API Documentation: Chat Completions

Base URL and Authentication

Start every request with our base URL and include your API key in the authorization header.

Use https://api.unlimitedtokens.cc/v1 as your base URL. Pass your key as Bearer YOUR_API_KEY. No subscription locks your access. Prepaid credit powers every call. Errors and refusals cost nothing. Your credit never expires. Generate keys via Google or email on the dashboard.

Chat Completions Endpoint

Send text prompts to POST /v1/chat/completions and receive text responses.

This endpoint handles all standard interactions. The model ID is always uncensored. It accepts messages with roles like user or assistant. No embeddings or image generation here. Just pure text input and output. Configure parameters like temperature and stop sequences. You control the output style.

Copycurl https://api.unlimitedtokens.cc/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Summarize the core changes in the latest release notes"}]
  }'

Supported Parameters and Options

Control model behavior with standard parameters like temperature and top_p.

Set temperature for creativity. Use top_p for nucleus sampling. Define stop sequences to halt generation. Enable json_object for structured data. Tools and function calling are fully supported. Stream responses via SSE. Set a seed for reproducibility. Presence and frequency penalties adjust token repetition. Adjust these to fit your workflow.

Streaming Responses via SSE

Receive tokens in real-time using Server-Sent Events.

Set stream: true in your request. The API sends chunks as they are generated. Each chunk contains partial text and usage data. The final chunk includes total token counts. This reduces perceived latency significantly. It is ideal for chat interfaces. Handle errors gracefully during streaming. Process each delta object as it arrives.

Copyfrom openai import OpenAI

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

Error Handling and Limits

Handle 401, 402, and 429 errors correctly.

A 401 means your key is invalid. Check your dashboard for the correct key. A 402 indicates insufficient credit. Top up via crypto to continue. A 429 signals rate limiting. You are limited to 300 requests per minute. Also, you have a limit of 8 concurrent requests. The request body must stay under 8 MB. Errors do not consume your credit. Refunds are not issued for credit, but double charges are fixed via support.

Copyimport OpenAI from "openai";

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

Context Window and Model Details

The model supports a 100,000 token context window.

This window covers both prompt and completion. You can generate up to 16,000 tokens per request. If you do not set max_tokens, the default is 2,048. This allows for long-form content generation. The model is uncensored and open-weight. It does not refuse lawful adult content. It is not GPT, Claude, or any other vendor model. It runs on our servers. Use it for unlimited vibes and deep context.

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)