Une seule API IAConnectez les meilleurs modèles chinois à prix réduit

Seedream 5.0 Flash is ByteDance's fast, lower-cost text-to-image model. It supports single-image and multi-reference editing with up to 10 references and generates 1K, 1.5K or 2K images, or exact pixel sizes, with strong text rendering.

Qwen Image 3.0 Pro is the Pro version of Qwen Image 3.0, with clear instruction following, stable bilingual text rendering, 1K/2K output and image editing with up to 3 references.

Qwen Image 3.0 Pro is the Pro version of Qwen Image 3.0, with clear instruction following, stable bilingual text rendering, 1K/2K output and image editing with up to 3 references.

Seedream 5.0 Pro (seedream-5-0-pro) is quality-first text-to-image model. It produces cinematic 1K and 2K images with best-in-class text rendering, supports up to 10 reference images for style and character consistency, and unifies generation and editing in a single API call.

wan‑2‑7‑image is an advanced image generation model in Alibaba’s Wan 2.7 series designed to create high‑quality visuals from text prompts. It excels at generating detailed, realistic images with accurate object representation and rich composition. The model supports multimodal input (e.g., combining text with reference images) to influence style and structure, and it’s well‑suited for creative workflows such as marketing assets, product visuals, social media graphics, and artistic content production. With strong semantic understanding and prompt adherence, wan‑2‑7‑image delivers both fidelity and expressive visual output.

wan‑2‑7‑image is a powerful image generation model in Alibaba’s Wan 2.7 series that creates high‑quality visuals from text prompts. It produces detailed and realistic images with strong semantic understanding and refined composition. The model supports multimodal input—such as combining text with reference images—to influence style, layout, or visual direction. It’s well‑suited for creative workflows like product visuals, marketing graphics, social media content, and artistic illustrations, delivering both fidelity and expressive visual output.

Qwen-Image-2.0 is an AI image model that combines “generation and editing” capabilities, supports extremely long descriptions, and delivers high-quality 2K output. It is particularly well-suited for image creation that requires clear text and professional design aesthetics.

Qwen-Image-2.0-Pro is the highest-fidelity variant of Alibaba’s Qwen image model, designed to generate and edit production-quality visuals from text or reference images. It delivers native 2K resolution with strong detail, accurate composition, and advanced text rendering, making it suitable for infographics, posters, and marketing assets. 

Z-Image-Turbo is a “fast, efficient, and cost-effective” AI image generation model, ideal for rapid image creation and batch processing.

Seedream 5.0 Lite delivers cutting-edge text-to-image generation. Create 4K resolution images with precise text rendering, multi-reference style fusion, and unified editing capabilities.

Seedream 5.0 Flash is ByteDance's fast, lower-cost text-to-image model. It supports single-image and multi-reference editing with up to 10 references and generates 1K, 1.5K or 2K images, or exact pixel sizes, with strong text rendering.

Qwen Image 3.0 Pro is the Pro version of Qwen Image 3.0, with clear instruction following, stable bilingual text rendering, 1K/2K output and image editing with up to 3 references.

Qwen Image 3.0 Pro is the Pro version of Qwen Image 3.0, with clear instruction following, stable bilingual text rendering, 1K/2K output and image editing with up to 3 references.

Seedream 5.0 Pro (seedream-5-0-pro) is quality-first text-to-image model. It produces cinematic 1K and 2K images with best-in-class text rendering, supports up to 10 reference images for style and character consistency, and unifies generation and editing in a single API call.

wan‑2‑7‑image is an advanced image generation model in Alibaba’s Wan 2.7 series designed to create high‑quality visuals from text prompts. It excels at generating detailed, realistic images with accurate object representation and rich composition. The model supports multimodal input (e.g., combining text with reference images) to influence style and structure, and it’s well‑suited for creative workflows such as marketing assets, product visuals, social media graphics, and artistic content production. With strong semantic understanding and prompt adherence, wan‑2‑7‑image delivers both fidelity and expressive visual output.

wan‑2‑7‑image is a powerful image generation model in Alibaba’s Wan 2.7 series that creates high‑quality visuals from text prompts. It produces detailed and realistic images with strong semantic understanding and refined composition. The model supports multimodal input—such as combining text with reference images—to influence style, layout, or visual direction. It’s well‑suited for creative workflows like product visuals, marketing graphics, social media content, and artistic illustrations, delivering both fidelity and expressive visual output.

Qwen-Image-2.0 is an AI image model that combines “generation and editing” capabilities, supports extremely long descriptions, and delivers high-quality 2K output. It is particularly well-suited for image creation that requires clear text and professional design aesthetics.

Qwen-Image-2.0-Pro is the highest-fidelity variant of Alibaba’s Qwen image model, designed to generate and edit production-quality visuals from text or reference images. It delivers native 2K resolution with strong detail, accurate composition, and advanced text rendering, making it suitable for infographics, posters, and marketing assets. 

Z-Image-Turbo is a “fast, efficient, and cost-effective” AI image generation model, ideal for rapid image creation and batch processing.

Seedream 5.0 Lite delivers cutting-edge text-to-image generation. Create 4K resolution images with precise text rendering, multi-reference style fusion, and unified editing capabilities.

Wan 3.0 Prime is the Prime version of Alibaba Cloud's all-in-one Wan 3.0 video model, with general, first-and-last-frame and file or webpage modes and 2–30 second output.

MiniMax H3 Max generates video from text and images at 480P, 768P or 1080P with 5–15 second clips, first/last frames, multimodal references and synced audio.

Seedance 2.0 Mini is the lightweight version of ByteDance's Seedance 2.0 for text-to-video and image-to-video, with 480p or 720p output.

HappyHorse 1.1 generates 720P or 1080P video from text, a first-frame image or 1–9 reference images. Video editing is not supported.

Kling-3.0-Turbo: A high-speed, high-quality AI video generation model ideal for quickly creating short videos.

pixverse-v6 is PixVerse's sixth-generation AI video generation model, primarily used for text-to-video and image-to-video generation.

kling-motion-control on 光谱汇深 uses a reference image plus a reference video to transfer subject motion into generated clips. Add an optional prompt, choose character orientation and mode, and control sound or watermark settings for kling motion workflows.

kling-motion-control on 光谱汇深 uses a reference image plus a reference video to transfer subject motion into generated clips. Add an optional prompt, choose character orientation and mode, and control sound or watermark settings for kling motion workflows.

HappyHorse-1.0 is an AI model that generates videos based on text input.

wan2.7‑r2v is the reference‑to‑video variant within Alibaba’s Wan 2.7 video generation model family. It uses one or more reference images or short clips as visual anchors and, combined with a text prompt, generates new video content that preserves the appearance and identity of characters or objects from the references while animating motion and scene direction. This makes it especially useful for consistent character representation, product showcases, brand assets, and creative workflows where visual continuity is important.

Kimi-K3 is a next-generation large language model launched by Moonshot AI. It features ultra-long context, multimodal understanding, and strong coding capabilities, making it suitable for complex reasoning, software development, knowledge analysis, and agent automation tasks.

Xiaomi has launched a high-performance large language model that enhances reasoning, coding, and multitasking capabilities, making it suitable for complex analysis, programming, and agent-based scenarios.

Launched by Alibaba Cloud Tongyi Qianwen, this flagship large language model features enhanced capabilities in reasoning, coding, and handling complex tasks, making it suitable for enterprise-level applications, chatbots, and high-difficulty task scenarios.

A general-purpose large language model launched by Moonshot AI, featuring strong reasoning, coding, and agent capabilities, making it suitable for handling complex tasks.

Alibaba Cloud Tongyi Qianwen has launched a high-performance general-purpose model that enhances reasoning, coding, and multi-task processing capabilities, making it suitable for intelligent Q&A, development, and enterprise applications.

A code-specific model launched by Moonshot AI that excels at code generation, understanding, debugging, and complex development tasks, and is suitable for use as an AI programming assistant.

Zhipu AI has launched a new-generation large language model that enhances reasoning, coding, and agent capabilities, making it suitable for complex tasks, development, and enterprise applications.

Launched by Alibaba Cloud Tongyi Qianwen, this high-performance large language model enhances reasoning, coding, and complex task-handling capabilities, making it suitable for enterprise applications and intelligent agent scenarios.

A lightweight large language model launched by StepFun that emphasizes fast response times and low cost, suitable for conversational, text generation, and high-concurrency use cases.

Kimi has launched a high-speed code model that focuses on code generation, autocompletion, debugging, and development tasks, balancing programming capabilities with responsiveness.