AI Video Generation API
Call Veo 3.1, Seedance 2.5, Kling V3, Wan 3.0, Hailuo 2.3 and more through one API key. Text-to-video and image-to-video with per-model pricing, and every model is 20% off the list price.
Text-to-Video and Image-to-Video API Models
Every video model below shares the same APIMart key, async task workflow and billing. Open a model to see its parameters, pricing table and code examples.
FLUX 3 Video API
FLUX 3 Video by Black Forest Labs supports text-to-video, image-to-video with 1–10 ordered keyframes, video continuation, and draft enhancement. Generate synchronized audio with 5–20 second HD or FHD output, configurable safety tolerance, and results stored on the APIMart CDN.
Native Audio5–20 SecondsOrdered KeyframesHD and FHDView API & pricing →Wan 3.0 API
Wan 3.0 API (Wan API) provides access to Alibaba Cloud's all-in-one video model. Wan API offers general, first-and-last-frame, and file or webpage generation. Wan API general generation accepts prompts with optional image, video, and audio references. Wan API frame generation requires a first frame and allows an optional last frame. One asynchronous Wan API endpoint creates 2–30 second videos at 480P, 720P, or 1080P with optional output audio.
Three Generation EntriesUp to 30 Seconds480P–1080PMultimodal ReferencesView API & pricing →Veo 3.1 API
Veo 3.1 API on APIMart provides access to both veo3.1-fast and veo3.1-quality models, the newest generation of the Google Veo 3 API. Veo 3.1 is Google DeepMind's upgrade to Veo 3, offering enhanced audiovisual quality, native synchronized audio, and advanced cinematic controls for professional video creation.
Commercial UseView API & pricing →Gemini Omni 1.1 Flash API
Gemini Omni 1.1 Flash is Google's GA Gemini Omni API model for multimodal video, supporting generation, natural-language editing, frame interpolation, and video extension. APIMart provides it through a dedicated official channel with asynchronous task tracking and resolution-based billing. Through the Omni Flash API, Gemini Omni Flash is billed by output resolution, and the live table on this page shows current Google Omni pricing for each tier.
Multimodal VideoFirst-Last Frame360p to 4KView API & pricing →Gemini Omni 1.1 Flash Ext API
Gemini Omni 1.1 Flash Ext API on APIMart provides streamlined text-to-video generation with the gemini-omni-1.1-flash-ext model. Send model, prompt, duration, resolution, size, and optional image_urls through APIMart's unified video generation endpoint, making gemini-omni-1.1-flash-ext easy to test, integrate, and scale.
Text to VideoFast GenerationSimple APIView API & pricing →Gemini Omni Flash Preview API
Gemini Omni Flash Preview API on APIMart provides streamlined text-to-video, image-to-video, and video-to-video generation with the Gemini-Omni-Flash-Preview model. Send model and prompt through APIMart's unified video generation endpoint, making Gemini-Omni-Flash-Preview easy to test, integrate, and scale.
Text to VideoImage to VideoVideo to VideoView API & pricing →PixVerse V6 API
PixVerse V6 API on APIMart gives developers access to a video model focused on precise control and native artistic expression. Use pixverse v6 for cinematic control, physics-aware motion, high-fidelity portraits, dynamic aesthetics, reference media guidance, and production-ready AI video workflows through one unified endpoint.
Text to VideoImage to VideoPrecise ControlView API & pricing →Kling V3 API
Kling V3 API on APIMart offers Kuaishou's latest AI video generation models — kling-v3-omni's all-in-one capabilities with multi-modal inputs, and kling-v3's cinematic excellence with up to 15-second video generation. Kling AI 3.0 is offered here as the Kling 3.0 API, so one APIMart key covers both models.
Commercial UseHigh QualityMulti-ModelView API & pricing →Kling V2.6 API
Kling 2.6 API on APIMart delivers battle-tested AI video generation with excellent cost-performance ratio. Features include audio generation, dynamic masks, camera control, and negative prompts for precise creative control.
Commercial UseAudio SupportCamera ControlView API & pricing →Kling 3.0 Turbo API
Kling 3.0 Turbo is Kuaishou's speed-optimized Kling AI video model on APIMart, built for an excellent speed-to-quality ratio. Tuned for low-latency production, it supports text-to-video, image-to-video, flexible aspect ratios, and negative prompts.
Commercial UseLow LatencyFast GenerationView API & pricing →Kling V2.6 Motion Control API
Kling Motion Control on APIMart uses a reference image plus a reference video to transfer subject motion into generated clips. Choose kling-v2-6-motion-control or kling-v3-motion-control, each with std and pro modes; output length follows the reference video and billing is per second. Add an optional prompt, set character orientation, and control sound or watermark settings. It brings Kling AI Motion Control to your own app through one API: choose Kling 2.6 Motion Control for the V2.6 model or Kling 3.0 Motion Control for V3.
Motion ControlReference ImageReference VideoCommercial UseView API & pricing →Kling Video O1 API
Kling Video O1 API on APIMart is Kuaishou's flagship AI video generation model. Powered by kling-video-o1's thinking-driven generation, it delivers the highest quality output through advanced reasoning capabilities for unmatched visual fidelity.
Flagship ModelThinking-DrivenHighest QualityView API & pricing →MiniMax Hailuo 02 API
MiniMax Hailuo 02 on APIMart is the latest generation AI video model, offering superior visual quality, high motion coherence, and professional-grade performance. Hailuo 02 (sometimes written Hailuo 2) uses the model ID MiniMax-Hailuo-02 in API requests.
Commercial UseHigh QualityView API & pricing →MiniMax Hailuo 2.3 API
MiniMax Hailuo 2.3 on APIMart is the latest generation AI video model, offering superior visual quality, high motion coherence, and professional-grade performance. Hailuo 2.3 is available as two model IDs, MiniMax-Hailuo-2.3 and MiniMax-Hailuo-2.3-Fast, with one API key.
Commercial UseHigh QualityView API & pricing →MiniMax H3 API
MiniMax H3 on APIMart is the latest generation AI video model, offering native 2K output, high motion coherence, multimodal references, and professional-grade performance.
Commercial UseHigh QualityView API & pricing →Vidu Q3 API
The Vidu Q3 Series offers two powerful AI video generation models: Pro delivers cinematic quality and stunning visual fidelity, while Turbo balances speed and quality for rapid iteration and bulk production.
Commercial UseHigh QualityFast GenerationView API & pricing →Vidu Q4 Preview API
Access the Vidu Q4 Preview API on APIMart with model ID viduq4-preview. Vidu supports one first frame or 1–15 reference images with optional reference audio, producing 3–16 second clips at up to 4K. Generated audio and seed control are available; it does not support text-only generation or end-frame control.
Image to VideoReference to Video3–16 SecondsUp to 4KView API & pricing →Wan 2.5 API
WAN 2.5 API on APIMart is a powerful AI video generation model, offering high visual quality, strong motion coherence, and reliable performance. Alibaba Wan 2.5 handles both text-to-video and image-to-video through one API.
Commercial UseHigh QualityView API & pricing →Wan 2.6 API
WAN 2.6 API on APIMart is the latest generation AI video model, offering superior visual quality, high motion coherence, and professional-grade performance. The wan2.6 API on APIMart includes three model IDs—wan2.6, wan2.6-i2v and wan2.6-i2v-flash—all callable with one key.
Commercial UseHigh QualityView API & pricing →Wan 2.7 API
WAN 2.7 API on APIMart is the latest generation AI video model, offering superior visual quality, high motion coherence, and professional-grade performance. For Wan I2V (image-to-video), set a first frame and an optional last frame on wan2.7, or use wan2.7-r2v for reference-driven video.
Commercial UseHigh QualityView API & pricing →Grok Imagine Video API
Grok Imagine Video API on APIMart handles text-to-video and Grok image to video with xAI's video models. Send a prompt, or add reference image URLs to animate a still image, and get high-quality videos with remarkable visual fidelity. This Grok video API exposes three Grok video model IDs—grok-imagine-video, grok-imagine-video-1.5 and grok-imagine-1.5-video-ext—under one APIMart key.
Video GenerationHigh QualityView API & pricing →SkyReels V4 API
The SkyReels V4 API on APIMart is Skywork AI's first unified video + audio foundation model. SkyReels V4 delivers 1080p at 32 FPS with 15-second clips, native audio, and cinematic multi-shot coherence in a single generation pass.
Video + Audio1080p / 32 FPSView API & pricing →Seedance 1.0 Pro API
Experience Seedance 1.0 Pro Fast video generation technology. Generate stunning videos with logical motion and high fidelity from text or images.
Commercial UseView API & pricing →Seedance 1.5 Pro API
Experience the power of Seedance 1.5 Pro video generation technology. Compared to previous Seedance versions, it offers smoother motion, higher image quality, and stronger instruction following capabilities.
Commercial UseNewSeedance 1.5 ProView API & pricing →Seedance 2.0 API
Seedance 2.0 API on APIMart is ByteDance's latest AI video generation model, delivering stunning visual quality, smooth motion, and professional-grade cinematic output. One Seedance API key gives you every Seedance 2 API variant—seedance-2.0, seedance-2.0-fast and seedance-2.0-mini.
Commercial UseHigh QualityView API & pricing →Seedance 2.5 API
Seedance 2.5 API exposes ByteDance's next-generation audio-video foundation model for production AI video with native 30-second single-pass clips, up to 50 multimodal references, first/last-frame control, region-level edits, and stronger continuity for ads, e-commerce, and film previs.
AI Video30s ClipsMultimodal ReferenceNative AudioView API & pricing →HappyHorse 1.0 API
HappyHorse 1.0 is Alibaba ATH-AI's unified multimodal video model, available on APIMart as the HappyHorse API. It generates 1080p video with synchronized native audio in a single forward pass, supports 7-language lip-sync, and ranks #1 on Artificial Analysis text-to-video and image-to-video leaderboards. Also written as Happy Horse 1.0, this HappyHorse AI video model sits next to the newer HappyHorse 1.1 in the same playground.
Text to VideoImage to VideoNative Audio1080pView API & pricing →
How to Choose a Video Generation API
Cinematic quality with native audio
Veo 3.1 and Seedance 2.5 generate video with synchronized sound and realistic physics, a good fit for ads, trailers and storytelling.
Image-to-video and character consistency
Kling V3, Seedance and Wan models animate a reference image while keeping the subject consistent, useful for product shots and avatars.
Motion control and camera moves
Kling V2.6 Motion Control transfers movement from a reference video, so you can direct actions and camera paths precisely.
Cost-efficient drafts at scale
Fast and lite variants such as Veo 3.1 Fast, Seedance 2.0 Fast and Hailuo 2.3 Fast keep per-second cost low for previews and batch generation.
AI Video Generation API FAQ
What is the best AI video generation API?
It depends on the job. Veo 3.1 leads on cinematic realism with audio, Seedance 2.5 and Kling V3 are strong for image-to-video and consistency, and fast variants suit high-volume drafts. APIMart lets you test them all with one key.
How much does a video generation API cost?
Video models are billed per second or per clip, depending on the model and resolution. Each model page shows the full pricing table, and every model is 20% off the list price, with membership tiers saving up to 28%.
Do you support text-to-video and image-to-video?
Yes. Most video models accept a text prompt, one or more reference images, or both. Supported inputs, durations and resolutions are listed on each model page.
How do I call a video generation API?
Create an API key, send a generation request with your prompt and parameters, then poll the task ID until the video is ready. The request format is consistent across models, so switching models only changes the model name.
Am I charged for failed video generations?
No. You only pay for successful generations; failed tasks are not billed.