Integrate the uncensored LLM API

Base URL and Authentication

Use the provided base URL and API key for all requests. The endpoint is https://api.howtomakechatgptunfiltered.com/v1. Pass your key in the Authorization header as a Bearer token. This standard format lets you swap in our service without changing your client code. You get an API key immediately after signing up with Google or email. No phone number is required.

Copycurl https://api.howtomakechatgptunfiltered.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "calculate total tokens for input array"}]
  }'

Errors like 401 indicate an invalid key, while 402 means you need more credit. Your key is active as soon as you see it on the dashboard.

POST /v1/chat/completions Parameters

Send your prompts to the chat completions endpoint with standard parameters. Use model: "uncensored" to select the model. The context window is 100,000 tokens for prompt and completion combined. You can set temperature, top_p, and stop sequences. Max output is 16,000 tokens per request. Set max_tokens to avoid unexpected truncation. JSON mode is available via response_format. Function calling works with tools. Parameters like presence_penalty and frequency_penalty help control repetition. Seed values ensure reproducible outputs.

Streaming Responses and Token Counting

Enable streaming by setting stream: true in your request. The API returns Server-Sent Events (SSE) for real-time token delivery. Token usage details appear in the final chunk of the stream. This allows you to track costs and context usage accurately. Streaming reduces perceived latency for long responses. It is ideal for chat interfaces. You can parse partial tokens for instant display. The last chunk contains the complete usage statistics. This transparency helps you monitor API consumption.

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 JSON Mode

Use function calling to integrate external tools. Define tools in the tools parameter. The model returns a function call object for your code to execute. Set tool_choice to auto or specify a tool. JSON mode enforces structured output. Set response_format to {"type": "json_object"}. This ensures valid JSON for parsing. It is useful for data extraction. Function calling supports complex workflows. The model handles tool arguments automatically. JSON mode prevents formatting errors. Both features work with the uncensored model. They integrate with standard OpenAI SDKs.

Error Handling and Rate Limits

Handle errors gracefully with standard HTTP status codes. 401 means your API key is invalid. 402 indicates insufficient prepaid credit. 429 signals that you hit the rate limit. The limit is 300 requests per minute per key. You can have 8 concurrent requests. The request body must be under 8 MB. Errors and refusals do not consume credit. Refunds are not available for used credit. Double charges are fixed via Support. Each account gets one active key. A new key replaces the old one. Always check the status code.

GET /v1/models Endpoint

Query available models with a GET request. The endpoint is /v1/models. It returns a list of model objects. Our service offers one model: uncensored. This confirms the API is working. Use this endpoint for health checks. It returns metadata about the model. The model ID is always uncensored. This standard endpoint ensures compatibility. It works with any OpenAI-compatible client. You can verify connectivity quickly. It is useful for automated tests. The response includes the model name and ID.

Python

Copyfrom openai import OpenAI

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

Node.js

Copyimport OpenAI from "openai";

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