DMXAPI

Editor Review

Before wiring this into an app, create a key in the dashboard and fill the base address and model name from the matching doc. Text chat can stream, and it can also analyze an image or call a function. Multimodal docs split image generation, image editing, video generation, video editing, speech synthesis, recognition, and voice cloning into separate pages. Balance and model-list APIs can be checked before a call. Parameters are written per model, so one sample does not cover every model. It fits developers who want text, image, video, and speech APIs from one dashboard.

AI Tools Navigator Editorial TeamUpdated: 2026-10-09

What is DMXAPI

DMXAPI is a model API gateway for developers. The official docs say the name comes from the initials of the Chinese words for large model. One key calls the models on the platform. Text chat supports streaming, image analysis, and function calling. Separate multimodal docs cover image generation and editing, video generation and editing, speech synthesis, speech recognition, and voice cloning. The platform also documents balance, token, and model-list APIs, plus how to connect third-party apps. The site describes itself as a unified AI API gateway and admin dashboard. It does not publish one shared price list.

DMXAPI Key Features

Text chat and function calls

The chat API supports streaming, image analysis, and function calls, using the platform key and the base address in the docs.

Image and video APIs

The docs separate image generation, image editing, video generation, and video editing, and each model page describes inputs and how to poll a task.

Speech synthesis and cloning

Multimodal docs cover speech synthesis, speech recognition, and voice cloning, in pages separate from the text chat API.

Balance and model list

The platform documents balance, token lookup, and model-list APIs so you can check the account and available models before a chat or generation job.

DMXAPI Use Cases

Add text chat to an app

A developer calls the chat API with one key, and turns on streaming or function calling when the doc for that model allows it.

Generate or edit images and video

A design or content developer submits an image, edit, or video job from the model doc, then polls the task for the result URL.

Add speech to a product

When a product needs readout, transcription, or a copied voice, the speech docs point to synthesis, recognition, or voice cloning.

Frequently Asked Questions

▶Which kinds of APIs can one DMXAPI key call?

The docs split the APIs into groups, and the same key is used on the matching page. Text covers chat, streaming, image analysis, and function calling. Multimodal pages cover image and video generation and editing, plus speech synthesis, recognition, and voice cloning. Balance, tokens, and the model list have their own queries. Model names and parameters come from the current page, not from one sample reused for every task.

▶Where do the base address and key go when integrating?

Samples in the docs pass the base address and key into the client you use. The key comes from the dashboard after sign-in. Keep it out of public repositories. Some model pages add their own path or an async lookup, especially video jobs, which often need a second request before the result URL is ready.

DMXAPI

Editor Review

What is DMXAPI

Basic Info

Best For

DMXAPI Key Features

DMXAPI Key Advantages

DMXAPI Use Cases

Frequently Asked Questions

Latest News

User Reviews

Coze

SiliconFlow

码上飞

Zion

OpenRouter

秒哒

Dify

Trickle AI

DMXAPI

Editor Review

What is DMXAPI

Basic Info

Best For

DMXAPI Key Features

DMXAPI Key Advantages

DMXAPI Use Cases

Frequently Asked Questions

Latest News

User Reviews

Related Tools

Coze

SiliconFlow

码上飞

Zion

OpenRouter

秒哒

Dify

Trickle AI