MiniMax H3 is an open, general-purpose multimodal video model. It understands text, image, video, and audio inputs in a unified way, and supports video generation, reference-based creation, and video editing.
MiniMax H3, a general-purpose multimodal generation model. H3 understands unified context across text, images, video, and audio, generating video with native stereo sound, up to 15 seconds at 2K resolution.
Early testing shows H3 is ready for commercial content creation across a wide range of use cases, excelling at instruction following, accurate text and brand rendering, and V2V motion transfer. With precise, controllable multimodal generation and editing, H3 is built for advertising, branding, e-commerce, product design, UI/UX, gaming, and more.
Powered by technologies including Contextual Omni Representation, H3-VAE, H3-Omni Transformer, and In-Context Regeneration, H3 delivers industry-leading price-performance. We offer 2K resolution by default. At 2K, H3's per-second price is less than a third of mainstream models, and at 768p, it's less than half the price of mainstream models' 720p.
Closed-source models have long dominated video generation, with slower iteration and a less open ecosystem than fields like large language models. To support the open-source community, accelerate compatibility with a broader range of AI hardware, and make it easier for users to build their own customized versions, we plan to open up the model weights in the coming days, subject to applicable laws and regulations. Hardware compatibility has been a key consideration since the earliest stages of H3's design.
https://platform.minimax.io/docs/guides/video-generation
Highlights
H3 understands unified context across text, images, video, and audio, generating video with native stereo sound, up to 15 seconds at 2K resolution.
A wide range of use cases, excelling at instruction following, accurate text and brand rendering, and V2V motion transfer.
Open weights model, delivers industry-leading price-performance.
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Pricing is based on the duration and terms of your contract with the vendor. This entitles you to a specified quantity of use for the contract duration. If you choose not to renew or replace your contract before it ends, access to these entitlements will expire.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
You buy MiniMax H3 as prepaid credit packs, not a subscription. Each dimension is a fixed contract amount you commit to upfront. You draw down credits as you generate video with the H3 model. The Standard and Scale packs each carry a $10,000 credit balance. Pro carries $20,000, and Business carries $50,000. Customer Pricing offers a $10,000 pack for negotiated arrangements. All packs work the same way and share one usage model. You pick a pack based on how much credit you expect to consume.
Top-of-mind questions for buyers
How do credits get drawn down when I generate video with the H3 model?
You spend credits per video generation task. Cost scales with output length in seconds and resolution. You can request 768P or 2K output and durations from 4 to 15 seconds. Longer, higher-resolution clips consume more credits. Your prepaid balance drops as tasks complete.
How long do the prepaid credits stay valid after purchase?
Credits are valid for one year from the date of purchase. You draw down your balance as you generate video during that period. Plan your pack size around the credit volume you expect to use within the year.
What happens if I run out of credits before I finish a video task?
A generation request fails when your balance cannot cover it, returning an insufficient balance error. The task does not run until you have enough credits. To continue, you purchase another credit pack and add it to your balance.
platform.minimax.io+1
Helpful?
Vendor refund policy
Not currently supported.
How can we make this page better?
Tell us how we can improve this page, or report an issue with this product.
Give us feedbackReport a problem with this product or seller
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA).
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
SaaS delivers cloud-based software applications directly to customers over the internet. You can access these applications through a subscription model. You will pay recurring monthly usage fees through your AWS bill, while AWS handles deployment and infrastructure management, ensuring scalability, reliability, and seamless integration with other AWS services.
Support
Vendor support
mail:api@hailuoai.com Description: Customers receive 24x7 email support with a guaranteed response within 24 hours. Technical assistance includes setup guidance, troubleshooting, and usage tips for MiniMax HailuoAI.
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
MiniMax Speech 02 is an advanced AI speech model capable of voice cloning and voice synthesis with high fidelity. It can replicate a speaker unique timbre and generate natural, expressive speech across different languages and styles.
Ranked #1 on the Artificial Analyze Text to Speech leaderboard, Speech 02 is designed for audio production, virtual assistants, call center and content creation, delivering realistic, customizable voice experiences at scale.
M3 is MiniMax next-generation model built for long-context and agentic workloads: it supports 1M context, native multimodal understanding, and achieves top tier coding performance powered by MiniMax Sparse Attention (MSA).
Connect your OpenAI, Anthropic, and Cohere tools to Amazon Bedrock instantly. A drop-in AI gateway: 100+ models including Claude, GPT, and Grok. Hundreds of apps. GDPR and HIPAA ready.
Real-time cost tracking, budget enforcement, and intelligent model routing for AWS Bedrock and all major LLM providers. 15 providers, 62 models. 2-line setup. Free forever for small teams.
Be the first to review this product. We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.