Coming soon |
| Billing | Usage-based inference — request a key |
Bring deterministic accuracy to your workflows. Get an API key — no credit card on the form.