Integrate in your stack
Drop the OpenAI-compatible API into Python, JavaScript, PHP, Laravel, Go, Flutter or any HTTP client you already use.
All-in-one AI API for Africa
MadAfri Nexus AI
One API key for every AI model
Chat with GPT, Claude, Gemini, DeepSeek, GLM and Kimi. Create images with GPT Image 2.5, Grok Imagine and Nano Banana. Generate video with Seedance, Wan 3.0 and MiniMax H3. One endpoint and one balance, built for developers and businesses across Africa.
- OpenAI
- Anthropic
- DeepSeek
- Zhipu AI
- Moonshot AI
- xAI
- ByteDance
- Alibaba
- MiniMax
- Pay as you go
- OpenAI-compatible
- Text, image and video with one key
Three ways to start
Your code, your editor, or no code at all
Call the API from any language, point your coding assistant at MadAfri, or wire it into an automation tool.
Use with your coding assistant
Point any editor or coding agent that accepts a custom base URL at MadAfri and run it on your balance.
Automate without code
Call MadAfri from the HTTP node of n8n, Make or Zapier. One endpoint, one key, nothing to install.
One unified API
A single HTTPS endpoint routes each request to the model you choose. Documented payloads, one key.
View docsText, image and video
Six chat model families, three image models and four video models, all behind the same key.
Browse modelsIdea to production
From prototype to live product with no contracts, no infrastructure to run and no account to open with each provider.
Start buildingMobile Money · Coming soon
Top up the way
you already pay
A bank card should not decide who gets to build with AI. We are working on top-ups with the mobile wallets you already use every day.
Follow the launch on Facebook- M-Pesa
- MTN MoMo
- Orange Money
- Airtel Money
- MVola
- Wave
- Moov Money
- More
Planned wallets. Availability will vary by country.
Works with the tools you already use
- Cursor
- VS Code
- JetBrains
- Zed
- Cline
- opencode
- aider
- Continue
- n8n
- Make
- Zapier
- Flowise
- LangChain
- LlamaIndex
- Python
- JavaScript
- PHP · Laravel
- Go
- Flutter
- cURL
Anything that accepts an OpenAI-compatible base URL.
How it works
Up and running in minutes
One MadAfri integration, then every request is routed to the model you name: text, image or video.
Multiple providers, one APIStreaming response
1. Your app
Sends one HTTPS request
POST /v1/chat/completions2. MadAfri
Routes to the model you chose
model: "claude-sonnet-5"- Auth
- Routing
- Metering
3. Providers
Chat models
GPT · Claude · Gemini · DeepSeek · GLM · Kimi
Image models
GPT Image 2.5 · Grok Imagine · Nano Banana
Video models
Seedance 2.5 · Seedance 2.0 · Wan 3.0 · MiniMax H3
4. Response
One unified answer streams back to your app
Get your key
Create an account in the console, add credit and generate an API key.
Pick a model
Set the model field to the one you want. Switching later is a one-string change.
Receive the answer
MadAfri routes the call, meters the usage and returns a normalized response to your app.
Models
Every major model, one endpoint
Switch models by changing one string. New versions are added as they ship.
See all models in the consoleChat & reasoning
GPT
OpenAI
General-purpose flagship for chat, coding, tool use and structured output.
Claude
Anthropic
Strong on long documents, careful writing, coding and agent workflows.
Gemini
Multimodal by default: text, images, audio and very long context.
DeepSeek
DeepSeek AI
High-value reasoning and coding models with open weights.
GLM
Zhipu AI · Z.ai
Bilingual general models with solid agent and coding skills at low cost.
Kimi
Moonshot AI
Long-context models tuned for research, coding and agentic tasks.
Image generation
GPT Image 2.5
OpenAI
OpenAI’s newest image model: faster generation, faithful edits and consistent style across a series.
Grok Imagine
xAI
xAI’s image model for quick, vivid drafts and social-ready visuals.
Nano Banana
Google’s Gemini image model, strong at precise edits, layouts and legible text in images.
Video
Video generation, pay as you go
Submit a job, poll the task, download the clip. Per-second rates are shown live in the console.
See live ratesSeedance 2.5
NewestByteDance
Billed per second · live rate in console
New-generation multimodal generation and editing, for longer takes and richer references.
- Takes up to 30 seconds
- Text, image, video and audio references
- Audio generated in sync with the picture
Seedance 2.0
ByteDance
Billed per second · live rate in console
A dependable workhorse for everyday commercial work, from quick drafts to key shots.
- Text-to-video and image-to-video
- Multi-reference input
- Tiers for speed or quality
Wan 3.0
Alibaba
Billed per second · live rate in console
Long clips from almost any input, including documents and slides.
- Clips up to 30 seconds
- Text, image and document input
- Sound generated with the video
MiniMax H3
MiniMax · Hailuo
Billed per second · live rate in console
One multimodal model for generating, referencing and editing video with sound.
- Up to 2K resolution, 15-second clips
- Native stereo audio
- Text, image, video and audio as context
Built for
Use cases that ship today
Whatever you are building, one key and one balance cover it.
AI developers
Drop your key into your stack and start shipping. OpenAI-compatible, so most existing code just works.
- OpenAI SDK compatible
- Switch models without code changes
- One key per project or environment
No-code automation
Power n8n, Make or Zapier workflows through one HTTPS endpoint. No SDK, no boilerplate.
- Works in any HTTP request node
- Plain JSON in, plain JSON out
- One key for every scenario
Coding agents
Use MadAfri as the model backend for editors and agentic coding tools that accept a custom base URL.
- Drop-in OpenAI-compatible base URL
- Streaming responses for live edits
- Long-context models available
Chatbots & support
Build multilingual assistants for WhatsApp, Telegram or your own app, in English, French and more.
- Multilingual models
- Vision models read photos and documents
- Pay only for the conversations you serve
Features
Everything you need to build with AI
Designed around the realities of building technology in Africa.
Multi-model access
One API for OpenAI, Anthropic, Google, DeepSeek, Zhipu and Moonshot models. Switch providers without changing your code.
Text, image and video
Chat, generate images and render video from the same key and the same balance.
Africa-first by design
English and French throughout, pages that stay light on slow connections, and choices shaped by how teams here build and pay.
Mobile Money top-upsSoon
Planned support for the wallets people already use, so a bank card is never a requirement.
HTTPS API
REST and JSON endpoints under api.madafri.com/v1. Copy an example from the docs and ship with your preferred HTTP stack.
Pay as you go
A prepaid balance and no subscription. The live rate for each model is shown in the console before you call it.
Developer ready
Call MadAfri in seconds
Replace one line and keep your SDK. Pick a model and a language to see the request.
curl https://api.madafri.com/v1/chat/completions \
-H "Authorization: Bearer $MADAFRI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "claude-sonnet-5",
"messages": [
{
"role": "user",
"content": "Explain how a mobile money payment API works, in three short sentences."
}
]
}'Example request. Exact model IDs and parameters are listed in your console.
FAQ
Questions, answered
The essentials on access, billing and compatibility.
What is MadAfri Nexus AI?
An all-in-one AI platform from Antananarivo, Madagascar. You get one API key and one balance for text, image and video models from many providers, instead of managing a separate account for each.
Will my existing OpenAI code work?
Yes. The API follows the OpenAI format. Set the base URL to https://api.madafri.com/v1, use your MadAfri key and pick a model. Official OpenAI SDKs and most frameworks that accept a custom base URL work unchanged.
How does billing work?
Pay as you go, with no subscription. Text models are billed by tokens, images per image and video per second. The current rate for every model is shown in the console before you call it.
Which models can I use?
GPT, Claude, Gemini, DeepSeek, GLM and Kimi for chat; GPT Image 2.5, Grok Imagine and Nano Banana for images; Seedance 2.5 and 2.0, Wan 3.0 and MiniMax H3 for video. The console always lists what is live.
How do I top up and get support?
Top-up options are shown in the console when you add credit. For help, message us on our Facebook page and we will reply in English or French.
Are you affiliated with the model providers?
No. MadAfri is an independent gateway. Model names and brands belong to their respective owners, and each provider’s usage policies still apply to your requests.
Ready to build?
Create a key, change one line and ship with the world’s best models.