Modèles API IA xAI
Modèles d'IA xAI sur MuAPI
Explorez les modèles xAI pour le chat, le code, la génération d'images et de vidéos, y compris les flux de type Gemini, Nano Banana et Veo disponibles via MuAPI.
All models
13 ModèlesVideo Generation Models
$0.150 / seconde
grok-imagine-image-to-video
Grok Imagine is xAI’s multimodal image-to-video model, capable of animating still images into cinematic videos from 6 to 30 seconds with synchronized ambient audio. It focuses on realism, fluid motion, and expressive lighting transitions while maintaining high generation speed.
$0.150 / seconde
grok-imagine-text-to-video
Grok Imagine is xAI’s fast, creative text-to-video model that generates cinematic clips from 6 to 30 seconds with smooth motion, expressive lighting, and ambient audio. It turns a written idea into a visually rich video.
$0.640 / seconde
grok-imagine-video-1-5-preview
Generate videos from images using the Grok Imagine Video 1.5 Preview model with support for multiple aspect ratios, resolutions, and durations up to 15 seconds.
$0.050 / seconde
grok-imagine-extend
Grok Imagine Extend lets you continue and expand existing Grok Imagine video generations seamlessly. Starting from a previously generated video, you can extend the scene while maintaining visual style, characters, motion, and audio consistency. Requires the original task_id from the initial video generation.
Image Generation Models
$0.050 / 1K jetons
grok-imagine-text-to-image
Grok Imagine is xAI’s high-quality image generation model that transforms text prompts into detailed, stylish, and visually expressive images. It excels at creating vivid scenes, characters, environments, and concept art with strong lighting, depth, and artistic clarity. Get 6 images each time.
$0.050 / génération
grok-imagine-image-to-image
Grok Imagine Image-to-Image transforms an existing image using natural language instructions while preserving scene structure, perspective, and lighting. It is ideal for object replacement, environment evolution, concept re-imagining, and creative edits that feel grounded and visually coherent rather than over-stylized.
$0.050 / génération
grok-imagine-image-2-edit
Grok Imagine Image 2.0 Edit applies a targeted, natural-language edit to a prior Grok Imagine Image 2.0 generation, changing only the described region while preserving the rest of the composition, style, and subject.
$0.050 / 1K jetons
grok-imagine-text-to-image-quality
Grok Imagine Quality is xAI's high-fidelity text-to-image mode that prioritizes accuracy and detail over speed. It produces sharper, more visually accurate images with stronger lighting, depth, and artistic clarity. Get 6 images each time.
$0.050 / 1K jetons
grok-imagine-image-2
Grok Imagine Image 2.0 is xAI's next-generation image model, built for precise instruction-following, sharp typography, and detailed layout control. It follows instructions closely down to fine detail and plans layout so dense, multi-part visuals hold together, turning a text prompt into a polished, commercial-ready image in one request.
Text & Chat Models
$0.000 / 1K jetons
grok-4-3
Grok 4.3 is a highly capable multimodal reasoning model, supporting mixed text/image inputs, adjustable reasoning effort, and integrated web search tools. Token-based pricing: $2.50/M input tokens, $5.00/M output tokens. Two endpoints: standard async (/grok-4-3) and live streaming (/grok-4-3/stream) via SSE.
$0.000 / 1K jetons
grok-4-5
Grok 4.5 is a highly capable multimodal reasoning model, supporting mixed text/image inputs, adjustable reasoning effort, and integrated web search tools. Token-based pricing: $1.60/M input tokens, $4.80/M output tokens. Two endpoints: standard async (/grok-4-5) and live streaming (/grok-4-5/stream) via SSE.
$0.000 / 1K jetons
grok-4-6
Grok 4.6 is xAI’s next-generation multimodal reasoning model, supporting mixed text/image inputs, adjustable reasoning effort, and integrated web search tools. Token-based pricing: $1.50/M input tokens, $4.50/M output tokens. Two endpoints: standard async (/grok-4-6) and live streaming (/grok-4-6/stream) via SSE.
$0.000 / 1K jetons
grok-4-7
Grok 4.7 is xAI’s next-generation multimodal reasoning model, supporting mixed text/image inputs, adjustable reasoning effort, and integrated web search tools. Token-based pricing: $1.40/M input tokens, $4.20/M output tokens. Two endpoints: standard async (/grok-4-7) and live streaming (/grok-4-7/stream) via SSE.