All Model Families
Kling 4.0
Developed by Kuaishou, Kling V4 is an video model built for professional production. It pairs stable complex motion with a 21:9 ultrawide format and targeted editing for expressions, camera angles, backgrounds, visual styles, and dialogue.…
Category
107 families · 6 sections
Kling 4.0
Developed by Kuaishou, Kling V4 is an video model built for professional production. It pairs stable complex motion with a 21:9 ultrawide format and targeted editing for expressions, camera angles, backgrounds, visual styles, and dialogue.…
Seedance 2.5
Seedance 2.5 API is now available on Atlas Cloud! It gives developers ByteDance's newest video model. It generates up to 30 seconds of native video in a single pass from text, a single image, or as many as 50 multimodal references, with syn…
Wan 3.0
Wan 3.0 API is the next generation of Alibaba's Wan video family, built to push long-form generation, multi-reference control, and audiovisual quality to new heights. Atlas Cloud already hosts Wan 2.7, 2.6, and 2.5, and Wan 3.0 runs on the…
MiniMax H3
MiniMax H3 is MiniMax's multimodal video family for text, image, and reference guided creation. Across supported routes, it preserves subjects from reference media, offers flexible aspect ratios, and pairs generated sound with visuals throu…
GPT Image 2.5
The gpt-image-2.5 family from OpenAI gives developers a choice of Flare and Sunburst for production image workflows. Render at arbitrary resolutions up to 3840x2160 and select from five quality tiers, including xhigh and max, to match speci…
Seedream 5.0 Pro
Seedream 5.0 Pro API gives developers ByteDance's controllable image editing model on Atlas Cloud. It places edits precisely with anchors and coordinates, separates images into editable layers, fuses multiple references, and matches exact c…
Kling 4.0
Developed by Kuaishou, Kling V4 is an video model built for professional production. It pairs stable complex motion with a 21:9 ultrawide format and targeted editing for expressions, camera angles, backgrounds, visual styles, and dialogue.…
Seedance 2.5
Seedance 2.5 API is now available on Atlas Cloud! It gives developers ByteDance's newest video model. It generates up to 30 seconds of native video in a single pass from text, a single image, or as many as 50 multimodal references, with syn…
Wan 3.0
Wan 3.0 API is the next generation of Alibaba's Wan video family, built to push long-form generation, multi-reference control, and audiovisual quality to new heights. Atlas Cloud already hosts Wan 2.7, 2.6, and 2.5, and Wan 3.0 runs on the…
MiniMax H3
MiniMax H3 is MiniMax's multimodal video family for text, image, and reference guided creation. Across supported routes, it preserves subjects from reference media, offers flexible aspect ratios, and pairs generated sound with visuals throu…
Seedance 2.0
Seedance 2.0 is ByteDance’s production video model for precise shot creation. Turn prompts into video, animate a first-frame image with optional last-frame guidance, or shape results with reference media and optional web search. Atlas Cloud…
Kling V3.0
From Kuaishou, the Kling V3 API family supports text, image, and reference video workflows. Transfer motion while preserving character identity, guide generation with visual references, and edit videos through natural language commands. Atl…
Grok Imagine Video
Grok Imagine Video gives developers access to xAI’s video family for creating, animating, extending, and editing clips. Generate 1 to 15 second videos from prompts, guide people, objects, or styles with up to seven reference images, and wor…
Vidu Q4 Preview
Vidu Q4 is Vidu's latest flagship video model, designed for image-to-video and reference-to-video generation. It can animate a single still image and create automatic scene transitions, giving developers two input paths for different produc…
Gemini Omni 1.1 Flash
Gemini Omni 1.1 Flash is Google DeepMind’s natively multimodal video family for flexible production workflows. Edit existing footage through text instructions, maintain visual consistency with up to 10 reference images and 3 video clips, or…
Seedance 2.0 Mini
The Seedance 2.0 Mini API is the lightest, lowest-cost tier of ByteDance's Seedance video line, built for teams where throughput and unit cost matter more than maximum polish. Use it for batch generation, rapid prototyping, and draft passes…
Wan 2.7
The Wan 2.7 API gives developers Alibaba's all-in-one video suite, covering text to video, image to video, reference to video, and video editing, plus image generation. It produces native 1080p clips up to 15 seconds with synced audio, firs…
Veo 3.1
Veo 3.1 is Google DeepMind's video generation family for cinematic production. It supports first and last frame control, up to three reference images for subject consistency, and scene extension with visual and audio continuity. Atlas Cloud…
Happyhorse 1.1
HappyHorse 1.1 is Alibaba's video generation family for developers working from text, source frames, or visual references. It turns prompts into clips, animates a chosen first frame with optional guidance, and can use one to nine reference…
Pixverse V6
Pixverse v6 is PixVerse's AI video generation model family for developers who need precise creative control. Prompts accept up to 5,000 characters, reference generation supports as many as seven images, and seeded requests help reproduce ou…
Youchuan
The Youchuan API now covers both the V8.1 and V8.2 generations, spanning stills and motion. Prompt-driven modes return four variations at once, images render at native 2K HD with no upscaling pass, blends fuse up to five references, and a s…
Vidu Q2
Vidu Q2 is a video generation family designed for controllable production workflows. Define start and end frames to shape a sequence, animate static visuals with smooth motion, and choose Turbo, Pro, or Pro Fast variants for different workf…
Ltx 2.3
ltx 2.3 is Lightricks' video generation family for cinematic creation across Fast and Pro workflows. Fast models can produce clips up to 20 seconds at 720p or 1080p, while image workflows can animate a first frame and optionally interpolate…
Vidu Q3
Vidu Q3 is Vidu's model family for polished video generation and visual storytelling. Its Pro, Turbo, Q3, and Q3-Mix options produce smooth motion, rich detail, multiple visual styles, intelligent camera switching, and fluid scene transitio…
Hailuo 02
Hailuo 02 is Hailuo AI’s video generation family, built for developers who need flexible performance across multiple tiers. Its Standard model delivers a verified 2.5x efficiency improvement and an 85% complex instruction response rate for…
Kling 2.6
Kling v2.6 is Kuaishou's video model family for cinematic text-to-video and image-to-video creation, AI avatars, and reference-driven motion transfer. It supports flexible aspect ratios, enhanced dynamics, stable identity, and temporal cons…
Grok Imagine Video 1.5
Grok Imagine Video 1.5 is xAI's video generation family for developers who need controlled motion from prompts and visual inputs. Animate a starting frame with natural language motion instructions, select 480p or 720p for reference workflow…
Kling 1.6
From Kuaishou, Kling 1.6 uses image references to maintain subject consistency in scenes with multiple characters or objects. Its Multi I2V Pro variant improves coherence and motion tracking, while I2V Pro offers smoother motion blending an…
Kling 2.1
Kling v2.1 is Kuaishou's AI video model family for developers building production video workflows. The family supports rapid 720p drafting, sharp and fluid image animation, professional visual depth, complex prompt interpretation, advanced…
MiniMax H3 Max
MiniMax H3 Max from MiniMax creates cinematic video and supports optional last frame guidance when animating a source image, giving developers more control over how each shot resolves. Atlas Cloud provides pay as you go access through an Op…
Grok Imagine Video 1.5 Lite
Grok Imagine Video 1.5 Lite is xAI's lowest-cost model in the Grok Imagine video family, built for integrated visual and sound generation from prompts or source images. It supports speech aligned to mouth movement and selectable output qual…
Vidu Q1
Vidu Q1 is Vidu's multimode video generation family for developers building controllable visual workflows. Create clips from text prompts, a source image, visual references, or defined start and end frames, choosing the input path that fits…
PixVerse C1
Pixverse c1 is PixVerse's first AI video model created specifically for film production. Its action engine, cinematic visual effects, reference-guided consistency, and multi-panel storyboard conversion support coherent, controllable multi-s…
Luma Ray
Luma Ray 3.2 API delivers Luma's Ray 3.2 video model through Atlas Cloud, the update that lets creators direct AI video frame by frame rather than just prompt it. Generate cinematic clips from text or a first frame, restyle a source video w…
MiniMax H3 Fast
MiniMax H3 Fast is MiniMax’s prompt-driven video generation family for cinematic text-to-video, controllable first-frame animation with an optional last frame, and reference-based clips that retain the source subject. Access every workflow…
Seedance 2.0 Fast
Seedance 2.0 fast is ByteDance’s video generation family for rapid production workflows. It turns text prompts into video with native audio, animates a first-frame image with an optional last frame, and accepts multimodal references for con…
FLUX 3
The FLUX 3 API brings Black Forest Labs' newest foundation model to your stack, a single Self-Flow architecture trained jointly on images, video, and audio. Generate clips up to 20 seconds carrying multilingual dialogue, sound effects, and…
VEED
Perfect for AI Avatar Video Creation
Kling 2.0
Kling 2.0 is Kuaishou's video generation model family for text-to-video and image-to-video creation. Its Master models pair high-fidelity visuals with refined lighting and camera realism, giving developers two focused workflows for turning…
Kling 2.5 Turbo Pro
Kling v2.5 Turbo Pro is Kuaishou's Kling video generation model for turning prompts and source images into polished clips. It delivers cinematic motion precision and enhanced temporal stability, helping scenes remain coherent as subjects an…
Kling o1
Kling O1 is Kuaishou's video model family built with Multi-modal Visual Language technology. Its text-to-video and image-to-video workflows connect language and visual context to create seamless scene dynamics from prompts or source images.…
Avatar Omni Human 2.0
ByteDance's Avatar Omni Human 2.0 is an audio-driven model for character animation. Support for multi-person scenes and dynamic gestures extends avatar creation to shared performances with expressive character movement. On Atlas Cloud, inte…
Vidu
Vidu is Shengshu Technology's video generation family, created for coherent motion and stable subjects across changing shots. The Q series supports multi subject control, intelligent camera switching, smooth motion, and synchronized audio a…
Avatar Omni Human 1.5
Gemini Omni Flash
Gemini Omni is Google DeepMind's natively multimodal video family for prompt guided creation and editing. Generate from text, animate still images, or revise existing footage with optional visual references while preserving untouched conten…
Hailuo 2.3
Built by MiniMax, Hailuo 2.3 brings professional video generation to creative and production workflows. Standard and Pro pair reliable prompt fidelity with advanced motion, physics realism, cinematic visuals, detailed scene evolution, and c…
Wan 2.6
The Wan 2.6 API builds a multi-shot story from one prompt instead of a single clip. Alibaba's storytelling engine cuts between shots with coherent transitions while holding character identity, voice, and style steady across the scene. It sp…
Flux.2 Image Models
Developed by Black Forest Labs, FLUX.2 is a powerhouse 32-billion parameter rectified flow Transformer model that redefines creative workflows by unifying AI image generation, editing, and composition. It transforms complex text prompts int…
Seedance 1.5 Pro
Seedance 1.5 Pro API brings ByteDance's audio-video model to developers through one endpoint. It generates video with synchronized native audio and multilingual lip sync, follows cinematic camera moves such as pans, orbits, and zooms, and k…
Ltx 2.3
Ltx 2.5, from Lightricks' LTX-2 family, turns text or a first-frame image into cinematic video with synchronized audio, while audio-to-video follows a driving dialogue, music, or ambient track and lets that audio determine duration. Choose…
Happy Horse 1.0
HappyHorse 1.0 belongs to Alibaba's video generation family for developers building controllable visual workflows. Create video from text or a first frame, guide identity and style with one to nine reference images, or transform existing fo…
Veo 3.1 Lite
Veo 3.1 Lite is Google's video model family for developers building scalable production pipelines. Depending on the endpoint, use flexible duration options, create an 8 second transition between defined first and last frames, or generate in…
Veo 3.1 Fast
Veo 3.1 Fast is Google's speed-focused video generation family, built for responsive production workflows and rapid creative iteration. Its prompt and keyframe workflows maintain impressive visual fidelity while producing smooth, expressive…
Seedance
Seedance 1 Pro is ByteDance's video generation family for cinematic, multi-shot creation. It maintains scene continuity across cuts and transforms still visuals into expressive motion with consistent detail from frame to frame. On Atlas Clo…
Nvidia Cosmos
Explore Nvidia Cosmos API on Atlas Cloud.
Van
Van is a flagship AI video series built on the Wan 2.5 and 2.6 frameworks, and the Van API unifies its full text-to-video and image-to-video lineup on Atlas Cloud. Render cinematic clips up to 1080p, then pick speed-optimized 2.6 models for…
Wan 2.5
The Wan 2.5 API produces video and audio in one pass, so voice, sound, and lip-sync line up without a separate step. Built on Alibaba's Diffusion Transformer architecture, it covers text and image to video from 480p to 1080p at 5 or 10 seco…
Wan
The Wan API brings Alibaba's open Wan video models to Atlas Cloud through one unified key. Wan 2.2 pioneered a Mixture-of-Experts architecture for video diffusion, lifting capacity and motion control at the same inference cost. It handles t…
Tools
Open, advanced large-scale image generative models that power high-fidelity creation and editing with modular APIs, reproducible training, built-in safety guardrails, and elastic, production-grade inference at scale.
GPT Image 2.5
The gpt-image-2.5 family from OpenAI gives developers a choice of Flare and Sunburst for production image workflows. Render at arbitrary resolutions up to 3840x2160 and select from five quality tiers, including xhigh and max, to match speci…
Seedream 5.0 Pro
Seedream 5.0 Pro API gives developers ByteDance's controllable image editing model on Atlas Cloud. It places edits precisely with anchors and coordinates, separates images into editable layers, fuses multiple references, and matches exact c…
Nano Banana 2.1
Nano Banana 2.1 is Google's image model family built on Gemini 3.6 Flash. It delivers Pro-level generation and editing at Flash-level speed, supports natural-language edits and merges across 1 to 14 input images, and maintains consistency f…
Nano Banana 2
Build with the Nano Banana 2 API, powered by Google's Gemini 3.1 Flash Image model. It generates native 4K visuals up to 4096x2304 with accurate text rendering and consistent characters across up to 14 reference images for both generation a…
GPT Image 2
The GPT Image 2 API gives developers access to OpenAI's latest image model, the successor to GPT Image 1.5. It generates and edits images with accurate text rendering across Latin and CJK scripts, plus strong composition for posters, mockup…
Grok Imagine Image 2.0
Built by xAI, Grok Imagine Image 2.0 combines polished text-to-image generation with natural-language editing for reference-based workflows. Produce 1K or 2K outputs, move from a prompt to a finished visual, and refine existing images with…
Wan 2.7
The Wan 2.7 API gives developers Alibaba's all-in-one video suite, covering text to video, image to video, reference to video, and video editing, plus image generation. It produces native 1080p clips up to 15 seconds with synced audio, firs…
Seedream 5.0 Lite
The Seedream 5.0 Lite API brings ByteDance's reasoning-first image model to Atlas Cloud. It is the first image model to pair real-time web search with visual reasoning, grounding generation in live information and real-world physics, with n…
Nano Banana 2 Lite
The Nano Banana 2 Lite API brings Google's Gemini 3.1 Flash-Lite image model to Atlas Cloud, the fastest and most cost-efficient tier in the Nano Banana family. It generates and edits images in seconds while keeping the character consistenc…
Seedream 4.7
ByteDance's Seedream 4.7 API unifies text to image generation, precise editing, and sequential image workflows in one family. It follows instructions while preserving identity, lighting, and local structure in source images, and can produce…
Grok Imagine
Grok Imagine Image is xAI's family for generating polished visuals and revising one or more reference images through natural language instructions. Its standard and quality endpoints cover text to image creation, single image changes, and i…
HiDream
The HiDream O1 1.5 Image API brings HiDream.ai's unified foundation model to your stack, running text-to-image, single-image editing, and subject-driven personalization on one pixel-level system. Tune guidance and inference steps for strong…
Youchuan
The Youchuan API now covers both the V8.1 and V8.2 generations, spanning stills and motion. Prompt-driven modes return four variations at once, images render at native 2K HD with no upscaling pass, blends fuse up to five references, and a s…
Nano Banana Pro
Nano Banana Pro is Google's next-generation Nano Banana image model for production visual workflows. It generates images with sharper detail, richer color control, and faster diffusion, while dedicated editing endpoints support precise AI-p…
Luma Uni 1
The Luma Uni 1 API delivers Luma's first unified reasoning image model through Atlas Cloud, covering text-to-image, directable editing, and reference generation from up to 9 images. Uni-1 reasons through a prompt instead of matching keyword…
Seedream 5.0 Flash
Seedream v5.0 Flash is ByteDance’s image model family for generation, editing, and structured asset extraction. Its layer decomposition endpoint separates one image into a base image and up to 16 ordered PNG layers, complete with bounding b…
FLUX 3
The FLUX 3 API brings Black Forest Labs' newest foundation model to your stack, a single Self-Flow architecture trained jointly on images, video, and audio. Generate clips up to 20 seconds carrying multilingual dialogue, sound effects, and…
Qwen Image 3.0 Pro
Qwen Image 3.0 pro is Qwen's image generation and editing family for developers building production visual workflows. It creates images up to 2048×2048, rewrites prompts automatically, selects resolution from prompt intent, and follows natu…
Qwen Image 3.0
Qwen Image 3.0 is Qwen's image generation and editing family for developers building visual products. It combines precise prompt adherence and complex text rendering with automatic prompt rewriting and prompt guided resolution selection. Th…
Qwen Image 2.0 Pro
Qwen Image 2.0 pro comes from the Qwen model family and serves professional image generation and editing workflows. Advanced prompt and instruction understanding turns detailed creative direction into high quality new images or precise edit…
Qwen Image 2.0
Qwen Image 2.0 is the next generation image model from the Qwen team at Alibaba Cloud. Built for text and image inputs, it delivers native 2K output, stronger semantic adherence, realistic detail, and precise instruction following across cr…
Midjourney 8.2
Midjourney 8.2 brings Midjourney's image and video creation family to developers through Atlas Cloud. Generate from text, reimagine or restyle existing images, blend two to five inputs, remove backgrounds, or animate an image into four 5-se…
Krea
The Krea API delivers Krea 2 Turbo, the speed-optimized open-source variant of Krea 2 from Krea, with its signature aesthetic range fully intact. Feed it a text prompt and it renders sharp, detailed images in one quick pass, well suited to…
Seedream 4.5
The Seedream 4.5 API brings ByteDance's latest image model to developers through one endpoint. It unifies 4K text-to-image generation with reference-based editing, rendering accurate typography and keeping subjects consistent across up to 1…
Qwen Image
Qwen Image is Alibaba's Tongyi Qianwen family for image generation and editing, built to render complex Chinese and English text across varied visual styles. Its 20B MMDiT models support detailed creation, in image text changes, object mani…
Nano Banana
Nano Banana brings Google’s Gemini image generation and editing models to developers through Atlas Cloud. Create visuals from text or revise existing images, then deliver them in PNG or JPEG across square, portrait, landscape, and ultrawide…
Wan 2.6
The Wan 2.6 API builds a multi-shot story from one prompt instead of a single clip. Alibaba's storytelling engine cuts between shots with coherent transitions while holding character identity, voice, and style steady across the scene. It sp…
Flux.2 Image Models
Developed by Black Forest Labs, FLUX.2 is a powerhouse 32-billion parameter rectified flow Transformer model that redefines creative workflows by unifying AI image generation, editing, and composition. It transforms complex text prompts int…
MAI Image 2.6
MAI Image 2.6 is Microsoft AI's image generation and editing family for photorealistic, design-ready output. Its flagship and Flash variants offer natural language generation, improved in-image text rendering, model-directed aspect ratios,…
MAI Image 2.5
The MAI Image 2.5 API delivers Microsoft's photorealistic image generation and editing family through one endpoint, spanning text-to-image and editing in standard and Flash variants. Alongside reliable in-image text, it produces natural por…
Seedream v4
Seedream v4 is ByteDance's advanced large scale image model, and the Seedream v4 API brings it to production with native 4K output, both text and image inputs, precise prompt based editing, and consistent multi image sequences of up to 14 f…
Nvidia Cosmos
Explore Nvidia Cosmos API on Atlas Cloud.
Ideogram
The Ideogram Image API brings Ideogram AI's typography-first model to Atlas Cloud, built to solve the text rendering that defeats generic image models. Its V4 lineup produces crisp posters, logos, and T-shirt graphics with correct spelling,…
GPT Image 1 Mini
GPT Image 1 MINI is OpenAI's cost-efficient, natively multimodal model for image creation. Powered by GPT-5 language understanding, it generates high-quality visuals from prompts and edits supplied images while preserving intent across crea…
GPT Image 1.5
GPT Image 1.5 is OpenAI's image model, powered by GPT-5 guidance for precise visual creation. Turn natural-language prompts into photorealistic scenes, product renders, concept art, and stylized graphics, then refine images with object chan…
Wan 2.5
The Wan 2.5 API produces video and audio in one pass, so voice, sound, and lip-sync line up without a separate step. Built on Alibaba's Diffusion Transformer architecture, it covers text and image to video from 480p to 1080p at 5 or 10 seco…
Tools
Open, advanced large-scale image generative models that power high-fidelity creation and editing with modular APIs, reproducible training, built-in safety guardrails, and elastic, production-grade inference at scale.
Seed
The Doubao Seed API opens ByteDance's full Seed lineup, from the flagship Seed 2.1 Pro to a dedicated Code Preview and the efficient Lite and Mini tiers. Every model handles deep reasoning, agentic planning, and repository-scale coding, wit…
DeepSeek
Access the full DeepSeek API on Atlas Cloud! A unified OpenAI-compatible endpoint covering every model in the DeepSeek lineup. Whether you need the DeepSeek V4 API for frontier-grade reasoning, the DeepSeek V4 Pro API for 1M-token long-cont…
GLM
GLM is Z.ai's flagship LLM series from Zhipu AI, and the GLM API spans everything from the agentic GLM-5 to the efficient 357B MoE GLM-4.6. These models specialize in autonomous task execution, complex agent orchestration, and production-gr…
GPT 6 Astra
GPT 6 Astra is OpenAI’s most intelligent and aligned model, built for demanding computer use, web browsing, software engineering, cybersecurity, science, and professional work. Its judgment supports complex workflows across code, research,…
Tencent Hy3
Tencent Hunyuan-Hy3 is an open-source Mixture-of-Experts (MoE) model featuring a integrated fast-and-slow thinking mechanism. With 295B total (21B active) parameters and a 256K context window, it delivers flagship-level performance with exc…
Grok
The Grok API gives developers xAI's Grok models on Atlas Cloud through one OpenAI-compatible key. It covers two models: Grok 4.3, an advanced reasoning model with a 1M token context window for long-document analysis and agentic workflows, a…
Kimi
Kimi API is Moonshot AI's open-weight K2 line, from the natively multimodal K2.5 to the coding-specialized K2.7 Code. Because vision is built into the model, you can turn screenshots, UI mockups, and short videos into working frontend code,…
MiniMax
As a premier suite of Large Language Models (LLMs) developed by MiniMax AI, MiniMax is engineered to redefine real-world productivity through cutting-edge artificial intelligence. The ecosystem features MiniMax M2.5, which is purpose-built…
ChatGPT
The ChatGPT API on Atlas Cloud brings OpenAI's newest GPT 5.6 family into one integration, spanning Sol for deep frontier reasoning, Terra for grounded production workloads, and Luna for natural conversation and content generation. Route ev…
Qwen
Qwen is Alibaba Cloud's large language model family, and the Qwen API opens the entire lineup to developers. Reach flagship Qwen3.7 Max for advanced reasoning and coding, efficient mixture-of-experts models across many scales, and Qwen3.5 F…
Gemini
The Gemini API opens Google's multimodal LLM family on Atlas Cloud, spanning Flash variants built for low-latency inference and Pro models tuned for advanced reasoning, coding, and long-context work, plus dedicated image generation. Route e…
Suno Chirp
The Suno Chirp API gives developers Suno's music generation models on Atlas Cloud through one key. From a text prompt and optional lyrics, it produces a full song with vocals and instrumentation, returning two variations per request, with i…
Gemini Flash TTS
Gemini Flash TTS is Google’s speech generation family for developers creating expressive audio from text. Choose Gemini 3.1 Flash for the latest generation, Gemini 2.5 Flash for controllable speech, or Gemini 2.5 Pro for studio quality. Pre…
MiniMax Speech 2.8
xAI TTS V1
xAI TTS v1 is xAI's high-fidelity text-to-speech model for converting written content into natural, expressive audio. It supports 20 languages and provides fine-grained delivery control for tailoring how speech sounds across applications. A…
MiniMax Lyrics
Minimax Lyrics is MiniMax's dedicated lyric-writing model for production-ready songwriting workflows. Refine unfinished lines, reorganize a draft, or extend an existing song while preserving its creative direction, then pass the result dire…
MiniMax Music 2.6
MimiMax Music 2.6 is MiniMax’s latest text-to-music model for developers building vocal and instrumental music experiences. Shape each song with a style prompt and lyrics, then organize its progression with supported section controls. Atlas…
MiniMax Music 3.0
MiniMax Music 3.0 brings MiniMax's 11.1B-parameter open-weights music model to developers. Shape song structure with section tags, supply optional lyrics, and choose vocal or instrumental output while the model handles composition, arrangem…
See Audio 1.0
Seed Audio 1.0 is ByteDance Doubao Voice's next-generation audio engine, designed to move creators beyond basic voice generation into directed narrative production. It streamlines audio engineering for publish-ready audiobooks, serialized e…
ElevenLabs
The ElevenLabs v3 API delivers the most expressive text-to-speech model from ElevenLabs, generating natural speech that carries genuine emotion. Inline audio tags like [whispers], [laughs], and [excited] shape delivery and tone, while multi…
Hunyuan 3D
The Hunyuan 3D API puts Tencent's Hunyuan3D foundation model in your stack, turning a text prompt or a single image into clean, watertight geometry through a two-stage shape and texture pipeline. Pick the Pro tier for up to 1.5M faces and 4…
Hi3D
Hi3D is Math Magic's image-to-3D family, powered by its in-house Sparc3D and Ultra3D models. It maintains structural fidelity, geometric accuracy, and texture consistency across four tiers, while v3.0 Master supports meshes up to 5 million…
Meshy 7
Meshy 7 is Meshy's 3D generation family for turning prompts, single images, or multiple references into textured assets. Its workflows support independent multi-view texture references, adjustable polygon budgets, optional PBR maps up to 8K…
Tripo
Tripo API brings Tripo3D's latest H3.1 engine to your stack, turning text prompts and single images into detailed 3D models. Generate dense meshes of up to 2 million polygons with configurable PBR materials, quad topology for rigging, and G…
Seed 3D
The Seed 3D API delivers ByteDance's Seed3D V2.0, a second-generation foundation model that turns a single image into a fully textured 3D asset with unified PBR maps for albedo, normal, metallic, and roughness produced in one pass. Its coar…
Recently Added
Seedance 2.5 Reference-to-Video
Multimodal video generation from reference images, videos, and audio. Supports video editing and extension.
Seedance 2.5 Text-to-Video
Generate videos from text prompts with native audio and optional web search.
MiniMax H3 Max Text-to-Video
MiniMax H3 Max text-to-video: generate a cinematic video from a text prompt. Supports 480P、768P, 5-15s., and 16:9/9:16/1:1/adaptive aspect ratios.
MiniMax H3 Max Image-to-Video
MiniMax H3 Max image-to-video: animate a first-frame image (optionally with a last frame) driven by a text prompt. Supports 480P、768P, 5-15s.
