API documentation for developers

Authentication and base URL setup

Start by configuring your client with the correct base URL and key. Our API lives at HTTPS://api.llamaapikey.com/v1. This setup works with the official OpenAI SDKs and any compatible client. You only need to change the base URL and provide your key. We do not use model routing or vendor lock-in.

• Base URL: HTTPS://api.llamaapikey.com/v1
• Model ID: "uncensored"
• Auth: Header Authorization: Bearer YOUR_API_KEY

Copycurl https://api.llamaapikey.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Generate API key for llama model usage"}]
  }'

Sending requests to /v1/chat/completions

Send a standard POST request to the chat completions endpoint. The model ID is "uncensored". It handles text in and text out efficiently. You can adjust parameters like temperature or top_p. Errors do not consume credit. Refusals for standard content are free.

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.llamaapikey.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 via SSE

Enable streaming by setting stream: true. You receive Server-Sent Events (SSE) for real-time output. The last chunk contains the token usage details. This approach is ideal for chat interfaces. You get immediate feedback without waiting for the full response.

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 and tool use

Use the standard tools format for function calling. Define your functions in the tools array. The model supports tool_choice for forced execution. You can also enforce JSON mode with response_format. This ensures structured outputs for your applications.

Copyimport OpenAI from "openai";

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

JSON mode and response formatting

Force the model to output valid JSON. Set response_format to {"type": "json_object"}. This prevents malformed responses in your parser. It works alongside function calling. You get reliable data structures for your backend logic.

Copycurl https://api.llamaapikey.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Generate API key for llama model usage"}]
  }'

Understanding token usage and billing

You pay for real token usage. Errors and refusals are free. The context window is 100,000 tokens. Max output is 16,000 tokens. Rate limit is 300 requests per minute. Handle 401 for invalid keys. Handle 402 for no credit. Handle 429 for rate limits.

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)