--- title: MiniMax H3 Reference2Video API | Image to Video | ModelsLab description: Generate videos from images with MiniMax H3 Reference2Video. Smooth motion, high-quality output. Plans from $21/month. url: https://modelslab.com/models/modelslab/h3-minimax-r2v.md canonical: https://modelslab.com/models/modelslab/h3-minimax-r2v type: product component: Playground/Endpoint/Index generated_at: 2026-08-12T22:57:55.194293Z --- [![MiniMax H3 Reference2Video thumbnail](https://assets.modelslab.ai/api-logos/01KPMZY676ZM0Z7YJWBM9C78QP.png)](https://modelslab.com/models/modelslab)MiniMax H3 Reference2Video --- [by ModelsLab](https://modelslab.com/models/modelslab)MiniMax H3 is an open-weight multimodal AI video generation model capable of creating up to 15-second videos with native stereo audio from text, images, video, and audio inputs. It supports text-to-video, image-to-video, video editing, and video-to-video `h3-minimax-r2v` Open Source Model [LLMs.txt](https://modelslab.com/models/modelslab/h3-minimax-r2v/llms.txt) [API Playground](/models/modelslab/h3-minimax-r2v)API DocumentationVibe CodeRelated ModelsDeveloper SupportModel Specs Input --- Prompt Create a cinematic continuous sequence using the storyboard as the visual reference. Keep the character, face, clothing, environment and visual style consistent. Animate each shot naturally: the ronin wakes and looks toward the smoke, walks slowly through the abandoned village, notices the figure in the fog, draws his katana, then suddenly charges forward and strikes. After the attack, slow the movement as he examines the glowing symbols appearing on his sword. He raises the sword toward the stormy sky as lightning builds, then walks toward the distant fortress as the clouds begin to clear. Smooth cinematic camera movement, natural body motion, realistic hair and clothing movement, atmospheric fog, smoke and rain. Epic Japanese fantasy film aesthetic. Add subtle cinematic orchestral background music that gradually builds during the confrontation and becomes powerful as the fortress is revealed. Duration Reference Image URLs Add Images orAdd URL File preview Reference Video URLs Add Videos orAdd URL Reference Audio URLs Add Audios orAdd URL Advanced Settings Customize your input with more control. Configure Login to Generate Video costs **$0.08** per second at **768p** Output --- Idle Unknown content type Looking for something different? --- Models that trade off differently against the one you are viewing ### Better quality Newer flagship models that generally produce stronger results. [![Seedance 2.0 Multi Reference To Video ](https://images.modelslab.sh/?Image=https://assets.modelslab.ai/generations/d0ffddce-bbae-4711-90b2-3b9289ca42ab.webp)](https://modelslab.com/models/byteplus/seedance-2-multi-reference-video)[BytePlus](https://modelslab.com/models/byteplus) [Seedance 2.0 Multi Reference To Video](https://modelslab.com/models/byteplus/seedance-2-multi-reference-video) [![Seedance 1.5 Pro](https://images.modelslab.sh/?Image=https://assets.modelslab.ai/generations/1cdda423-9013-441b-81b0-543f839bf8cf.webp)](https://modelslab.com/models/byteplus/seedance-1-5-pro)[BytePlus](https://modelslab.com/models/byteplus) [Seedance 1.5 Pro](https://modelslab.com/models/byteplus/seedance-1-5-pro) [![Seedance 2.0 Start/End Frame To Video](https://images.modelslab.sh/?Image=https://assets.modelslab.ai/generations/ca79b12d-194b-498a-83a3-7ae6c707b36e.webp)](https://modelslab.com/models/byteplus/seedance-2-start-end-frame-video)[BytePlus](https://modelslab.com/models/byteplus) [Seedance 2.0 Start/End Frame To Video](https://modelslab.com/models/byteplus/seedance-2-start-end-frame-video) [![LTX 2 PRO Image To Video ](https://images.modelslab.sh/?Image=https://assets.modelslab.ai/generations/c1f3b2ed-f802-4ce1-a425-5fbce6ffd5e3.webp)](https://modelslab.com/models/ltx/ltx-2-pro-i2v)[LTX](https://modelslab.com/models/ltx) [LTX 2 PRO Image To Video](https://modelslab.com/models/ltx/ltx-2-pro-i2v) [![Grok Imagine Text To Video ](https://images.modelslab.sh/?Image=https://assets.modelslab.ai/generations/66741ffe-f704-47ef-92d5-32fec90bcc7a.webp)](https://modelslab.com/models/xai/grok-imagine-video-t2v)[xAI](https://modelslab.com/models/xai) [Grok Imagine Text To Video](https://modelslab.com/models/xai/grok-imagine-video-t2v) [![WAN 2.7 Image To Video](https://images.modelslab.sh/?Image=https://assets.modelslab.ai/generations/664e4096-e396-409f-96d6-17142ab59c41.webp)](https://modelslab.com/models/alibaba_cloud/wan2.7-i2v)[Alibaba](https://modelslab.com/models/alibaba_cloud) [WAN 2.7 Image To Video](https://modelslab.com/models/alibaba_cloud/wan2.7-i2v) ### Faster turnaround Built for speed when you are iterating on a prompt. [![Happyhorse 1.1 Image To Video ](https://images.modelslab.sh/?Image=https://assets.modelslab.ai/generations/23489cc6-cd6a-4f36-8d60-d59a71dd9624.webp)](https://modelslab.com/models/alibaba_cloud/happyhorse-1.1-i2v)[Alibaba Cloud](https://modelslab.com/models/alibaba_cloud) [Happyhorse 1.1 Image To Video](https://modelslab.com/models/alibaba_cloud/happyhorse-1.1-i2v) [![Happyhorse 1.1 Text To Video ](https://images.modelslab.sh/?Image=https://assets.modelslab.ai/generations/c19c7e8c-26d6-4954-ac16-a5638c84abc8.webp)](https://modelslab.com/models/alibaba_cloud/happyhorse-1.1-t2v)[Alibaba Cloud](https://modelslab.com/models/alibaba_cloud) [Happyhorse 1.1 Text To Video](https://modelslab.com/models/alibaba_cloud/happyhorse-1.1-t2v) [![Happyhorse 1.1 Reference To Video](https://images.modelslab.sh/?Image=https://assets.modelslab.ai/generations/bb1db5a4-c39b-4338-a44b-70c82f461272.webp)](https://modelslab.com/models/alibaba_cloud/happyhorse-1.1-r2v)[Alibaba Cloud](https://modelslab.com/models/alibaba_cloud) [Happyhorse 1.1 Reference To Video](https://modelslab.com/models/alibaba_cloud/happyhorse-1.1-r2v) Related Models --- Discover similar models you might be interested in [View all Video Models](https://modelslab.com/models?feature=videogen) [![happyhorse-1.0-video-edit](https://images.modelslab.sh/?Image=https://assets.modelslab.ai/generations/949b575a-34dd-471a-89be-094d466c2658.png)](https://modelslab.com/models/alibaba_cloud/happyhorse-1.0-v2v)[Alibaba Cloud](https://modelslab.com/models/alibaba_cloud) [happyhorse-1.0-video-edit Closed Source Model](https://modelslab.com/models/alibaba_cloud/happyhorse-1.0-v2v) [![Gemini Omni — Image To Video](https://images.modelslab.sh/?Image=https://assets.modelslab.ai/generations/2fc4ca82-5714-445e-ba24-9ce66de9d44b.webp)](https://modelslab.com/models/google/gemini-omni-image-to-video)[Google](https://modelslab.com/models/google) [Gemini Omni — Image To Video Closed Source Model](https://modelslab.com/models/google/gemini-omni-image-to-video) [![wan2.6 Image To Video (Flash)](https://images.modelslab.sh/?Image=https://assets.modelslab.ai/generations/118afa95-ea11-4749-8b78-d513b799afcd.webp)](https://modelslab.com/models/alibaba_cloud/wan2.6-i2v-flash)[Alibaba Cloud](https://modelslab.com/models/alibaba_cloud) [wan2.6 Image To Video (Flash) Closed Source Model](https://modelslab.com/models/alibaba_cloud/wan2.6-i2v-flash) [![CogVideoX](https://images.modelslab.sh/?Image=https://pub-3626123a908346a7a8be8d9295f44e26.r2.dev/livewire-tmp/VmhYqa98ohanHj8vL6mQjkr5TG2sSS-metaY29ndmlkZW94LndlYnA=-.webp)Popular](https://modelslab.com/models/modelslab/cogvideox)[ModelsLab](https://modelslab.com/models/modelslab) [CogVideoX Open Source Model](https://modelslab.com/models/modelslab/cogvideox) [![Kling 3.0 Motion Control](https://images.modelslab.sh/?Image=https://assets.modelslab.ai/generations/7daa7ece-d55e-441e-80fa-dedd8e1a0c7b.webp)](https://modelslab.com/models/klingai/kling-v3-motion-control)[Kling AI](https://modelslab.com/models/tencent) [Kling 3.0 Motion Control Closed Source Model](https://modelslab.com/models/klingai/kling-v3-motion-control) [![Kling V2.1 Image To Video ](https://images.modelslab.sh/?Image=https://assets.modelslab.ai/generations/17b21170-bd49-4758-b9c0-9475512d71d6.webp)](https://modelslab.com/models/klingai/kling-v2-1-i2v)[Kling AI](https://modelslab.com/models/tencent) [Kling V2.1 Image To Video Closed Source Model](https://modelslab.com/models/klingai/kling-v2-1-i2v) View all 18 related models About MiniMax H3 Reference2Video --- MiniMax H3 Reference2Video is a video generation AI model by ModelsLab available on ModelsLab. Access MiniMax H3 Reference2Video through our API with pay-per-use pricing and no minimum commitments. ### Technical Specifications Model IDh3-minimax-r2v ProviderModelsLab CategoryVideo Models TaskVideo Generation Price$0.05 per second of output AddedAugust 12, 2026 ### Key Features - AI video generation from text or image input - Motion control and camera movement parameters - Adjustable frame rate and video duration - High-quality cinematic output up to 1080p - Native audio generation support ### Quick Start Integrate MiniMax H3 Reference2Video into your application with a single API call. Get your API key from the [pricing page](https://modelslab.com/pricing) to get started. PythonJavaScriptcURLPHP ``` import requests import json url = "https://modelslab.com/api/v6/video/img2video" headers = { "Content-Type": "application/json" } data = { "model_id": "h3-minimax-r2v", "prompt": "your prompt here", "key": "YOUR_API_KEY" } try: response = requests.post(url, headers=headers, json=data) response.raise_for_status() # Raises an HTTPError for bad responses (4XX or 5XX) result = response.json() print("API Response:") print(json.dumps(result, indent=2)) except requests.exceptions.HTTPError as http_err: print(f"HTTP error occurred: {http_err} - {response.text}") except Exception as err: print(f"Other error occurred: {err}") ``` ### Pricing MiniMax H3 Reference2Video API costs $0.05 per second of output. Pay only for what you use with no minimum commitments. [View pricing plans](https://modelslab.com/pricing) ### Use Cases - Marketing and promotional video creation - Social media short-form video content - Product demos and explainer videos - Creative storytelling and animation [Browse Video Models](https://modelslab.com/models?feature=videogen) [More from ModelsLab](https://modelslab.com/models/modelslab) [View Pricing](https://modelslab.com/pricing) MiniMax H3 Reference2Video FAQ --- ### What is MiniMax H3 Reference2Video? MiniMax H3 Reference2Video is a video generation AI model by ModelsLab available on ModelsLab. Access it through our API with pay-per-use pricing and no minimum commitments. ### How do I use the MiniMax H3 Reference2Video API? You can integrate MiniMax H3 Reference2Video into your application with a single API call. Sign up on ModelsLab to get your API key, then use the model ID "h3-minimax-r2v" in your API requests. We provide SDKs for Python, JavaScript, and cURL examples in the API documentation. ### How much does MiniMax H3 Reference2Video cost? MiniMax H3 Reference2Video costs $0.05 per second of output. ModelsLab plans start at $21/month (Basic), and the $149/month Open Source plan includes unlimited generation on open-source models. ### What is the MiniMax H3 Reference2Video model ID? The model ID for MiniMax H3 Reference2Video is "h3-minimax-r2v". Use this ID in your API requests to specify this model. ### Do I need a paid plan to use MiniMax H3 Reference2Video? Yes. ModelsLab is subscription-based with no free tier — plans start at $21/month (Basic, 3,250 API calls). The $149/month Open Source Unlimited plan includes unlimited generation across open-source models; premium third-party models are billed per call from your wallet. --- *This markdown version is optimized for AI agents and LLMs.* **Links:** - [Website](https://modelslab.com) - [API Documentation](https://docs.modelslab.com) - [Blog](https://modelslab.com/blog) --- *Generated by ModelsLab - 2026-08-13*