> For the complete documentation index, see [llms.txt](https://docs.majestix.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.majestix.ai/readme.md).

# Home

Multi-model AI gateway with credits-based billing, agentic orchestration, and 59 pre-built agents.

## What is Majestix AI Inference Hub?

Majestix AI Inference Hub is an AI-as-a-Service backend that gives you unified access to a dynamically updated model catalog through a single API with a single billing system. The live platform currently exposes **55 enabled models**.

Instead of managing API keys, rate limits, and billing for each model separately, you get one endpoint, one credit system, and automatic fallback when things go wrong.

## Key Features

**Multi-Model Gateway**

* 55 enabled models across chat, coding, reasoning, vision, and image generation
* Automatic fallback on all paths (non-streaming, streaming chat, streaming code)
* Auto-routing based on task complexity
* SSE streaming for all models

**Credits System**

* Pay-as-you-go with simple credit-based pricing
* 1 credit = $0.001 USD
* Plans: Free (500 cr/mo), Guru ($10/mo, 10K cr), Pro ($50/mo, 55K cr)
* Reservation-based billing prevents overcharges

**Authentication**

* API keys for programmatic access (VSCode, CLI, SDK)
* Firebase Auth + App Check for web apps
* OIDC for service-to-service communication

**Agentic Orchestration**

* Scheduled agent tasks with Cloud Scheduler cron triggers
* Ensemble consensus: 3 models iterate until quality threshold met
* Swarm pipelines: multi-agent sequential workflows with DAG dependencies
* Folder-based agent pack import with bundled swarm execution
* 59 pre-built agents for common tasks
* Per-user limits: 200 tasks, 50 scheduled tasks
* Auto-pause after 3 consecutive scheduled failures

**Security**

* 8-layer defense-in-depth for agent execution
* KMS-encrypted credentials at rest
* DNS-pinned requests (TOCTOU prevention)
* Default-deny URL whitelist

## Architecture at a Glance

```
Clients (Web, VSCode, CLI, Cloud Tasks)
    |
    v
inference-api (Cloud Run)          agent-executor (Cloud Run)
  /chat, /code, /models             /execute, /ensemble, /swarm
  Credits + Auth + Routing           Agentic loops + Tools + Security
    |                                    |
    v                                    v
  AI Model APIs                    External APIs (DNS-pinned)
                                   Firestore + Cloud KMS
```

## Quick Links

| Section                                  | Description                                                         |
| ---------------------------------------- | ------------------------------------------------------------------- |
| [Getting Started](/getting-started.md)   | Authentication, credits, first API call                             |
| [Web App](/web-app.md)                   | Chat interface, settings, billing, agents, and every page in detail |
| [API Reference](/api-reference.md)       | Endpoints, request/response formats                                 |
| [Models](/models.md)                     | Live model catalog, pricing, and free-tier routing rules            |
| [Agents](/agents.md)                     | Scheduled tasks, tools, credentials, security                       |
| [Orchestration](/orchestration.md)       | Ensemble consensus and swarm pipelines                              |
| [Architecture](/architecture.md)         | System design, infrastructure, security                             |
| [VSCode Extension](/vscode-extension.md) | IDE integration                                                     |


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.majestix.ai/readme.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.