# MiniMax H3-Image: 4K Images, Open Weights and API Access > Explore MiniMax H3-Image: native 4K generation, editing with reference images, open weights and official API access, with the limits to check. - Canonical HTML: https://omniakey.com/blog/minimax-h3-image - Markdown: https://omniakey.com/blog/minimax-h3-image.md - Published: 2026-11-10 (updated 2026-11-10) - Author: Kiki, COO at OmniaKey - Language: en - Category: Guide - Reading time: 6 min - All posts: https://omniakey.com/blog/llms.txt --- MiniMax H3-Image is available through MiniMax's API, MiniMax Code and Hailuo AI, with weights on Hugging Face. It generates 4096×4096 images and edits with up to 16 reference images. MiniMax's [pricing page](https://platform.minimax.io/docs/pricing/overview) lists a 4K text-to-image example at $0.03439 at the launch rate. - **Model:** one 33.1B-parameter checkpoint for text-to-image and reference editing, per the [model card](https://huggingface.co/MiniMaxAI/MiniMax-H3-Image). - **Sizes:** 4096×4096 at 1:1 to 6272×2688 at 21:9, plus custom sizes up to 20 MP. - **Access:** MiniMax API, MiniMax Code and Hailuo AI; weights on Hugging Face under a [custom community license](https://huggingface.co/MiniMaxAI/MiniMax-H3-Image/raw/main/LICENSE). ## What is MiniMax H3-Image? H3-Image is the image member of MiniMax's H3 family. One checkpoint handles text-to-image and editing of one or more reference images, so a pipeline can keep one model instead of pairing a generator with a separate editor. MiniMax's [announcement](https://www.minimax.io/blog/minimax-h3-image) pitches about 16 MP output, more natural detail and stronger instruction following than other open-weight models. Those are vendor claims; the API parameters, published sizes and prices are what you can plan around. H3-Image is separate from MiniMax H3, the video model. For that API, the [MiniMax H3 prompt guide](https://omniakey.com/blog/minimax-h3-prompt-guide) covers its three-field structure and example clips. ## How large is a native 4K image? The 4K preset targets a 4096×4096 area (16.8 MP); at 1:1 that is the full image. MiniMax says it needs no upscaler. The [model card](https://huggingface.co/MiniMaxAI/MiniMax-H3-Image) lists about 16 MP sizes for each ratio: |Ratio|4K size| |-|-| |1:1|4096×4096| |4:3|4736×3552| |16:9|5472×3072| |21:9|6272×2688| The API also takes an exact `WIDTHxHEIGHT`. The [image guide](https://platform.minimax.io/docs/guides/image-generation) allows an area from 655,360 to 20,000,000 pixels and an aspect ratio from 1:3 to 3:1, returned without scaling or rounding. Use `aspect_ratio` plus `area` (`1K`, `2K`, `4K`) or `size`, never both; sending both returns 400. ## How does editing with 16 reference images work? Editing uses `POST /v1/images/edits` with a prompt and 1 to 16 reference images. Upload order sets the labels: the first file is ``, the second ``, and the prompt refers to them by name. The [image guide](https://platform.minimax.io/docs/guides/image-generation) documents the request format. References can be JPG, JPEG, PNG, WEBP, HEIC or HEIF, up to 64 MiB each, 128 to 8192 px per side and no more than a 4:1 ratio. The request body is capped at 64 MiB; Base64 grows to about 4/3 of the file size, so several large references are easier to send as public URLs or `mm_file://` IDs. Prompt enhancement always runs on edits; `data[].revised_prompt` returns the prompt actually used. > Masked edits and transparent backgrounds are not supported. Editing returns a full rectangular image in JPEG, PNG or WebP, so a mask-based product shot or an alpha cut-out needs a different model. ## Standard or Highspeed: which model ID? The IDs are `MiniMax-H3-Image` and `MiniMax-H3-Image-Highspeed`. They use the same parameters and limits; their official price examples differ. MiniMax's [announcement](https://www.minimax.io/blog/minimax-h3-image) says 4K generation takes under 10 seconds, without naming a baseline, GPU or batch size. We did not run a speed test. Compare both IDs on your prompts before choosing. ## What does the H3-Image API cost? MiniMax bills by tokens; these are example request totals, not fixed per-image prices. The [pricing page](https://platform.minimax.io/docs/pricing/overview) lists: |4K example|Standard|Highspeed| |-|-|-| |Launch|$0.03439|$0.06501| |Regular|$0.06879|$0.13001| The launch rate is 50% off before November 17, 2026 at 16:00 UTC when the delivered image has at least 16,600,000 pixels. The discount ends at that time. That covers 4096×4096 and the sizes above. At the launch example, 100 standard 4K images cost about $3.44; the regular example doubles that to $6.88. Standard's token rates are $2.30 per million input text tokens, $1.50 per million input image tokens and $3.80 per million output image tokens. Highspeed raises input images to $3.00 and output images to $7.60. H3-Image-Context-IR prompt enhancement is $2.30 per million input tokens. ## Can you run the open weights locally? The weights are downloadable, but the license is a custom community license, not an open-source license. The [agreement](https://huggingface.co/MiniMaxAI/MiniMax-H3-Image/raw/main/LICENSE) excludes the EU, UK, South Korea and the US from its Applicable Territory and requires prior written authorization when annualized revenue exceeds $1 million or when you provide a hosted service to third parties. The H3-Image download is 68.65 GB, plus a separate 66.7 GB Qwen3-VL text encoder; a full install is roughly 135 GB. That is disk size, not VRAM. MiniMax's [model card](https://huggingface.co/MiniMaxAI/MiniMax-H3-Image) lists recipes for specific GPUs, including H200, RTX PRO 6000 Blackwell and AMD Instinct MI350X, and publishes no minimum VRAM. Check the card for a supported setup. ## What do the official samples show? These are MiniMax's model-card assets, cropped for layout. The [model card](https://huggingface.co/MiniMaxAI/MiniMax-H3-Image) has the originals. ![Official MiniMax H3-Image sample: a person hangs white laundry on a rooftop under a large moon at dusk](https://omniakey.com/_img/blog/minimax-h3-image/official-rooftop.811864ca.992.webp) _Official MiniMax H3-Image sample, cropped from its photography showcase._ A person hangs white laundry on a rooftop in warm evening light. A large moon sits below a billowing sheet, with rooftops and a reflecting puddle. Inspect the translucent cloth and warm light; this is a sample, not a photograph. ![Official MiniMax H3-Image sample: a woman in a red dress cuts a moon-shaped sphere at an outdoor table under a starry sky](https://omniakey.com/_img/blog/minimax-h3-image/official-moon-table.9ab9ae73.984.webp) _Official MiniMax H3-Image sample, cropped from its surreal showcase._ A woman in a red dress cuts a moon-shaped sphere on a plate at a white-clothed outdoor table under a starry sky. Ordinary tableware beside the impossible object and the warm/cool light define the scene. ![Official MiniMax H3-Image edit sample: gray 3D lunar base render on the left, rendered film still on the right](https://omniakey.com/_img/blog/minimax-h3-image/official-edit-render.a7a887b5.1600.webp) _Official MiniMax H3-Image sample: gray 3D input (left) to rendered film still (right)._ The edit pair starts with a gray, clay-like lunar base: habitat, rover and astronaut. The result adds a black sky, strong shadows and metal-like materials. The arrangement stays recognizable; some fine shapes differ. ## Where can you use H3-Image today? MiniMax lists three hosted entry points: the API Platform, MiniMax Code and Hailuo AI. The API runs on the global and Chinese platforms; the weights are on Hugging Face and ModelScope. The [announcement](https://www.minimax.io/blog/minimax-h3-image) and [model card](https://huggingface.co/MiniMaxAI/MiniMax-H3-Image) list these. The OmniaKey catalogue we checked on November 10 lists image models such as [GPT Image 2.5 Sunburst](https://omniakey.com/gpt-image-2-5-sunburst), not H3-Image. The [GPT Image 2.5 API guide](https://omniakey.com/blog/gpt-image-2-5-api) shows how to call an image model through one key. You can compare the [Seedream 5.5 launch notes](https://omniakey.com/blog/seedream-5-5) or try models in the [AI image generator](https://omniakey.com/ai-image-generator). For a hosted image API inside OmniaKey today, [GPT Image 2.5 Sunburst](https://omniakey.com/gpt-image-2-5-sunburst) is one current option. For H3-Image itself, use MiniMax's API and its launch discount through November 17. ## Frequently asked questions ### When did MiniMax H3-Image come out? The announcement is dated November 11, 2026, and the license November 10, 2026. Both pages were live when we checked on November 10 in New York. ### Is MiniMax H3-Image open source? No. The weights are downloadable under a custom community license, not an open-source license; the [agreement](https://huggingface.co/MiniMaxAI/MiniMax-H3-Image/raw/main/LICENSE) sets territorial and authorization limits. ### Does H3-Image support masked edits or transparent PNGs? No. The [image guide](https://platform.minimax.io/docs/guides/image-generation) lists preview images, masked edits and transparent backgrounds as unsupported. Editing takes 1 to 16 reference images plus a prompt and returns a full rectangular JPEG, PNG or WebP. ### How much does one 4K image cost? The 4K text-to-image example is $0.03439 on Standard and $0.06501 on Highspeed at the launch rate; regular examples are $0.06879 and $0.13001. Charges follow token usage. ### Is H3-Image the same as MiniMax H3? No. H3 is MiniMax's video model; H3-Image is a separate image checkpoint built on H3. OmniaKey's `minimax-h3` entry is video, not this image API. ## Sources checked - [MiniMax-H3-Image Community License Agreement](https://huggingface.co/MiniMaxAI/MiniMax-H3-Image/raw/main/LICENSE), license date November 10, 2026. - [MiniMax: MiniMax H3-Image announcement](https://www.minimax.io/blog/minimax-h3-image), byline November 11, 2026. - [MiniMax: image generation pricing](https://platform.minimax.io/docs/pricing/overview), checked November 10, 2026. - [MiniMax-H3-Image model card](https://huggingface.co/MiniMaxAI/MiniMax-H3-Image), checked November 10, 2026. - [MiniMax: image generation guide](https://platform.minimax.io/docs/guides/image-generation), checked November 10, 2026.