Quickstart for Ollama NSFW users

Prerequisites and Authentication

You need an API key and the base URL to start. Sign up on the Get API key page using Google or email. Your key appears immediately; no card is required for the trial. The base URL is https://api.ollamansfw.com/v1. Set this in your environment or SDK config. The model identifier is uncensored. It is an open-weight model running on our servers, distinct from GPT or other vendor models.

Your First Request

Send a standard chat completion request. The API expects a messages array with a role and content. Use curl to test connectivity. Replace YOUR_API_KEY with your actual key. The response returns the generated text in choices[0].message.content. If you get a 401, check your key. A 402 means you need credit.

Python SDK Integration

Use the official openai Python package. Install it via pip. Configure the client with the custom base URL and API key. This ensures compatibility with our endpoint. The code below demonstrates a simple text generation. It handles the request and prints the result. Error handling should catch HTTP exceptions. This approach works for any OpenAI-compatible client.

Node.js SDK Integration

Install the openai Node.js package. Set the base URL and API key in the client initialization. The structure mirrors the Python example. Pass the model ID uncensored. The response contains the completion data. Use async/await for clean code. This method is ideal for server-side applications or CLI tools that need direct API access.

Streaming Responses

Enable streaming by setting stream: true. The API returns a server-sent events (SSE) stream. Each chunk contains partial text. The final chunk includes token usage statistics. This reduces perceived latency for long responses. Handle stream errors gracefully. The SDKs provide built-in stream iterators. Process each chunk to update the UI in real time.

Limits, Errors, and Context

The context window is 100,000 tokens total. Output can run to the end of the window. Rate limits are 300 requests per minute. Concurrent requests are limited to 8 per key. Request bodies must be under 8 MB. Common errors: 401 (invalid key), 402 (insufficient credit), 429 (rate limit). Errors do not consume credit. Refusals for unlawful content are free. Credit never expires.

cURL

Copycurl https://api.ollamansfw.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."}]
  }'

Python

Copyfrom openai import OpenAI

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