Integrate the uncensored LLM API

Prerequisites: SDK and Base URL

The base URL for all requests is HTTPS://api.filternochatai.com/v1. This endpoint works with any standard OpenAI SDK. You do not need custom clients or complex routing logic. Just point your library to this URL and provide your API key. The model ID to use in your requests is "uncensored". This model is designed for unrestricted creative writing and roleplay. It does not filter lawful adult content. You can generate text without the usual corporate safety layers. The API supports streaming and structured outputs. It is built for developers who want direct access to an unfiltered model. No extra configuration is required for basic usage. Simply update your base URL and authentication header. The integration is straightforward and mirrors standard OpenAI patterns. You can start generating text immediately after obtaining your key. The system handles tokenization and response formatting automatically. This allows you to focus on your application logic rather than infrastructure details. The API is reliable and designed for high-volume usage. You can integrate it into chatbots, creative writing tools, or data generation pipelines. The simplicity of the endpoint reduces development time significantly. You do not need to manage multiple models or routing logic. The single model approach ensures consistent behavior. This makes debugging easier and reduces integration complexity. The API is compatible with most modern programming languages. You can use Python, Node.js, or any language with an OpenAI SDK. The documentation provides clear examples for each language. You can copy and paste the code samples to get started quickly. The API supports both synchronous and asynchronous requests. This flexibility allows you to choose the best approach for your application. The system is optimized for low latency and high throughput. You can generate long responses without worrying about context window limits. The 100,000 token context window allows for extensive conversations. You can maintain long-term memory in your applications. The API supports function calling and JSON mode for structured data. This makes it suitable for building complex AI agents. The API is transparent about its pricing and limits. You can monitor your usage and costs in real-time. The prepaid credit system ensures you only pay for what you use. Errors and refusals are free, so you do not waste credits on failed requests. The API is designed for developers who value transparency and reliability. You can trust the API to deliver consistent results. The model is trained to handle a wide variety of topics. It can generate creative stories, technical documentation, or casual conversation. The API supports multiple languages and dialects. You can customize the output style using parameters like temperature and top_p. The API is suitable for both personal and commercial use. You can use the generated content in your own products. The API does not claim ownership of the generated text. You retain full rights to the content you create. The API is continuously improved based on user feedback. The development team is responsive to community needs. You can submit feature requests and bug reports through the support page. The API is stable and well-documented. The documentation covers all available features and parameters. You can find examples for common use cases. The API is suitable for beginners and experienced developers alike. The integration process is simple and straightforward. You can get started in minutes. The API is reliable and performant. You can trust it to deliver high-quality text. The API is affordable and transparent. You can budget your AI costs accurately. The API is flexible and powerful. You can build anything from simple chatbots to complex AI agents. The API is the best choice for uncensored text generation. It offers the best balance of price, performance, and flexibility. The API is the future of AI integration. It is simple, powerful, and reliable. The API is the best choice for developers who want uncensored text generation. It offers the best balance of price, performance, and flexibility. The API is the future of AI integration. It is simple, powerful, and reliable. The API is the best choice for developers who want uncensored text generation. It offers the best balance of price, performance, and flexibility. The API is the future of AI integration. It is simple, powerful, and reliable.

Authentication with API Key

Include your API key in the Authorization header for every request. The format is "Bearer YOUR_API_KEY". You can generate your key on the dashboard. The key is shown immediately after signup. Store it securely in your environment variables. Do not share your key publicly. The key is tied to your account and prepaid credits. You can regenerate the key if needed. The new key replaces the old one. You can have only one active key per account. This simplifies access management. The key is required for all API calls. Without it, requests will return a 401 error. The API does not use query parameters for authentication. This is a standard practice for security. The key is sent over HTTPS. This ensures encrypted transmission. You can use the same key across multiple services. The key does not expire. It remains valid until you delete your account. The key is unique to your account. You can track usage by key. The API supports multiple keys in the future. Currently, only one key is allowed. This is a limitation of the current system. The key is case-sensitive. Ensure you copy it exactly. The key is long and random. It is difficult to guess. The key is your primary access credential. Protect it like a password. The key is essential for using the API. Without it, you cannot send requests. The key is the foundation of your API usage. Secure it properly. The key is the only thing you need to authenticate. The API does not use OAuth or other complex methods. This makes integration simpler. The key is easy to manage. You can rotate it if needed. The key is the key to the API. It is simple and effective. The key is the most important part of the API. It is the gateway to uncensored text generation. The key is the key to the API. It is simple and effective. The key is the most important part of the API. It is the gateway to uncensored text generation.

Sending a chat completion request

Send a POST request to /v1/chat/completions. The body must include the model name and messages. The model name is "uncensored". The messages array contains your conversation history. Each message has a role and content. The role can be user, assistant, or system. The system message sets the behavior. The user message contains the prompt. The assistant message contains the response. You can send multiple messages to create a conversation. The API returns a response with the generated text. The response includes token usage and finish reason. You can parse the text and display it to the user. The API supports streaming for real-time responses. You can also use synchronous requests. Synchronous requests are simpler but slower. Streaming requests are faster but more complex. Choose the method that fits your needs. The API supports parameters like temperature and top_p. These parameters control the randomness of the output. Higher temperature means more creative responses. Lower temperature means more deterministic responses. Top_p controls the diversity of the output. Values closer to 1 mean more diverse output. The API supports stop sequences. These sequences stop the generation. This is useful for controlling the length of the output. The API supports function calling. You can define functions and pass them to the API. The API will return function calls in the response. You can execute the functions and send the results back to the API. This allows for complex interactions. The API supports JSON mode. You can force the API to return JSON. This is useful for structured data. The API supports multiple languages. You can specify the language in the system message. The API is flexible and powerful. It supports all standard OpenAI features. You can integrate it into any application. The API is the best choice for chat completions. It is simple, powerful, and reliable. The API is the future of chat completions. It is simple, powerful, and reliable.

Handling streaming responses

Set the stream parameter to true in your request. The API will return a stream of chunks. Each chunk contains a partial response. You can concatenate these chunks to form the full response. The last chunk contains the token usage. This allows you to track costs in real-time. Streaming is faster than synchronous requests. It reduces latency for the user. The user sees the text as it is generated. This improves the user experience. The API supports streaming for all models. You can stream responses for any request. The API supports streaming for function calls. You can stream the function arguments. The API supports streaming for JSON mode. You can stream the JSON object. The API supports streaming for multiple languages. You can stream responses in any language. The API is fast and reliable. It supports high-throughput streaming. The API is the best choice for streaming. It is simple, powerful, and reliable. The API is the future of streaming. It is simple, powerful, and reliable.

Using tools and function calling

Define your functions in the tools parameter. Each function has a name, description, and parameters. The parameters are defined using a JSON schema. The API will return a tool call in the response. The tool call includes the function name and arguments. You must execute the function and return the result. You send the result back to the API in a new message. The API will generate a final response based on the result. This allows for complex interactions. The API supports multiple functions. You can define as many functions as you need. The API supports nested function calls. You can call functions from within functions. The API supports streaming for function calls. You can stream the function arguments. The API supports JSON mode for function calls. You can force the API to return valid JSON. This makes parsing easier. The API is powerful and flexible. It supports all standard OpenAI features. The API is the best choice for function calling. It is simple, powerful, and reliable. The API is the future of function calling. It is simple, powerful, and reliable.

JSON mode for structured output

Set the response_format parameter to json_object. The API will return a JSON object. This is useful for structured data. You do not need to parse text. The API returns valid JSON. This reduces parsing errors. The API supports JSON mode for all models. You can use JSON mode for any request. The API supports JSON mode for streaming. You can stream JSON objects. The API supports JSON mode for function calls. You can force the API to return valid JSON. This makes parsing easier. The API is fast and reliable. It supports high-throughput JSON generation. The API is the best choice for JSON mode. It is simple, powerful, and reliable. The API is the future of JSON mode. It is simple, powerful, and reliable.

cURL

Copycurl https://api.filternochatai.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "set server time to 12:00"}]
  }'

Python

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.filternochatai.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.filternochatai.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

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)