# MiniMax H3 Image and Highspeed now available on AI Gateway

Source: [Vercel](https://vercel.com/changelog/minimax-h3-image-and-highspeed-now-available-on-ai-gateway)  
Feed7 permalink: https://feed7.dev/p/minimax-h3-image-and-highspeed-now-available-on-ai-gateway-1iwg1qm  
Published: 2026-11-10T00:00:00.000Z  
Trust: Official Source (official_source)

## Why Included

Vercel AI Gateway now exposes MiniMax H3 Image generation and editing through one API key, with custom output sizes and an OpenAI-compatible images API.

## Source Summary

AI Gateway adds **MiniMax H3 Image** and **H3 Image Highspeed** for text-to-image generation and image edits. Both support custom dimensions and aspect ratios, including **2K and 4K** output, and the Highspeed variant offers faster generation.

## Practical Implication

Builders can call either model through AI Gateway without a separate MiniMax account, or use the **OpenAI-compatible `/v1/images/generations` and `/v1/images/edits` routes**. The gateway also provides usage and cost tracking.

## Agent-Ready Context

AI Gateway adds **MiniMax H3 Image** and **H3 Image Highspeed** for text-to-image generation and image edits. Both support custom dimensions and aspect ratios, including **2K and 4K** output, and the Highspeed variant offers faster generation.

Builders can call either model through AI Gateway without a separate MiniMax account, or use the **OpenAI-compatible `/v1/images/generations` and `/v1/images/edits` routes**. The gateway also provides usage and cost tracking.

The material gives no generation-time or quality measurements for the Highspeed variant. Pricing is described as matching provider pricing, with no inference markup or platform fee.

## Connected Context

Feed7 judgment across 1059 accumulated Signals:

This adds two MiniMax image routes to AI Gateway, including custom dimensions up to 4K, image edits, and a faster variant. OpenAI-compatible routes and usage and cost tracking make them accessible within existing integrations. The listing establishes availability and interface options, but supplies no latency or quality results to show when Highspeed or either route is preferable.

- [GPT Image 2.5 Flare and Sunburst now available on AI Gateway](https://feed7.dev/p/gpt-image-2-5-flare-and-sunburst-now-available-on-ai-gateway-15krfwf) — Both listings expose image generation and editing through AI Gateway and present a speed-related choice; Flare and Sunburst are described in terms of iteration speed and composition control, while MiniMax adds custom dimensions and a Highspeed variant without measured comparisons.
- [Grok Imagine Image 2.0 now available on Vercel AI Gateway](https://feed7.dev/p/grok-imagine-image-2-0-preview-now-available-on-vercel-ai-gateway-1mdku5a) — Both provide image edits and higher-resolution options through the gateway; Grok also offers batches and targeted edits, while MiniMax adds custom dimensions up to 4K. Neither listing establishes comparative quality or latency.
- [Muse Image now available on AI Gateway](https://feed7.dev/p/muse-image-now-available-on-ai-gateway-0ql84pl) — Muse and MiniMax both cover generation and instruction-based editing through the same gateway; Muse adds reference guidance, while MiniMax specifies custom dimensions and a faster variant. The supplied material does not establish which better fits a given workflow.

## Context Map

- Layer: infra
- Domains: image
- Topics: generative-media, gateways, tool-use

## Uncertainty

- The material gives no generation-time or quality measurements for the Highspeed variant. Pricing is described as matching provider pricing, with no inference markup or platform fee.

## Agent Instruction

Use this item as source-backed context. Do not invent claims beyond the linked source. If this item conflicts with another source, call out the conflict.
