Gemma api Quickstart Guide

Authentication and base URL

Start by generating your key on the dashboard. Use the provided base URL to route requests to our uncensored model. Authentication relies on a standard header.

Base URL: HTTPS://api.apigemma.com/v1

Header: Authorization: Bearer YOUR_API_KEY

Only one active key per account. Replacing it revokes the old one immediately. No phone number is required for signup.

Chat completions endpoint

Send text prompts to the chat completions endpoint. The model returns text without content refusals for lawful adult use.

Context window: 100,000 tokens. Max output: 16,000 tokens. Errors and refusals cost nothing.

Supports function calling, JSON mode, and streaming via SSE.

Streaming responses with SSE

Enable streaming by setting the stream flag to true. Receive tokens in real-time via Server-Sent Events.

Token usage is reported in the final chunk. This is ideal for chat interfaces and voice synthesis pipelines.

Stream events are reliable and follow standard OpenAI formats.

JSON mode and function calling

Force structured output by setting response_format to json_object. This ensures consistent parsing for downstream applications.

Use tools for function calling. The model handles tool execution seamlessly.

Parameters like temperature and top_p control creativity and randomness.

Parameters: temperature, top_p, and seed

Control output variation with temperature (0-2), top_p (0-1), and seed for reproducibility.

Use stop sequences to truncate responses. presence_penalty and frequency_penalty reduce repetition.

These parameters work exactly like the OpenAI SDK.

Limits, errors, and context window

Rate limit: 300 requests/minute, 8 concurrent requests. Max body size: 8 MB.

401: Invalid key. 402: No credit. 429: Rate limit exceeded.

Context window is 100,000 tokens. Output max is 16,000 tokens.

cURL

Copycurl https://api.apigemma.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Show me the gemma model weights config file"}]
  }'

Python

Copyfrom openai import OpenAI

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