Modèles les plus récents et populaires

Seedance 2.0 is ByteDance's multimodal video model supporting text-to-video, first-and-last-frames, and omni-reference modes. APIXO exclusive: unlimited concurrency, real-person portrait support, and hidden capabilities.

Seedance 2.0 Fast is the speed-optimized variant of ByteDance's multimodal video model. It supports text-to-video, first-and-last-frames, and omni-reference modes with lower per-second pricing and the same APIXO-exclusive capabilities.

GPT-Image-2 is OpenAI's next-generation image model for stronger photorealism, cleaner image editing, and sharper in-image text rendering.

HappyHorse is Alibaba's video generation and editing model for text-to-video, image-to-video, reference-guided generation, and video-edit workflows with 720p/1080p output.

BFL’s latest Pro & Flex pipelines for text-to-image and image-to-image with unified 1K/2K pricing and ~30s generation.

Nano Banana Pro is Google's AGI-level image generation model with reasoning capabilities, native 4K output, Search Grounding for real-time data integration, near-perfect text rendering, and superior spatial awareness.

Midjourney is an advanced AI image generation model known for artistic, high-quality outputs. It supports text-to-image, image-to-image, image-edit, Vary, and Upscale workflows.

Professional-grade image generation with enhanced prompt understanding and superior quality output.

GPT-Image-1 is OpenAI's advanced multimodal model for high-quality image generation with natural language understanding.

Gemini 2.5 Flash Image Preview (aka Nano Banana) is an advanced AI model excelling in natural language-driven image generation and editing. It produces hyper-realistic, physics-aware visuals with seamless style transformations.

Seedream 5.0 Pro is ByteDance's premium single-image model for text-to-image and image-to-image generation, supporting 1K/2K resolution, eight aspect ratios, up to 10 reference images, and strict custom-size control.

Seedance 1.5 Pro is ByteDance's per-second video model for fast text-to-video and image-to-video generation with 480p/720p/1080p output, optional sound, aspect ratio control, and fixed-lens camera stability.

Gemini Omni is Google's multimodal video generation model for creating videos from text, image references, source video, reusable audio assets, and character asset IDs.

Wan 2.7 Image is Alibaba's omni-image API for text-to-image, reference-guided image generation, image editing, sequential images, and high-resolution Omni Image Pro workflows.

Wan 2.7 is Alibaba's video generation and editing model for text-to-video, image-to-video, reference-guided generation, and video-edit workflows with optional audio input and 720p/1080p output.

Wan 2.6 is Alibaba's multi-mode video generation model for text, image, flash image, reference, and flash reference workflows, with optional audio input and 720p/1080p output.

Seedream 5.0 is ByteDance's next-generation AI image model with real-time web search, controllable editing, and logical reasoning. It supports text-to-image and image-to-image with 2K/3K resolution, multiple aspect ratios, and up to 14 reference images.

Sora 2 Pro is OpenAI’s premium video generation model with higher quality output, supporting text-to-video and image-to-video at 720p and 1080p resolutions with flexible durations of 4, 8, or 12 seconds.

Seedance 2.0 Mini is ByteDance's lightweight multimodal video model for text-to-video, first-and-last-frames, and omni-reference workflows with 480p/720p output.

Wan 2.6 Image is Alibaba's text-to-image and image-to-image model with prompt, negative prompt, aspect ratio, batch count, and optional seed control.

Wan 2.5 Image is Alibaba's batch-friendly image generation model for text-to-image and image-to-image workflows, defaulting to four generated images per request.

Image Upscaler is APIXO's single-image enhancement API for 2K, 4K, and 8K upscaling with JPG, PNG, and WEBP output format control.

Image Watermark Remover is APIXO's authorized single-image cleanup API for removing sample marks or overlays from images you own or have permission to process.

Kling 3.0 Turbo is Kuaishou's fast video generation model for text-to-video and single-image image-to-video workflows with 720p/1080p output and 3-15 second clips.

MiniMax Image 01 is MiniMax’s text-to-image and image-to-image model with prompt optimization, flexible size control, 1K/2K presets, and up to 9 generated images per task.

MiniMax Speech 2.8 is an async text-to-speech API with HD and turbo quality modes, preset voices, custom MiniMax voice_id support, emotion control, pronunciation dictionaries, and multilingual output settings.

MiniMax Voice creates reusable custom voice IDs from text-described voice design or a single public reference audio clip, then returns preview audio for validation.

Hailuo 2.3 is Miniax's async video model with standard and pro modes for text-to-video and image-to-video generation. Standard mode supports 6s/10s at 768p, while pro mode returns fixed 5s at 1080p.

Hailuo 2.3 Fast is Miniax's speed-optimized image-to-video model with standard and pro modes. Standard supports 6s/10s at 768p, while pro returns fixed 6s output at 1080p.

Grok Image is xAI's image generation model for text-to-image and image-to-image workflows with simple aspect-ratio control and async task delivery. Text-to-image returns 6 images per request on APIXO.

Wan 2.2 Animate API is Alibaba's character animation model that combines one source image and one motion video to generate stylized animated outputs with animate/replace behavior.

Grok Video is xAI's async video generation model for text-to-video and image-to-video workflows, with optional continuation via task_id + index and style control.

Kling 3.0 Std is Kuaishou's standard-quality video generation model with text-to-video, image-to-video, and motion-control modes. It supports clips up to 15 seconds with optional sound generation and flexible aspect ratios.

InfiniteTalk converts one photo plus audio into audio-driven talking or singing avatar videos with precise lip synchronization. Supports up to 10 minutes at 480p or 720p resolution.

Nano Banana 2 is Google’s high-resolution image generation model with 1K/2K/4K output control, 20,000-character prompts, optional Google Search context, and support for up to 14 reference images.

Vidu Q3 is a per-second video generation model that combines standard and Turbo text-to-video plus image-to-video workflows in one API. It supports single-image animation, first-and-last-frame transitions, optional sound and BGM, and output up to 1080p.

Kling 2.5 Turbo Pro is Kuaishou's high-speed video model for text-to-video and image-to-video creation. It supports 5-10 second clips, optional tail-frame images, aspect ratio control for text-to-video, plus negative prompts and CFG scale guidance.

LTX-2 19B is Lightricks' open-source 19B diffusion transformer for cinematic video generation. It supports text-to-video and image-to-video workflows, LoRA conditioning, and high-fidelity outputs up to 1080p in the API.

Kling 2.1 is Kuaishou's multi-tier video model with Standard, Pro, and Master modes for image-to-video and text-to-video creation. It supports 5-10 second clips, optional tail images for Pro, and aspect ratio control for Master text-to-video.

Kling 2.6 is Kuaishou's native audio-visual video model that generates video, speech, sound effects, and ambience in one pass. It supports text-to-audio-visual and image-to-audio-visual creation with Chinese and English voice generation and up to 10-second clips.

Latest Suno text-to-music model that returns two polished songs per call with faster queues and richer vocals.

Passerelle compatible OpenAI pour le chat, les agents, le raisonnement et la génération structurée.

Passerelle compatible OpenAI pour le chat, les agents, le raisonnement et la génération structurée.

Passerelle compatible OpenAI pour le chat, les agents, le raisonnement et la génération structurée.

Passerelle compatible OpenAI pour le chat, les agents, le raisonnement et la génération structurée.

Passerelle compatible OpenAI pour le chat, les agents, le raisonnement et la génération structurée.

Passerelle compatible OpenAI pour le chat, les agents, le raisonnement et la génération structurée.

Passerelle compatible OpenAI pour le chat, les agents, le raisonnement et la génération structurée.

Passerelle compatible OpenAI pour le chat, les agents, le raisonnement et la génération structurée.

Passerelle compatible OpenAI pour le chat, les agents, le raisonnement et la génération structurée.

Passerelle compatible OpenAI pour le chat, les agents, le raisonnement et la génération structurée.

Passerelle compatible OpenAI pour le chat, les agents, le raisonnement et la génération structurée.

Passerelle compatible OpenAI pour le chat, les agents, le raisonnement et la génération structurée.

Passerelle compatible OpenAI pour le chat, les agents, le raisonnement et la génération structurée.

Passerelle compatible OpenAI pour le chat, les agents, le raisonnement et la génération structurée.

Passerelle compatible OpenAI pour le chat, les agents, le raisonnement et la génération structurée.

Passerelle compatible OpenAI pour le chat, les agents, le raisonnement et la génération structurée.

Passerelle compatible OpenAI pour le chat, les agents, le raisonnement et la génération structurée.

Passerelle compatible OpenAI pour le chat, les agents, le raisonnement et la génération structurée.

Passerelle compatible OpenAI pour le chat, les agents, le raisonnement et la génération structurée.

Passerelle compatible OpenAI pour le chat, les agents, le raisonnement et la génération structurée.

Passerelle compatible OpenAI pour le chat, les agents, le raisonnement et la génération structurée.

Passerelle compatible OpenAI pour le chat, les agents, le raisonnement et la génération structurée.

Google DeepMind’s upgraded AI video model with lite, fast, and quality routes, 4/6/8 second duration control, 720p/1080p/4k output, and multi-image reference workflows.

Wan 2.5 is Alibaba's video generation model for text-to-video and image-to-video workflows, with optional audio input, 480p/720p/1080p output, 5 or 10 second clips, and prompt expansion.

Sora 2 is OpenAI’s latest AI video generation model, supporting both text-to-video and image-to-video. It delivers realistic motion, physics consistency, with improved control over style, scene, and aspect ratio—ideal for creative apps and social media content.

Seedream 4.5 is a powerful text-to-image and image-to-image AI model delivering high-quality image generation with support for 2K and 4K resolutions.