AI API Quickstart

Authentication

Use your API key in the Authorization header. The key is generated immediately after signup and can be regenerated at any time; regenerating revokes the previous key. Prepaid credit never expires, and keys do not expire independently of your credit balance.

Send requests to the dedicated endpoint:

https://api.aiapisource.com/v1

Authentication is handled via standard bearer token format.

Chat Completions Endpoint

Post to POST /v1/chat/completions with a JSON body containing the model set to uncensored and your messages. The model returns text in response to text input.

• Context window: 100,000 tokens (prompt + completion).
• Request body limit: 8 MB.
• No embeddings, images, or fine-tuning endpoints are available.

Example request:

Copycurl https://api.aiapisource.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Write a blunt product review of a cheap VPN."}]
  }'

Streaming Responses

Add "stream": true to your request to receive Server-Sent Events (SSE). The stream delivers chunks as the model generates text. The stream ends when the model completes the response or encounters an error; the fact sheet does not specify behavior for context limit mid-stream beyond the hard 100,000 token window.

Handle SSE events in your client to accumulate or process partial responses.

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

The API supports tool/function calling. Define functions in the tools parameter. The model may return a tool_calls array in the response. You must execute the functions on your side and send the results back in a subsequent message.

This is standard OpenAI-compatible behavior. No abstraction layers are required.

Copyfrom openai import OpenAI

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

Model Information

The model ID is uncensored. It is an open-weight model run on our own GPU servers, tuned to answer without content refusals for lawful adult use. It is NOT GPT, Claude, Gemini, Grok, DeepSeek, or any other vendor's model.

Check GET /v1/models for available models. Only one model is offered.

Copyimport OpenAI from "openai";

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

Rate Limits and Errors

Limit: 300 requests per minute per key. Hard content limit: no sexual content involving minors.

Common errors:

• 401: Invalid or missing API key. Regenerate if needed.
• 402: Insufficient prepaid credit. Top up from $10.
• 429: Rate limit exceeded (300 req/min).

Prompts are not used for training. No SLA or certifications are claimed.