SubQ developer documentation

Context12M

context for large codebases, long documents, and agent state in one request.

Speed150

tokens per second for interactive long-context products and agents.

Cost1/5

the cost of other leading LLMs for long-context inference.

Drop-in API

Keep the OpenAI SDK. Change the base URL.

Use the same Chat Completions request shape your app already sends, then call the SubQ API.

POST/v1/chat/completions

import OpenAI from "openai";

const client = new OpenAI({
apiKey: process.env.SUBQ_API_KEY,
baseURL: "https://api.subq.ai/v1",
});

const completion = await client.chat.completions.create({
model: "subq-preview",
messages: [{ role: "user", content: "Hello World" }],
stream: true,
});

01Start with the API shape

Base URL, compatibility boundaries, and how SubQ fits into an existing Chat Completions integration.

02Authenticate securely

Create an API key, send it as a bearer token, and keep credentials out of source control.

03Create chat completions

Supported fields, message formats, response shapes, streaming, and generated snippets.