Introduction

The Cemented Grounded Search API runs a Plan → Collect → Process → Analyze pipeline against the live web and returns a cited answer in the OpenAI Responses API shape. It is wire-compatible with the official OpenAI SDKs — point your client at https://www.cemented.ai/v1, swap the model name for sonnet or opus, and existing code that calls /v1/responses keeps working.

Make your first call

Provision a key in the dashboard, then drop your existing OpenAI client onto Cemented:

Python

from openai import OpenAI

client = OpenAI(
    api_key="ck-...",
    base_url="https://www.cemented.ai/v1",
)

response = client.responses.create(
    model="sonnet",
    input="What did NVIDIA report in its latest 10-Q?",
    extra_body={"vendor_events": False},
)

print(response.output_text)

TypeScript

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "ck-...",
  baseURL: "https://www.cemented.ai/v1",
});

const response = await client.responses.create({
  model: "sonnet",
  input: "What did NVIDIA report in its latest 10-Q?",
  // @ts-expect-error — Cemented-specific extension
  vendor_events: false,
});

console.log(response.output_text);

response.output_text in these examples is an OpenAI SDK convenience accessor assembled from the response’s output-message content. The raw HTTP response has no top-level output_text field; clients using fetch should read the text property from an output_text content part in response.output.

vendor_events: false suppresses Cemented-specific stream events so the official SDKs only see what they natively model. Leave it on if you want to surface pipeline progress in your UI.

Next steps

• The API Reference covers authentication, streaming, request shapes, and the /v1/responses schema.
• Working with citations shows how to expand inline [N] markers into footnotes or HTML tooltips.