Hermes API: Switch your client in three lines

Install the OpenAI SDK

Since our endpoint is OpenAI-compatible, you can use the official SDKs you already know. This approach lets you switch from other vendors without rewriting your application logic. We support the standard openai package for Python and Node.js environments.

Ensure you are using a recent version of the SDK to guarantee compatibility with streaming and tool calling features. The client library handles the JSON serialization and HTTP transport automatically, so you can focus on the model parameters rather than network details.

Configure Base URL & Key

Authentication is handled via a Bearer token in the Authorization header. You obtain your key by signing up with an email and password on our dashboard. No credit card is required for the trial, and you can regenerate your key at any time to revoke access.

Set the base URL to our dedicated endpoint. This ensures all requests go to our uncensored model infrastructure instead of the default OpenAI cloud. You can find your API key on the 'Get API key' page immediately after signup.

Send Your First Request

Send a standard chat completion request to test connectivity. The model ID is always uncensored. This model is tuned to answer without content refusals for lawful adult use, making it ideal for creative writing, roleplay, or unrestricted research.

• Use POST /v1/chat/completions for text generation.
• The context window supports up to 100,000 tokens for prompt plus completion.
• Requests are charged based on input and output token counts.

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

Enable Streaming (SSE)

For better user experience, enable streaming to receive tokens as they are generated. This reduces perceived latency, especially for longer responses. The server returns Server-Sent Events (SSE) that your client can parse in real-time.

Set the stream parameter to true in your request body. The SDK will yield chunks as they arrive. This is particularly useful for chat interfaces where you want to display text incrementally rather than waiting for the entire response to finish.

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)

Use Tool/Function Calling

Our API supports function calling, allowing the model to output structured JSON for external tool execution. Define your functions in the tools parameter, and the model will return tool_calls in the response if appropriate.

This feature works exactly as documented in the OpenAI specification. You can parse the function name and arguments, execute your backend logic, and feed the results back into the conversation. It is fully compatible with standard OpenAI SDK tool-calling workflows.

Copyimport OpenAI from "openai";

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

Check Available Models

Query the models endpoint to verify connectivity and see available options. Currently, we offer a single dedicated model: uncensored. This simplicity avoids the complexity of model routing or generic infrastructure, ensuring predictable behavior.

You can also use this endpoint to debug authentication issues. If the request fails, check your API key validity and network connectivity. The response will list the model details, including the context window size and token limits.

Copyfrom openai import OpenAI

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

Handle Rate Limits & Errors

Our API enforces a limit of 300 requests per minute per key. If you exceed this, you will receive a 429 error. We also support an 8 MB request body limit for complex prompts or large context windows.

Common errors include 401 (invalid key) and 402 (insufficient credit). Prepaid credit never expires, so you can top up at your convenience. Credit bonuses are applied automatically for larger purchases: +5% from $50 and +10% from $100.