# MiniMax H3 Image Highspeed

> MiniMax H3 Image Highspeed (official ID MiniMax-H3-Image-Highspeed, RouteMux slug minimax/minimax-h3-image-highspeed) is the low-latency tier of the MiniMax H3 Image family, built for interactive creative tools and rapid multi-turn iteration. It shares the full capability set of the standard minimax/minimax-h3-image model: text-to-image generation at native 1K, 2K, and 4K resolution (up to roughly 16 megapixels) and image editing with up to 16 reference images. Use the standard minimax/minimax-h3-image model for cost-sensitive batch pipelines, and pick Highspeed when a user is waiting on screen for immediate results.

Canonical: https://routemux.com/minimax/minimax-h3-image-highspeed
Provider: MiniMax

## Key facts

| Field | Value |
| --- | --- |
| Model ID | minimax/minimax-h3-image-highspeed |
| Official model ID | MiniMax-H3-Image-Highspeed |
| Input modalities | text, image |
| Output modalities | image |
| Capabilities | Image Generation, Image Edit |
| Upstream release | 2026-11-10 |
| Availability | available |

## Pricing

- RouteMux: $3.8 per 1M tokens
- Official: $7.6 per 1M tokens
- Saving vs official: 50%
- Official price source: https://platform.minimax.io/docs/pricing/overview, verified 2026-11-11

Billing is prepaid wallet, charged per successful request only.

## API access

Base URL: https://api.routemux.com

Supported protocols:

- openai_images

## What is MiniMax H3 Image Highspeed

MiniMax H3 Image Highspeed (official ID MiniMax-H3-Image-Highspeed, RouteMux slug minimax/minimax-h3-image-highspeed) is the low-latency tier of the MiniMax H3 Image family, built for interactive creative tools and rapid multi-turn iteration. It shares the full capability set of the standard minimax/minimax-h3-image model: text-to-image generation at native 1K, 2K, and 4K resolution (up to roughly 16 megapixels) and image editing with up to 16 reference images. Use the standard minimax/minimax-h3-image model for cost-sensitive batch pipelines, and pick Highspeed when a user is waiting on screen for immediate results.

On RouteMux, it speaks the OpenAI Images protocol: send text-to-image requests to POST https://api.routemux.com/v1/images/generations and multi-reference editing requests to POST https://api.routemux.com/v1/images/edits. The prompt accepts up to 32,000 Unicode codepoints, and each call can produce n=1 to 10 images. Image editing accepts 1 to 16 reference images via the JSON images array (each entry containing an image_url string) or multipart form uploads under image or image[]; local mask inpainting (mask) and streaming (stream must be omitted or false) are not supported.

Dimensions can be specified in two ways: pair area ("1K", "2K", or "4K") with aspect_ratio ("auto" or X:Y where X and Y are integers from 1 to 300 and X/Y is between 1/3 and 3, such as 1:1, 16:9, 9:16, 21:9, 3:1, or 1:3), or pass an explicit pixel size (WxH with total area between 655,360 and 20,000,000 pixels and aspect ratio between 1/3 and 3; when size is WxH, both aspect_ratio and area must be omitted; size also accepts "auto"). Prompt expansion is enabled by default for text-to-image; setting disable_prompt_enhanced to true on text-to-image requires an explicit WxH size or X:Y aspect_ratio (image editing rejects disable_prompt_enhanced=true). Supported output_format values are "png", "jpeg", "jpg", and "webp", and response_format accepts "url" or "b64_json". output_compression takes an integer from 0 to 100 (default 95) and applies to jpeg and webp only. Reference image_url values must be public https URLs or data URLs; mm_file:// references are not supported.

Because image generation is non-idempotent (non_idempotent), upstream token billing starts as soon as inference begins. The RouteMux gateway retries this model only when upstream returns HTTP 429, and never retries on 5xx responses, timeouts, or network errors. Configure max_retries=0 in the OpenAI SDK and omit --retry in curl so client-side timeouts never cause duplicate generations and double charges.

## Key capabilities

- **Low-latency H3 Image tier** — Delivers the same 1K/2K/4K resolution ceiling and parameter set with faster turnaround for interactive apps.
- **Up to 16 reference images** — Send 1 to 16 reference images to /v1/images/edits for subject consistency and multi-element composition, with n=1 to 10 outputs.
- **Non-idempotent retry protection** — Gateway 5xx and timeout retries are disabled; pass max_retries=0 in the OpenAI SDK to avoid duplicate billing.
- **50% below official pricing** — Billed per input and output token on RouteMux at 50% off MiniMax official Highspeed rates.

## Use cases

- **Interactive design canvases & live previews** — Let users tweak prompts, reference images, and aspect ratios in real time with faster 2K/4K turnaround.
- **Rapid multi-reference look exploration** — Combine up to 16 reference images in /v1/images/edits with n=1 to 10 outputs to compare variations quickly.

## Other variants in this family

- MiniMax H3 Image (`minimax/minimax-h3-image`)

## Sources

- [MiniMax Image Generation Guide](https://platform.minimax.io/docs/guides/image-generation)
- [MiniMax Pricing Overview](https://platform.minimax.io/docs/pricing/overview)

_Content reviewed by the RouteMux team on 2026-11-11._