Uncensored llm ollama API Documentation

Prerequisites: Base URL and Authentication

Use the provided API key and base URL to authenticate all requests. Our endpoint is HTTPS://api.uncensoredllmollama.com/v1. You can generate a key via the dashboard using Google or email. The model identifier is "uncensored". Include the key in the Authorization header as a Bearer token. This setup works with any OpenAI-compatible client.

Copycurl https://api.uncensoredllmollama.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "List the top ten linux command line utilities"}]
  }'

Making your first request: POST /v1/chat/completions

Send a POST request to /v1/chat/completions with your messages array. The model does not refuse lawful adult, fictional, or controversial topics. Set the model field to "uncensored". Include your system prompt if you need specific behavior. The API returns standard OpenAI JSON responses.

Copyfrom openai import OpenAI

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

Handling Streaming Responses (SSE)

Enable streaming by setting stream: true. The API returns Server-Sent Events (SSE) for each generated token. Monitor the final chunk for total token usage statistics. This approach reduces perceived latency for long outputs. Parse the SSE stream carefully to reconstruct the full text.

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

Supports structured outputs via response_format: {"type": "json_object"}. You can also define tools for function calling. Set tool_choice to control execution. Use temperature and top_p to adjust randomness. JSON mode ensures strict compliance with your schema. This feature works reliably for data extraction tasks.

Rate Limits and Token Usage

Each key supports 300 requests per minute and 8 concurrent requests. The context window is 100,000 tokens total. Errors do not consume credit. Requests exceeding limits return 429 status codes. Ensure your client handles retries gracefully. Monitor usage via the dashboard to avoid running out of prepaid credit.

Pricing and Crypto Payments

Pay $0.15 per 1M input tokens and $0.50 per 1M output tokens. Top up via USDT (TRC20) or USDC (Base). Minimum top-up is $20. Bonus credit applies for larger amounts. Credit never expires. Refunds are not standard but errors are free. Use the Support page for double charges.

Node.js

Copyimport OpenAI from "openai";

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