API Documentation

Quickstart: Connect in 3 Lines

Our API works exactly like the standard chat-completions interface you already know. Simply point your client to our base URL and provide your API key. No complex routing or vendor-specific quirks. We handle the rest.

The base URL for all requests is https://api.toolsaiuncensored.com/v1. You can use any official OpenAI SDK or compatible library by updating the base URL configuration. Authentication relies on a single bearer token provided via the Authorization header. This ensures seamless integration with your existing stack.

Copycurl https://api.toolsaiuncensored.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "run unit tests on the legacy auth module"}]
  }'

Endpoints: Chat Completions & Models

We expose only the essential endpoints for text generation. The POST /v1/chat/completions endpoint processes your prompts and returns generated text. Use GET /v1/models to verify the available model ID. We do not offer embeddings, image generation, audio processing, or fine-tuning services. Keep your infrastructure simple.

The model ID you must send is uncensored. This is our own tuned open-weight model, not a resold GPT or Claude instance. It answers directly without content filters for lawful adult use. Check the endpoint documentation for specific payload structures.

Copyfrom openai import OpenAI

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

Parameters: Temperature, Top P, and Seed

Control the creativity and determinism of your outputs using standard parameters. Adjust temperature to vary randomness. Set top_p to limit nucleus sampling. Use seed for reproducible results. These tools give you precise control over the text generation process.

You can also set presence_penalty and frequency_penalty to influence token repetition. The stop parameter allows you to define custom termination sequences. This level of control ensures the output matches your specific use case. Configure these values in your request body.

Copyimport OpenAI from "openai";

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

Streaming & JSON Mode

Receive responses in real-time using Server-Sent Events (SSE). Streaming reduces perceived latency significantly. Each chunk includes token usage data in the final event. This allows for accurate billing tracking during long generations.

For structured data, enable JSON mode by setting response_format to {"type": "json_object"}. The model will attempt to output valid JSON. This is ideal for programmatic pipelines. Combine streaming with JSON mode for efficient, structured data extraction without parsing errors.

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

Define tools in your request to let the model call functions dynamically. Specify tools and tool_choice to control execution. The model returns tool calls in the response stream. This enables complex workflows and agent-like behavior.

Pass the function definitions in the messages array. The model will invoke the appropriate tool based on your prompt context. You can then execute the function locally and feed the result back into the conversation. This supports advanced automation patterns.

Rate Limits & Constraints

Your API key allows 300 requests per minute. You can run 8 concurrent requests simultaneously. The maximum request body size is 8 MB. Each key is tied to one account; generating a new key replaces the old one.

The context window supports 100,000 tokens total, including both input and output. The maximum output per request is 16,000 tokens. If you do not specify max_tokens, the default limit is 2,048 tokens. Monitor your usage to stay within these bounds.