APIXO documents text-to-video, image-to-video, and video extension workflows for the flux-3 endpoint.
我们注意到您可能偏好使用 简体中文. 要切换语言吗？
Il semble que vous préfériez Français. Souhaitez-vous changer de langue ?
Es scheint, Sie bevorzugen Deutsch. Möchten Sie die Sprache wechseln?
Parece que prefieres Español. ¿Te gustaría cambiar de idioma?
Sembra che tu preferisca Italiano. Vuoi cambiare lingua?
優先言語は次のようです 日本語. 言語を切り替えますか？
선호하시는 언어는 다음과 같습니다 한국어. 언어를 변경하시겠습니까?
Похоже, вы предпочитаете Русский. Хотите сменить язык?
Tercih ettiğiniz dil Türkçe. Dili değiştirmek ister misiniz?
Wygląda na to, że wolisz Polski. Czy chcesz zmienić język?
Black Friday: Up to 66% off most AI models.
Explore the deals
FLUX 3 is Black Forest Labs’ multimodal video model for short-form generation with native audio and multi-shot scene development. On APIXO, it supports text-to-video, image-to-video, start-and-end-frame animation, and video extension through an asynchronous endpoint with 720p or 1080p MP4 output.
Create with FLUX 3
Capabilities
What FLUX 3 brings to APIXO video generation
Prompt-driven video
Turn text prompts into short clips with configurable durations, aspect ratios, and resolutions. APIXO documents 5–20 second outputs and 720p or 1080p support for this workflow.
Image animation
Animate a single reference image or two start-and-end frames to create motion from a still source. The endpoint accepts image URLs and returns MP4 video after async processing.
Video extension
Extend an existing clip by supplying one public MP4 source URL. Extend an existing clip to continue its action, camera movement, or scene context beyond the original endpoint.
Audio-aware output
Audio is enabled by default through APIXO, making the model suitable for social promos, product demos, and short-form content where sound matters.
Reference-based control
Use image or video references to guide motion and scene context. This gives teams a practical path from a visual source to a generated video without relying on prompt-only generation.
Async integration
The endpoint is designed for asynchronous workflows, so developers can submit a task, poll for status, and retrieve MP4 URLs when generation completes.
Details
FLUX 3 API specifications
Core parameters documented for APIXO’s FLUX 3 endpoint.
Text prompt, 1 or 2 image URLs, or 1 MP4 URL
Input
Text-to-Video / Image-to-Video / Video Extend
Modes
MP4 video URLs
Output
5–20 Seconds
Duration
720p / 1080p
Resolution
From 170 Credits / second
Price
Use Cases
What FLUX 3 video workflows support on APIXO
Product marketing
Short-form ad loops
Launch short-form creatives from a prompt and a product still, then quickly test different aspect ratios and durations for paid social and landing-page hero videos.
Visual storytelling
Scene transitions
Animate a single reference frame or a start-and-end pair to build motion-led product reveals, mood boards, and scene transitions without manual editing.
Content extension
Clip continuation
Extend an uploaded source clip to create looped assets, forward motion, or continuity for ads, trailers, and branded social cutdowns.
Audiovisual Content
Native Audio Output
Generate video with sound enabled through APIXO, allowing speech, effects, and ambience to accompany the visual result without requiring a separate audio-generation request.
Quick Start
How to get started with FLUX 3 on APIXO
Move from prompt testing to production-ready video generation with a simple async workflow.
01
Try the playground
Prototype prompts, durations, and aspect ratios in the APIXO playground before wiring the endpoint into your app.
02
Submit an async task
Send the request with mode, prompt, duration, resolution, and any image or video references through the async endpoint.
03
Retrieve MP4 output
Poll the status endpoint and use the returned MP4 URLs once generation completes.
Notes & FAQ
FLUX 3 notes and implementation questions
Notes
01
APIXO currently documents three FLUX 3 video modes: text-to-video, image-to-video, and video extension.
02
Image-to-video accepts one image URL or two image URLs for a start-and-end-frame animation workflow.
03
Video extension requires exactly one public MP4 URL up to 50 MB and 15 seconds.
04
Audio is enabled by default with sound: true.
05
Supported durations are 5–20 seconds, and resolutions are 720p or 1080p.
Frequently Asked Questions
It accepts one image URL or two image URLs for a start-and-end-frame animation workflow.
The endpoint returns MP4 video URLs in the task result payload after the task reaches success.
Explore Other Models
Discover more AI models for your next creative workflow
Alibaba
Wan 3.0 Video
Create Wan 3.0 videos from text, images, reference audio, clips, files, or links. Guide motion with references, export up to 1080p, or use the APIXO API.
VideoNew
50 Credits/sec
VideoKuaishou
Kling 3.0 Omni
Use the Kling 3.0 Omni API for nine Standard, Pro, and 4K text-to-video, image-to-video, and reference-to-video modes from 84 Credits to 420 Credits per second.
VideoNew
84 Credits/secAlibaba
HappyHorse
Use Alibaba HappyHorse through APIXO for text, first-frame, multi-reference, and video-edit workflows with audio and 720p or 1080p output.
VideoNew
125 Credits/secByteDance
Seedance 2.5
Explore Seedance 2.5 for longer audiovisual storytelling, timeline direction, multimodal references, multilingual scenes, and selective video revision.
VideoNew
85 Credits/sec
MiniMax
MiniMax H3
Call MiniMax H3 through the APIXO API for 768p or 2K video with native stereo audio, from text, image, or mixed image/video/audio references. Text-to-video, image-to-video, and reference-to-video from one endpoint. Also known as Hailuo 3.0.
VideoNew
100 Credits/secGoogle
Gemini Omni
Use Gemini Omni on APIXO for multimodal video generation with image, source-video, reusable audio, and character references plus output up to 4K.
VideoNew
100 Credits/secAlibaba
Wan 2.7
Edit and generate videos with Wan 2.7 on APIXO. Supports video-to-video editing, multimodal reference, 1080p resolution, and synchronized audio.
VideoNew
100 Credits/secKuaishou
Kling 3.0 Std
Use Kling 3.0 Standard through APIXO for 3–15-second video generation, optional native audio, multi-shot prompts, and character motion transfer.
VideoNew
84 Credits/sec