> ## Documentation Index
> Fetch the complete documentation index at: https://docs.mountsea.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Introduction

# Mountsea AI API Introduction

Discover all you can do with our Mountsea AI API! Our comprehensive AI platform empowers developers to integrate advanced AI capabilities into their applications 鈥?including video generation, image creation, music production, and multi-model LLM chat.

## Overview

Mountsea AI provides a unified API gateway to access the world's leading AI models across **video**, **image**, **music**, and **language** domains. We offer the following core services:

<CardGroup cols={2}>
  <Card title="Mountsea API" icon="server" href="api-reference/mountsea-api/introduction">
    **Official-key quality · Production stable · Full-platform models.** Unified `/ms/v1` async API with endpoint marketplace, task polling, and webhook callbacks.
  </Card>

  <Card title="Hub (Premium AI Gateway)" icon="bolt" href="api-reference/hub/introduction">
    **Flagship-quality 路 Production-stable 路 Cheaper than official.** One API for **Nano Banana**, **GPT Image 2**, **Veo 3.1**, **Kling v3**, **WAN 2.7**, **Seedance 2.0**, **ElevenLabs Music**, Whisper.
  </Card>

  <Card title="Google (Gemini)" icon="video" href="api-reference/gemini/introduction">
    Video & image generation powered by **Veo 2 / Veo 3 / Veo 3.1** and **Nano Banana** models
  </Card>

  <Card title="馃毀 Sora2 (Unavailable)" icon="film" href="api-reference/sora/introduction">
    Currently **unavailable** on Mountsea. For video generation, use [Hub](api-reference/hub/introduction) or [Gemini Video](api-reference/gemini/video-introduction) instead.
  </Card>

  <Card title="OpenAI (GPT Image)" icon="palette" href="api-reference/openai/introduction">
    **GPT Image 2** image generation & editing 鈥?async task API + official `openai` SDK compatibility
  </Card>

  <Card title="XAI (Grok)" icon="image" href="api-reference/xai/introduction">
    Image & video generation powered by xAI's **Grok** models
  </Card>

  <Card title="Suno" icon="music" href="api-reference/suno/introduction">
    Full-suite AI music generation, voice persona, custom model training, and audio processing via **Suno AI**
  </Card>

  <Card title="ElevenLabs" icon="waveform-lines" href="api-reference/eleven/introduction">
    AI music generation with composition plans, video scoring, and stem separation via **ElevenLabs**
  </Card>

  <Card title="Producer" icon="headphones" href="api-reference/producer/introduction">
    AI music generation powered by Google DeepMind's **Lyria 3 Pro** model
  </Card>

  <Card title="Chat" icon="comments" href="api-reference/chat/introduction">
    Multi-protocol AI chat gateway supporting **OpenAI**, **Claude**, and **Gemini** APIs
  </Card>
</CardGroup>

## Why Mountsea AI Stands Out

### All-in-One API Platform

A single API key gives you access to multiple AI services across different domains 鈥?no need to manage separate accounts and credentials for each AI provider.

### Stable Official-Key Gateway

Mountsea API exposes premium model endpoints through a unified `/ms/v1` task system. Discover models from the endpoint marketplace, submit a task by endpoint slug, and poll or receive a webhook when generation completes.

### Multi-Protocol LLM Gateway

Our Chat service supports **OpenAI Compatible API**, **Anthropic (Claude) API**, **OpenAI Responses API**, and **Google Gemini Native API**. Use official SDKs directly 鈥?just change the `base_url`.

### Comprehensive AI Model Coverage

Access top-tier AI models from leading providers:

| Domain         | Models                                                                                                                                |
| -------------- | ------------------------------------------------------------------------------------------------------------------------------------- |
| **Video**      | Veo 2, Veo 3, Veo 3.1, Grok Imagine Video, Kling v3 Pro/Standard, WAN 2.7, Seedance 2.0 *(Sora-2 / Sora-2-Pro currently unavailable)* |
| **Image**      | Nano Banana Fast/Pro/2, GPT Image 2, Grok Imagine Image                                                                               |
| **Music**      | Suno (chirp-v35 \~ chirp-v55, custom models), ElevenLabs music\_v1 / Music, Lyria 3 Pro                                               |
| **Transcribe** | Whisper, Wizper                                                                                                                       |
| **LLM**        | GPT-5.1, GPT-5.2, Claude 4.5, Claude Opus 4.6, Claude Sonnet 4.6, Gemini 2.5/3/3.1                                                    |

### Budget-Friendly Excellence

Enjoy premium AI tools at competitive prices. Our platform delivers high-quality, scalable solutions while keeping your projects cost-effective.

***

## Available Services

### Mountsea API - Official-Key Stable Gateway

Mountsea API is the new unified microservice for high-quality, production-stable, full-platform model access:

* **Unified endpoint marketplace** - `GET /ms/v1/endpoints` lists available image, video, audio, chat, transcribe, and embeddings endpoints.
* **One async task pattern** - submit with `POST /ms/v1/run/{endpoint_slug}`, then poll `GET /ms/v1/tasks/{task_id}`.
* **Schema-first integration** - every endpoint detail includes `input_schema`, `output_schema`, and copy-ready examples.
* **Webhook support** - pass `webhook_url` to receive signed terminal task callbacks.

[Explore Mountsea API Documentation](api-reference/mountsea-api/introduction)

***

### 鈿?Hub 鈥?Premium AI Gateway (Image / Video / Audio / Transcribe)

A single unified API gateway aggregating the world's best third-party AI models 鈥?designed around three promises:

* 馃弳 **Flagship quality** 鈥?only the **official flagship model weights** (Veo 3.1, Nano Banana Pro, GPT Image 2, Kling v3 Pro, WAN 2.7, Seedance 2.0, ElevenLabs Music). No knock-offs, no distillations. **Outputs are identical to going direct to the provider.**
* 馃洝锔?**Production stable** 鈥?multi-region routing, automatic failover, transparent retries on transient errors, queue-aware load balancing. Built for **24/7 production traffic** with no surprise rate-limit walls.
* 馃挵 **Cheaper than official** 鈥?pay only when `status=completed` (failed tasks are **free**), billed in unified credits at a **meaningful discount** versus going direct. No per-provider minimums, no monthly subscriptions.

**One endpoint per capability, many models** 鈥?switch between models by changing the `model` field; no code changes needed.

* **馃柤锔?Image** 鈥?`nano-banana` (Fast / 2 / Pro), `gpt-image-2`, plus `*-edit` variants for image editing
* **馃幀 Video** 鈥?`veo-3.1` (`-fast` / `-lite` / `-ref` / `-first-last` / `-image`), `veo-3`, `kling-v3-pro` / `-standard`, `wan-2.7` (+ `-image` / `-ref` / `-edit`), `seedance-2.0` (+ `-fast` / `-image` / `-ref`)
* **馃幍 Audio (Music)** 鈥?`elevenlabs-music` text-to-music
* **馃帣锔?Transcribe** 鈥?Whisper / Wizper for audio & video speech-to-text and translation
* **馃攳 Model Discovery** 鈥?`GET /hub/v1/models` returns every model with full `input_schema` + ready-to-copy `example`

\[Explore Hub Documentation 鈫抅(api-reference/hub/introduction)

***

### 馃幀 Google (Gemini) 鈥?Video, Image & SDK Compat

Powered by Google's cutting-edge AI, this service is organized into three dedicated sections:

* **馃帴 Video Generation** 鈥?Create videos with **Veo 2 / Veo 3 / Veo 3.1**. Supports `text2video`, `img2video`, `ingredients2video`, upsample to 1080p/4K, extend, reshoot, and object insert/remove.
* **馃柤锔?Image Generation (Nano Banana)** 鈥?Create and edit images with **Nano Banana Fast / Pro / 2** models, multiple aspect ratios, up to 4K resolution.
* **馃攲 Gemini Compat (Official SDK)** 鈥?Drop-in replacement for Google's official **@google/genai** SDK. Use `generateContent` / `streamGenerateContent` with base URL `https://api.mountsea.ai/gemini`. Image models (`gemini-2.5-flash-image`, `gemini-3.1-flash-image-preview`, `gemini-3-pro-image-preview`) auto-route to Nano Banana.

\[Explore Gemini Documentation 鈫抅(api-reference/gemini/introduction)

***

### 馃毀 Sora2 鈥?Currently Unavailable

<Warning>
  **Sora2 is currently UNAVAILABLE on Mountsea.** Endpoints (`/sora/*`) will be rejected at the gateway. For video generation, please use one of the alternatives below:

  * [Hub 鈥?Premium AI Gateway](api-reference/hub/introduction) 鈥?Veo 3.1, Kling v3, WAN 2.7, Seedance 2.0 (recommended)
  * [Gemini Video (Veo 2 / 3 / 3.1)](api-reference/gemini/video-introduction)
  * [XAI (Grok) Video](api-reference/xai/introduction)
</Warning>

\[Sora2 documentation kept for reference 鈫抅(api-reference/sora/introduction)

***

### 馃柤锔?XAI (Grok) 鈥?Image & Video Generation

Powered by xAI's Grok models, this service provides:

* **Text-to-Image** 鈥?Generate high-quality images from text prompts using **grok-imagine-image**, with customizable aspect ratios (1:1, 2:3, 3:2, 9:16, 16:9)
* **Image-to-Image** 鈥?Provide a reference image to guide generation 鈥?output size follows the reference
* **Text-to-Video** 鈥?Generate videos from text prompts using **grok-imagine-video**, with control over duration (6s/10s/15s), aspect ratio, and resolution (480P/720P)
* **Image-to-Video** 鈥?Use a reference image to guide video generation 鈥?aspect ratio and resolution follow the reference automatically
* **Async Task System** 鈥?All generation requests return a `taskId` for polling

\[Explore XAI Documentation 鈫抅(api-reference/xai/introduction)

***

### 馃帹 OpenAI 鈥?GPT Image Generation & Editing

Powered by OpenAI's latest **GPT Image 2** model, this service provides:

* **Text-to-Image** 鈥?Generate images from text prompts with flexible sizes (1024x1024, 1024x1536, 1536x1024) and quality levels
* **Image Editing** 鈥?Edit existing images by providing a URL or base64 data URL
* **Inpainting** 鈥?Use a mask image to repaint specific areas of an input image
* **Transparent Background** 鈥?Generate images with transparent background (`background: transparent`)
* **Two API Styles**:
  * **Async Task API** (`/openai/images`) 鈥?unified endpoint with `taskId` polling
  * **OpenAI Compat API** (`/openai/v1/images/*`) 鈥?drop-in replacement for OpenAI's official SDK, just change `base_url`

\[Explore OpenAI Documentation 鈫抅(api-reference/openai/introduction)

***

### 馃幍 Suno 鈥?Music Generation

Powered by Suno AI, this service provides a full suite of music creation and processing tools:

* **Music Generation** 鈥?Create, extend, cover, mashup, sample, and generate inspiration-based tracks using 15 task types via a unified `/generate` endpoint, with models from `chirp-v35` to `chirp-v55`
* **Sound Effects** 鈥?Generate one-shot or looped sound effects from text descriptions
* **Lyrics Generation** 鈥?Generate original lyrics or mashup lyrics from two songs
* **Voice Persona** 鈥?Create verified voice personas from your own recordings through a single-task two-phase voice verification flow (init 鈫?await phrase 鈫?complete)
* **Custom Models** 鈥?Train personalized music models on your own audio (6+ training clips), then use `chirp-custom:<uuid>` for generation
* **Audio Processing** 鈥?Concat clips, remaster tracks (V4.5+/V5 models), adjust playback speed with pitch preservation
* **Stem Separation** 鈥?Separate tracks into vocals + instrumental (two-track) or all individual stems
* **Audio Export** 鈥?Export to MP4 (with visualizer), lossless WAV, or MDI (MIDI) format
* **Audio Analysis** 鈥?Get synchronized lyrics timeline, downbeat detection, and enhanced style tags
* **Vocal Persona** 鈥?Extract vocal characteristics from clips and create reusable personas for consistent vocal style

\[Explore Suno Documentation 鈫抅(api-reference/suno/introduction)

***

### 馃幎 ElevenLabs 鈥?AI Music Generation

Powered by ElevenLabs' music\_v1 model, this service provides:

* **Text-to-Music** 鈥?Generate music from simple text prompts or structured composition plans with section-level style and lyrics control
* **Composition Plan** 鈥?AI-generated structured plans with sections, global/local styles, and lyrics 鈥?free, no credits consumed
* **Video to Music** 鈥?Automatically generate background music that matches your video content (up to 10 videos, 600s total)
* **Stem Separation** 鈥?Split audio into 2 tracks (vocals + instrumental) or 6 individual stems
* **Inpainting** 鈥?Edit specific sections of existing songs (enterprise only)
* **Multiple Output Formats** 鈥?MP3, PCM, Opus with configurable sample rates and bitrates

Available models: **music\_v1**

\[Explore ElevenLabs Documentation 鈫抅(api-reference/eleven/introduction)

***

### 馃帶 Producer 鈥?AI Music Generation

Powered by Google DeepMind's **Lyria 3 Pro** model, this service provides high-quality music generation:

* **Create Music** 鈥?Generate original tracks from sound prompts, lyrics, and images
* **Image-Guided Generation** 鈥?Use images to influence the mood and style of generated music
* **Instrumental Mode** 鈥?Generate without vocals
* **Stem Separation** 鈥?Separate audio into individual stems (vocals, drums, bass, etc.)
* **Multi-Format Export** 鈥?Download as MP3/M4A/WAV audio or generate video with preset visualizers

Available models: **Lyria 3 Pro**

\[Explore Producer Documentation 鈫抅(api-reference/producer/introduction)

***

### 馃挰 Chat 鈥?Multi-Protocol AI Gateway

A unified gateway supporting multiple API protocols:

| Protocol               | Base URL                              | Description                                         |
| ---------------------- | ------------------------------------- | --------------------------------------------------- |
| **OpenAI Compatible**  | `https://api.mountsea.ai/chat`        | Drop-in replacement for OpenAI Chat Completions API |
| **OpenAI Responses**   | `https://api.mountsea.ai/chat`        | OpenAI Responses API format                         |
| **Anthropic (Claude)** | `https://api.mountsea.ai/chat/claude` | Claude Code & Anthropic SDK compatible              |
| **Gemini Native**      | `https://api.mountsea.ai/chat/gemini` | Google Gemini Native API format                     |

* 鉁?Use official SDKs (OpenAI, Anthropic, Google GenAI) directly
* 鉁?Full streaming, function calling, and tool support
* 鉁?Compatible with **Claude Code**, **Cursor**, **Cherry Studio**, and other AI tools
* 鉁?Access GPT-5.1/5.2, Claude 4.5/Opus/Sonnet, Gemini 2.5/3/3.1 models

\[Explore Chat Documentation 鈫抅(api-reference/chat/introduction)

***

## How to Get Started

<Steps>
  <Step title="Get Your API Key">
    Sign up at [offoff.ai](https://offoff.ai), go to **API Keys**, and create a new API key.
  </Step>

  <Step title="Choose Your Service">
    Select the service that fits your needs 鈥?video, image, music, or chat.
  </Step>

  <Step title="Make Your First API Call">
    Use `Authorization: Bearer your-api-key` in your request header and call the appropriate endpoint.
  </Step>

  <Step title="Track & Download Results">
    For async tasks (video/music), poll the task status endpoint until complete, then download your content.
  </Step>
</Steps>

Check out our [Quick Start Guide](quickstart) for step-by-step examples.

***

## API Base URL

All API requests are made to:

```
https://api.mountsea.ai
```

<Note>
  **Exception**: The Claude (Anthropic) compatible API uses `https://api.mountsea.ai/chat/claude` as the base URL.
</Note>

***

## Get Started Today

Ready to integrate AI capabilities into your applications?

* 馃摉 Check out our [Quick Start Guide](quickstart)
* Explore [Mountsea API](api-reference/mountsea-api/introduction) - stable `/ms/v1` gateway for official-key quality, full-platform models
* 鈿?Explore [Hub Premium AI Gateway](api-reference/hub/introduction) 鈥?Nano Banana, GPT Image 2, Veo 3.1, Kling v3, WAN 2.7, Seedance 2.0, ElevenLabs Music
* 馃幀 Explore [Gemini Video & Image API](api-reference/gemini/introduction)
* 馃攲 Try [Gemini Compat API](api-reference/gemini/compat-introduction) with the official `@google/genai` SDK
* 馃毀 [Sora2 Video API](api-reference/sora/introduction) 鈥?**currently unavailable**
* 馃柤锔?Explore [XAI (Grok) Image & Video API](api-reference/xai/introduction)
* 馃帹 Try [OpenAI GPT Image API](api-reference/openai/introduction) with both async tasks and the official `openai` SDK
* 馃幍 Explore [Suno Music API](api-reference/suno/introduction)
* 馃幎 Explore [ElevenLabs Music API](api-reference/eleven/introduction)
* 馃帶 Explore [Producer Music API](api-reference/producer/introduction)
* 馃挰 Explore [Chat LLM Gateway](api-reference/chat/introduction)
* 馃摓 Need help? [Contact us](https://offoff.ai)

***

*Transform your creative projects with the power of AI. Start building amazing applications today!*