Iymau API Documentation

Authentication and API keys

Your API key authenticates every request. Sign up with Google or email to receive a single active key immediately. Keep this key secure, as it acts as your password for the service. If you lose it, generate a new one to replace the old active key. The system charges by real token usage, so errors and refusals are free. You can top up with crypto at any time.

Copycurl https://api.iyamau.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "What is the capital of France?"}]
  }'

First request with the chat completions endpoint

Send a POST request to the chat completions endpoint to generate text. Use the base URL provided on the dashboard to ensure compatibility with standard clients. The model identifier is always "uncensored" for this dedicated service. You can adjust parameters like temperature and top_p to control creativity. The system accepts standard JSON payloads for prompts and messages. Errors do not consume your prepaid credit. This approach works with any OpenAI-compatible SDK you prefer.

Copyfrom openai import OpenAI

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

Integration with Node.js clients

Use the official Node.js SDK or any compatible library to interact with the API. Configure the client with your base URL and API key. The uncensored model responds to standard message formats. You can send multiple turns in a single request for conversational context. The response object contains the generated text and usage statistics. Streaming is supported for real-time token delivery. This method ensures low latency for your applications. The service handles the heavy lifting on our servers.

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.iyamau.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 responses and SSE

Enable streaming by setting the stream parameter to true. You receive Server-Sent Events (SSE) for each token generated. This allows for immediate display of text as it is produced. The final chunk contains the total token usage for the request. This feature is ideal for chat interfaces and live applications. It reduces perceived latency for end users. You can parse the JSON objects in each SSE event. The uncensored model supports this standard protocol efficiently.

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)

Parameters: temperature, top_p, and JSON mode

Control generation behavior with standard parameters. Set temperature to adjust randomness, with higher values increasing creativity. Use top_p to filter the vocabulary distribution. Enable JSON mode by setting response_format to json_object for structured data. The uncensored model adheres to these constraints reliably. You can also specify stop sequences to halt generation early. Seed values allow for reproducible results during testing. These options give you precise control over the output quality.

Rate limits, quotas, and common errors

The API enforces a limit of 300 requests per minute per key. You can have up to 8 concurrent requests active at once. Each request body must not exceed 8 MB. If you receive a 401 error, check your API key validity. A 402 error indicates insufficient prepaid credit; top up via crypto to continue. A 429 error means you have hit the rate limit. Wait a few seconds before retrying. The context window supports 100,000 tokens total. This allows for extensive document processing or long conversations.