Quickstart: Integrate Our Cheap AI API

Authentication & Base URL

To use our cheap ai api, you need an API key from your dashboard. All requests target the base URL https://api.cheapaiapis.com/v1. This ensures compatibility with existing OpenAI SDKs and clients.

Include your key in the Authorization header as a Bearer token. If the key is invalid, you will receive a 401 error. If your prepaid credit is exhausted, you get a 402 error. Register at Get API key to receive your token immediately.

The model identifier for our uncensored LLM is simply "uncensored". This single model handles all text generation tasks without routing overhead.

Copycurl https://api.cheapaiapis.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Write a blunt product review of a cheap VPN."}]
  }'

Standard Chat Completions

The chat completions api endpoint accepts POST requests with a messages array. Each message requires a role (system, user, or assistant) and content. This structure allows for multi-turn conversations or single-shot prompts.

Our infrastructure processes text input and returns text output efficiently. The model is tuned for flexibility, handling diverse topics without unnecessary refusals for lawful adult content. Request bodies are limited to 8 MB.

Use the Python SDK to integrate quickly. The client automatically handles serialization and HTTP requests.

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.cheapaiapis.com/v1", api_key="YOUR_KEY")

resp = client.chat.completions.create(
    model="uncensored",
    messages=[{"role": "user", "content": "Summarise this thread without softening it."}],
)
print(resp.choices[0].message.content)

Streaming Responses (SSE)

For applications requiring real-time feedback, enable streaming by setting stream: true. The API returns Server-Sent Events (SSE) containing partial token chunks.

This approach reduces perceived latency for end-users. You process each chunk as it arrives, assembling the final response. Streaming works with all standard OpenAI-compatible clients configured for SSE.

Be mindful of the 300 requests per minute limit per key. Streaming does not bypass rate limits; it only changes how data is delivered.

Copystream = client.chat.completions.create(
    model="uncensored",
    messages=[{"role": "user", "content": "Tell the story in second person."}],
    stream=True,
)
for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)

Function Calling Support

Our function calling api implementation allows you to define tools in the request. The model returns structured JSON matching your schema, enabling programmatic actions.

Define functions with names, descriptions, and parameter schemas. The API responds with tool calls that you execute, then pass results back to the model for a final answer. This keeps logic separate from generation.

Ensure your function definitions are valid JSON. Errors in schema structure may cause the model to return malformed tool calls.

Model Listing & Tokens

Use GET /v1/models to retrieve available models. You will see the "uncensored" model listed with its specific capabilities.

The model supports a 100,000 token context window, combining prompt and completion tokens. This allows for extensive document processing or long conversations without immediate truncation.

Pricing is transparent: $0.25 per 1M input tokens and $1.00 per 1M output tokens. Credits never expire, so you pay only for what you use.

Limits, Errors & Context

Monitor your usage via the dashboard. The API enforces a 300 requests per minute limit per key. Exceeding this results in a 429 error. Regenerate your key if needed to reset state.

Common errors include 401 (invalid key), 402 (insufficient funds), and 429 (rate limit). Always handle these gracefully in your client code.

Context window limits apply to the total tokens sent and received. Plan your prompt structure to maximize the 100k limit efficiently.

Node.js

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.cheapaiapis.com/v1", apiKey: process.env.API_KEY });

const resp = await client.chat.completions.create({
  model: "uncensored",
  messages: [{ role: "user", content: "Draft a villain monologue for my game." }],
});
console.log(resp.choices[0].message.content);