Gemma API: First request in five minutes

Base URL & Authentication

Start by creating an account on the Get API key page. You only need an email and password; no phone number or credit card is required to activate the trial credit. Once registered, your API key is displayed immediately. Copy this key and store it securely. Use it in the Authorization header as a Bearer token for all requests. The base URL for all endpoints is https://api.gemma4api.com/v1. This URL works with any standard OpenAI-compatible client, allowing you to switch providers by simply changing the base URL and API key in your configuration.

First Request

Send your first prompt using curl to verify connectivity. Replace YOUR_API_KEY with your actual key. The model identifier is uncensored. This simple text-in, text-out request confirms your authentication is correct and the model is responding. If you receive a JSON response with a choices array, your setup is complete. You can now proceed to integrate the SDK for more complex workflows.

Copycurl https://api.gemma4api.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 SDK Integration

Install the official OpenAI Python package. Set the base URL and API key environment variables or pass them directly to the client constructor. Use the model ID uncensored to ensure you are calling our specific instance. This approach ensures your code remains compatible with standard OpenAI patterns while leveraging our uncensored model for content generation. The SDK handles retries and JSON parsing automatically.

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.gemma4api.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 SDK Integration

For JavaScript environments, install the OpenAI Node.js package. Configure the client with the base URL https://api.gemma4api.com/v1 and your API key. Use the model ID uncensored in your completion calls. This setup allows you to maintain standard OpenAI-compatible code structures while benefiting from the specific model behavior hosted on our servers. Ensure you handle asynchronous responses correctly within your Node.js event loop.

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.gemma4api.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 the stream parameter to true in your API request. This returns a Server-Sent Events (SSE) stream, allowing you to display tokens as they are generated. This is ideal for chat interfaces where latency matters. Each chunk contains a partial delta of the response. Handle the stream end event to know when the generation is complete. This method reduces perceived latency significantly compared to waiting for the full response.

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 & Context Window

Your requests support a context window of 100,000 tokens for both prompt and completion combined. The rate limit is 300 requests per minute per key, with a maximum request body size of 8 MB. Common errors include 401 for invalid keys, 402 if your prepaid credit is exhausted, and 429 if you exceed the per-minute limit. Regenerating your API key revokes the old one but does not reset the rate counter. Ensure your client handles these HTTP status codes appropriately to maintain smooth operation.