Quickstart Guide

Prerequisites: SDK and Base URL

Start by installing your preferred SDK. We are an independent service, so configure your client to point at our base URL instead of the default vendor endpoint.

• Base URL: https://api.apillama.cc/v1
• Model ID: uncensored
• Authentication: Bearer token via Authorization header

This configuration works with any library that speaks the OpenAI protocol. You do not need a specific version, just ensure your client supports standard HTTP headers.

Authentication with API Key

Your API key authorizes all requests to the endpoint. Generate it from the dashboard by selecting "Continue with Google" or using email and password.

The key is displayed immediately after creation. Store it securely because it provides full access to your prepaid credit. Requests without a valid key receive a 401 error.

Sending Your First Completion

Send a standard chat completion request to receive a text response. The model processes your input and returns the continuation without content refusals for lawful adult topics.

Copycurl https://api.apillama.cc/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "fix syntax error in python script"}]
  }'

This endpoint accepts standard parameters like temperature and top_p. Adjust these to control creativity or determinism in your output.

Enabling Streaming and Tools

Enable streaming by setting stream: true in your request body. The server returns a server-sent events stream, delivering tokens as they are generated.

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.apillama.cc/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)

You can also define function calling schemas in the tools array. The model will output structured tool calls that your application can execute. This approach works well for complex logic tasks.

Handling JSON Mode Responses

Force structured output by setting response_format to {"type": "json_object"}. This ensures the model returns valid JSON, which is ideal for API integrations.

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.apillama.cc/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);

Combine this with a strict schema in your system prompt. The model adheres to the structure, reducing the need for post-processing validation in your code.

Monitoring Token Usage

Track token consumption in the final chunk of a streaming response. Each chunk includes usage data, allowing you to calculate costs in real time.

Pricing is $0.15 per million input tokens and $0.50 per million output tokens. Errors do not consume credits. Refusals based on the hard content limit are free. Monitor your balance to avoid unexpected stops.

Streaming

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)