API Quickstart: Chat Completions

Authentication & Base URL

Your API key authenticates every request. Use the Authorization header with the Bearer scheme. Your base URL is https://api.nsfwopenrouter.com/v1. This URL works with any OpenAI-compatible SDK. You do not need a subscription. You pay only for tokens used. Errors and refusals incur no charge. Sign up via Google or email to receive your key instantly.

Sending a Chat Completion Request

Send a POST request to /v1/chat/completions. The model ID is always uncensored. Provide your system prompt to define behavior. Include user messages in the messages array. The API returns text output directly. No complex routing occurs. Traffic goes straight to our servers. This ensures consistent NSFW handling without upstream filters.

Handling Streaming Responses

Enable streaming by setting stream to true. The API returns Server-Sent Events (SSE). Each chunk contains partial text. Token usage details appear in the final chunk. This reduces perceived latency for users. It allows real-time display of generated content. Handle errors within the stream logic. Discard incomplete chunks on failure.

Configuring Model Parameters

Adjust temperature for creativity. Use top_p for nucleus sampling. Set max_tokens to limit output length. The default max is 2,048 tokens. You can request up to 16,000 tokens per request. The context window supports 100,000 tokens total. This includes both prompt and completion. Fine-tune these settings for your specific roleplay needs.

Enforcing JSON Mode

Use response_format with {"type": "json_object"}. The model guarantees valid JSON output. This structure is essential for programmatic integration. Parse the response directly into your application objects. Avoid regex parsing for reliability. This feature ensures consistent data extraction. It works seamlessly with standard SDKs.

Understanding Tool Calls

Define tools in the request body. The model can return structured function calls. Use tool_choice to force specific behaviors. This enables dynamic agent workflows. The API supports standard OpenAI tool formats. Parse the tool_calls array in the response. Execute functions and feed results back. This allows complex multi-step interactions.

cURL

Copycurl https://api.nsfwopenrouter.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Run my unit tests and show results"}]
  }'

Python

Copyfrom openai import OpenAI

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