PrixGratuit (API)

Contexte200K

RaisonnementOui

StatutActif

Entrées : text, image, video · Sorties : text

Pépites du moment : cette fiche suit une API gratuite (0 € / M tokens en entrée et sortie). Les quotas, rate limits et conditions peuvent évoluer — vérifiez avant un usage en production.

Slug API : z-ai/glm-4.6v-flash-free
Éditeur : z-ai
Contexte : 200K tokens
Modalités d’entrée : text, image, video
Raisonnement : oui

Utilisez les snippets ci-dessous avec votre clé API. Ouvrir la fiche technique.

Appeler l’API

Appeler le modèle en API

Remplacez <ZENMUX_API_KEY> / $ZENMUX_API_KEY par votre clé. Compatible OpenAI, Anthropic et Gemini.

curl https://zenmux.ai/api/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $ZENMUX_API_KEY" \
  -d '{
    "model": "z-ai/glm-4.6v-flash-free",
    "messages": [{"role": "user", "content": "Bonjour"}]
  }'

from openai import OpenAI

client = OpenAI(
    base_url="https://zenmux.ai/api/v1",
    api_key="<ZENMUX_API_KEY>",
)

completion = client.chat.completions.create(
    model="z-ai/glm-4.6v-flash-free",
    messages=[{"role": "user", "content": "Bonjour"}],
)
print(completion.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://zenmux.ai/api/v1",
  apiKey: "<ZENMUX_API_KEY>",
});

const completion = await client.chat.completions.create({
  model: "z-ai/glm-4.6v-flash-free",
  messages: [{ role: "user", content: "Bonjour" }],
});
console.log(completion.choices[0].message.content);

curl https://zenmux.ai/api/v1/responses \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $ZENMUX_API_KEY" \
  -d '{
    "model": "z-ai/glm-4.6v-flash-free",
    "input": "Bonjour"
  }'

from openai import OpenAI

client = OpenAI(
    base_url="https://zenmux.ai/api/v1",
    api_key="<ZENMUX_API_KEY>",
)

response = client.responses.create(
    model="z-ai/glm-4.6v-flash-free",
    input="Bonjour",
)
print(response.output_text)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://zenmux.ai/api/v1",
  apiKey: "<ZENMUX_API_KEY>",
});

const response = await client.responses.create({
  model: "z-ai/glm-4.6v-flash-free",
  input: "Bonjour",
});
console.log(response.output_text);

curl https://zenmux.ai/api/anthropic/v1/messages \
  -H "content-type: application/json" \
  -H "x-api-key: $ZENMUX_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -d '{
    "model": "z-ai/glm-4.6v-flash-free",
    "max_tokens": 1024,
    "messages": [{"role": "user", "content": "Bonjour"}]
  }'

from anthropic import Anthropic

client = Anthropic(
    base_url="https://zenmux.ai/api/anthropic",
    api_key="<ZENMUX_API_KEY>",
)

message = client.messages.create(
    model="z-ai/glm-4.6v-flash-free",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Bonjour"}],
)
print(message.content[0].text)

import Anthropic from "@anthropic-ai/sdk";

const client = new Anthropic({
  baseURL: "https://zenmux.ai/api/anthropic",
  apiKey: "<ZENMUX_API_KEY>",
});

const message = await client.messages.create({
  model: "z-ai/glm-4.6v-flash-free",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Bonjour" }],
});
console.log(message.content[0].text);

from google import genai
from google.genai import types

client = genai.Client(
    api_key="<ZENMUX_API_KEY>",
    vertexai=True,
    http_options=types.HttpOptions(
        api_version="v1",
        base_url="https://zenmux.ai/api/vertex-ai",
    ),
)

response = client.models.generate_content(
    model="z-ai/glm-4.6v-flash-free",
    contents="Bonjour",
)
print(response.text)

import { GoogleGenAI } from "@google/genai";

const ai = new GoogleGenAI({
  apiKey: "<ZENMUX_API_KEY>",
  vertexai: true,
  httpOptions: {
    apiVersion: "v1",
    baseUrl: "https://zenmux.ai/api/vertex-ai",
  },
});

const response = await ai.models.generateContent({
  model: "z-ai/glm-4.6v-flash-free",
  contents: "Bonjour",
});
console.log(response.text);

Z.AI: GLM 4.6V Flash (Free)

Appeler le modèle en API

Construisons l'IA de confiance, ensemble.