Guide API Gemini

Cette plateforme appelle les modeles Gemini via des endpoints compatibles OpenAI, ce qui permet d utiliser le SDK openai.

Installation

Python

pip install openai

JavaScript

npm install openai

curl

# curl est generalement deja disponible; aucun SDK n est requis

Utilisation de base

Python

from openai import OpenAI

client = OpenAI(
    api_key="your-api-key",
    base_url="https://aisupermarket.work/v1",
)

response = client.chat.completions.create(
    model="gemini-2.5-flash",
    messages=[{"role": "user", "content": "Hello, please introduce yourself"}],
)
print(response.choices[0].message.content)

JavaScript

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "your-api-key",
  baseURL: "https://aisupermarket.work/v1",
});

const response = await client.chat.completions.create({
  model: "gemini-2.5-flash",
  messages: [{ role: "user", content: "Hello, please introduce yourself" }],
});
console.log(response.choices[0].message.content);

curl

curl https://aisupermarket.work/v1/chat/completions \
  -H "Authorization: Bearer your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-2.5-flash",
    "messages": [{"role": "user", "content": "Hello, please introduce yourself"}]
  }'

Modeles courants

Modele	Description
gemini-2.5-flash	Rapide et adapte a la plupart des taches
gemini-2.5-pro	Capacite la plus forte avec raisonnement approfondi
gemini-3.5-flash	Modele Flash de nouvelle generation