Opensfw API Quickstart Guide

Authentication and Base URL

Start by generating your key on the dashboard. Use the https://api.opensfw.com/v1 base URL and set your API key in the Authorization header. This setup works with any standard OpenAI SDK client.

Making your first chat completion request

Send a POST request to /v1/chat/completions with your model ID and messages. The uncensored model processes your input and returns the generated text. Use the curl example below to verify connectivity.

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

Streaming responses and token usage

Enable streaming by setting stream: true in your request. You receive chunks of text as they generate. The final chunk contains the complete token usage statistics for billing. Use the Python example to handle the stream.

Copyfrom openai import OpenAI

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

Function calling and JSON mode

Define tools in your request for structured outputs. Use response_format: {"type": "json_object"} for strict JSON responses. This works seamlessly with standard function calling parameters.

Copyimport OpenAI from "openai";

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

Handling errors and rate limits

Check for 401 if your key is invalid, 402 for insufficient credit, and 429 for rate limits. You get 300 requests per minute and 8 concurrent requests per key. Errors do not consume tokens.

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)

Understanding context windows and limits

The uncensored model supports a 100,000 token context window. Max output is 16,000 tokens per request. Keep your request body under 8 MB. This ensures consistent performance for large inputs.