Llama API: First request in five minutes

llamaapis.com

Installation

Start by installing the official OpenAI Python client. It handles the HTTP requests and JSON parsing for you.

• pip install openai

You can also use the JavaScript SDK for Node.js. Both libraries are fully compatible with our API because we follow the OpenAI chat-completions specification exactly.

Authentication Setup

Our API uses standard API key authentication. After signing up at https://llamaapis.com, you receive a key immediately. No credit card is required for the trial tier.

Store this key in an environment variable or pass it directly to your client. The key authenticates all requests to the /v1 endpoints. If you lose your key, you can regenerate it from your dashboard, which invalidates the old one immediately.

Basic Chat Completion Request

Make a request to the chat completions endpoint. You must set the base URL to our server and provide your API key.

The model ID is uncensored. This model does not apply standard content filters for lawful adult use.

Here is how you make a simple request using curl:

Copycurl https://api.llamaapis.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."}]
  }'

The response returns a generated text string. If you need function calling, the structure is identical to OpenAI's format.

Streaming Responses (SSE)

For real-time output, enable streaming by setting stream: true. The server sends Server-Sent Events (SSE) containing partial deltas.

This is useful for chat interfaces where you want to show text as it is generated. The context window supports up to 100,000 tokens, so streaming works efficiently even for long conversations.

Example streaming implementation:

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)

Remember to handle the stop event to close the connection cleanly.

Tool/Function Calling Support

Our API supports structured tool calling. Define your functions in the tools parameter and set the model to respond with function calls.

The client library will parse the JSON arguments automatically. This works exactly as documented in the OpenAI specification.

Example using the Python SDK:

Copyfrom openai import OpenAI

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

The model will return the function name and arguments. You execute the function and send the result back in the next message.

Limits, Errors, and Context

Be aware of the following limits:

• Rate limit: 300 requests per minute per API key.
• Max request body: 8 MB.
• Context window: 100,000 tokens total (input + output).

Common errors:

• 401 Unauthorized: Invalid or missing API key.
• 402 Payment Required: Insufficient prepaid credit.
• 429 Too Many Requests: You exceeded the 300 rpm limit.

We do not offer embeddings, image generation, or audio processing. This is a text-only LLM API.

Node.js

Copyimport OpenAI from "openai";

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