Google: Gemma 3n 2B (free)

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "your-llmt_-key-here",
  baseURL: "https://llmtest.io/v1",
});

const response = await client.chat.completions.create({
  model: "google/gemma-3n-e2b-it:free",
  messages: [
    { role: "system", content: "You are a helpful assistant." },
    { role: "user", content: "Hello, how are you?" }
  ],
  temperature: 0.7,          // 0-2, higher = more creative
  max_tokens: 1024,          // max tokens to generate
  // stream: true,           // enable streaming (SSE)
  // top_p: 0.9,             // nucleus sampling
  // response_format: { type: "json_object" },  // guaranteed JSON output
});

from openai import OpenAI

client = OpenAI(
    api_key="your-llmt_-key-here",
    base_url="https://llmtest.io/v1",
)

response = client.chat.completions.create(
    model="google/gemma-3n-e2b-it:free",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Hello, how are you?"}
    ],
    temperature=0.7,          # 0-2, higher = more creative
    max_tokens=1024,          # max tokens to generate
    # stream=True,            # enable streaming (SSE)
    # top_p=0.9,              # nucleus sampling
    # response_format={"type": "json_object"},  # guaranteed JSON output
)

curl -X POST "https://llmtest.io/v1/chat/completions" \
  -H "Authorization: Bearer your-llmt_-key-here" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemma-3n-e2b-it:free",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "Hello, how are you?"}
    ],
    "temperature": 0.7,
    "max_tokens": 1024
  }'