Gemma api key documentation

Authentication and Base URL

Use your unique API key to authenticate every request. The base URL is HTTPS://api.gemmaapikey.com/v1 and you send the key in the Authorization header. This works with any OpenAI-compatible client by changing base_url and the API key. If you lose it, generate a new one from the dashboard. The old key stops working immediately. Errors and refusals do not consume your prepaid credit.

First Request

Send a POST request to /v1/chat/completions with the model id "uncensored". Include your system prompt and user message in the messages array. The model responds with text generated without content refusals for lawful adult use.

Copyfrom openai import OpenAI

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

Set temperature and top_p to control randomness. Use stop sequences to halt generation early. The response includes token usage in the final chunk if streaming is enabled.

Node SDK Integration

Install the official OpenAI SDK for Node.js. Configure it with your API key and the base URL from this guide. Call the chat.completions.create method with your prompt.

Copyimport OpenAI from "openai";

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

This approach keeps costs predictable because you pay only for tokens used. The prepaid credit is charged by real usage. No monthly fees apply. You can top up with crypto at any time.

Streaming Responses

Enable streaming by setting stream to true in your request. The API returns Server-Sent Events (SSE) chunks. Each chunk contains partial text until the final chunk includes the token usage.

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)

Streaming reduces perceived latency for long responses. It also allows you to display progress to users in real time. The context window supports 100,000 tokens for prompt and completion together.

Rate Limits and Context

You are limited to 300 requests per minute per key. Only 8 requests can run simultaneously. The request body must not exceed 8 MB. These limits ensure stable performance for all users.

The model supports function calling, JSON mode, and standard parameters like seed and presence_penalty. Max output is 16,000 tokens per request. If you do not set max_tokens, it defaults to 2,048.

Errors and Troubleshooting

A 401 error means your API key is invalid or expired. Check the dashboard for your active key. A 402 error indicates insufficient prepaid credit. Top up via crypto to continue. A 429 error means you hit the rate limit. Wait a few seconds and retry.

Errors do not consume your credit. If you double-charge, use the Support page to fix it. Credit never expires, so you can top up later.

cURL

Copycurl https://api.gemmaapikey.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Return the current system status"}]
  }'