gemini-2.5-flash-lite — Free API

Created by Google ⭐ Score: 44
llm7-io/gemini-2-5-flash-lite
🛠️ Function Calling ⚡ JSON Mode chat
Get API key → Test in Playground →

Overview

The Google Gemini 2.5 Flash-Lite is a pre-trained 1M token text-based LLM ideal for chat applications, producing up to 65k tokens at 15 RPM and 1k RPD. It's open to developers but not OpenAI compatible or requiring a credit card.

Model ID
gemini-2-5-flash-lite
Base URL
https://api.llm7.io/v1

Quick Start — 3 Lines of Code

Paste your API key and run. See the config generator for Claude Code, Cursor, and more tools.

from openai import OpenAI

client = OpenAI(
    base_url="https://api.llm7.io/v1",
    api_key="YOUR_API_KEY"
)

response = client.chat.completions.create(
    model="gemini-2-5-flash-lite",
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)
import OpenAI from "openai";

const openai = new OpenAI({
  baseURL: "https://api.llm7.io/v1",
  apiKey: "YOUR_API_KEY",
});

const completion = await openai.chat.completions.create({
  model: "gemini-2-5-flash-lite",
  messages: [{ role: "user", content: "Hello!" }],
});

console.log(completion.choices[0].message.content);
curl https://api.llm7.io/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "gemini-2-5-flash-lite",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Other Free Models from LLM7.io

deepseek-r1-0528

131K ctx · No card

deepseek-v3-0324

131K ctx · No card

gpt-4o-mini

131K ctx · No card

mistral-small-3.1-24b

32K ctx · No card

qwen2.5-coder-32b

131K ctx · No card

More About LLM7.io

How to get an API key, rate limits, platform limitations, and tool configuration — everything you need to set up LLM7.io as a free LLM API backend.

View LLM7.io full guide →