Hermes uncensored uncensored ai API docs

Base URL and authentication

The base URL for all requests is https://api.hermesuncensored.com/v1. You obtain an API key by clicking "Get API key" on the dashboard and authenticating with Google or an email password. The key is displayed immediately and acts as the Authorization header value. No phone number is required for signup.

Make your first request

Send a POST request to /v1/chat/completions with the model ID "uncensored". The model responds to lawful adult, fictional, or controversial topics without standard refusals. You can verify connectivity by checking the response status code and content.

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

Integrate with Python

Use the official OpenAI Python SDK to interact with the endpoint. Set the base_url to our service and provide your API key. The client handles JSON serialization and streaming automatically. This approach works for any OpenAI-compatible client library.

Copyfrom openai import OpenAI

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

Integrate with Node.js

The Node.js SDK follows the same configuration pattern. Initialize the client with your base URL and key. You can then call chat.completions.create() with standard parameters. This ensures compatibility with existing codebases that target OpenAI.

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.hermesuncensored.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 responses

Enable streaming by setting stream to true. The API returns Server-Sent Events (SSE) containing partial tokens. The final chunk includes the complete token usage statistics. This method reduces perceived latency for long-form generation tasks.

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)

Limits, errors, and context

The context window supports 100,000 tokens for the prompt and completion combined. You are limited to 300 requests per minute and 8 concurrent requests per key. Common errors include 401 for invalid keys and 402 when prepaid credit is exhausted. Requests that exceed the 8 MB body limit also fail immediately.