Skip to main content

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 โ€” including video generation, image creation, music production, and multi-model LLM chat.

Overview

Mountsea AI provides a unified API gateway to access the worldโ€™s leading AI models across video, image, music, and language domains. We offer five core services:

Why Mountsea AI Stands Out

All-in-One API Platform

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

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 โ€” just change the base_url.

Comprehensive AI Model Coverage

Access top-tier AI models from leading providers:
DomainModels
VideoVeo 2, Veo 3, Veo 3.1, Sora-2, Sora-2-Pro
ImageNano Banana Fast, Nano Banana Pro, Nano Banana 2
MusicSuno (chirp-v35 ~ chirp-v50), FUZZ-0.8 ~ FUZZ-2.0 Pro
LLMGPT-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

๐ŸŽฌ Google (Gemini) โ€” Video & Image Generation

Powered by Googleโ€™s cutting-edge AI, this service provides:
  • Video Generation โ€” Create videos from text prompts (text2video), images (img2video), or reference ingredients (ingredients2video) using Veo 2 / Veo 3 / Veo 3.1 models
  • Video Upsampling โ€” Upscale to 1080p or 4K resolution, or generate GIF previews
  • Video Reshoot โ€” Re-generate video with different camera motions (pan, zoom, dolly, etc.)
  • Video Object Editing โ€” Insert or remove objects from videos using masks
  • Prompt Expansion โ€” Expand simple prompts into detailed cinematic descriptions
  • Image Generation โ€” Create and edit images using Nano Banana models (Fast / Pro / 2) with support for multiple aspect ratios and up to 4K resolution
Explore Gemini Documentation โ†’

๐ŸŽฅ Sora2 โ€” OpenAI Video Generation

Powered by OpenAIโ€™s Sora, this service provides:
  • Text-to-Video Generation โ€” Create high-quality videos from text prompts using Sora-2 or Sora-2-Pro models
  • Image-to-Video โ€” Use reference images to guide video generation
  • Character Roles โ€” Create custom characters from short video clips, then reference them in prompts with @character_name
  • Style Presets โ€” Choose from styles like anime, retro, comic, vintage, and more
  • Flexible Video Formats โ€” Landscape/portrait orientation, variable durations (10s/15s/25s), optional watermark removal
Explore Sora2 Documentation โ†’

๐ŸŽต Suno โ€” Music Generation

Powered by Suno AI, this service provides a full suite of music creation tools:
  • Music Generation โ€” Create, extend, cover, mashup, and sample music tracks with models from chirp-v35 to chirp-v50
  • Lyrics Generation โ€” Generate original lyrics or mashup lyrics from two songs
  • Audio Processing โ€” Concat clips, remaster tracks, adjust playback speed
  • Audio Export โ€” Export to MP4 (with visualizer) or WAV format
  • Advanced Features โ€” Persona/timbre creation, stem separation, timing analysis, downbeat detection, style tag enhancement
  • Upload & Process โ€” Upload external audio files for cover, extend, or other operations
Explore Suno Documentation โ†’

๐ŸŽง Producer โ€” Professional Music Production

Powered by FUZZ models, this service provides professional-grade music generation and editing:
  • Create Music โ€” Generate original tracks with style prompts, negative prompts, and time-range control
  • Extend Music โ€” Seamlessly continue existing tracks from any position
  • Cover Music โ€” Transform music into different styles while preserving structure
  • Replace Section โ€” Replace specific portions of a track with new content
  • Swap Vocals / Sound โ€” Replace vocals or instrumental independently
  • Music Variation โ€” Create variations of existing tracks
  • Stem Separation โ€” Separate audio into individual stems
  • Download โ€” Export as MP3/M4A/WAV audio or generate video with preset visualizers
Available models: FUZZ-2.0 Pro, FUZZ-2.0, FUZZ-2.0 Raw, FUZZ-1.1 Pro, FUZZ-1.1, FUZZ-1.0 Pro, FUZZ-1.0, FUZZ-0.8 Explore Producer Documentation โ†’

๐Ÿ’ฌ Chat โ€” Multi-Protocol AI Gateway

A unified gateway supporting multiple API protocols:
ProtocolBase URLDescription
OpenAI Compatiblehttps://api.mountsea.ai/chatDrop-in replacement for OpenAI Chat Completions API
OpenAI Responseshttps://api.mountsea.ai/chatOpenAI Responses API format
Anthropic (Claude)https://api.mountsea.ai/chat/claudeClaude Code & Anthropic SDK compatible
Gemini Nativehttps://api.mountsea.ai/chat/geminiGoogle Gemini Native API format
  • โœ… Use official SDKs (OpenAI, Anthropic, Google GenAI) directly
  • โœ… Full streaming, function calling, and tool support
  • โœ… Compatible with Claude Code, Cursor, Cherry Studio, and other AI tools
  • โœ… Access GPT-5.1/5.2, Claude 4.5/Opus/Sonnet, Gemini 2.5/3/3.1 models
Explore Chat Documentation โ†’

How to Get Started

1

Get Your API Key

Sign up at shanhaiapi.com, go to API ๅฏ†้’ฅ็ฎก็†, and create a new API key.
2

Choose Your Service

Select the service that fits your needs โ€” video, image, music, or chat.
3

Make Your First API Call

Use Authorization: Bearer your-api-key in your request header and call the appropriate endpoint.
4

Track & Download Results

For async tasks (video/music), poll the task status endpoint until complete, then download your content.
Check out our Quick Start Guide for step-by-step examples.

API Base URL

All API requests are made to:
https://api.mountsea.ai
Exception: The Claude (Anthropic) compatible API uses https://api.mountsea.ai/chat/claude as the base URL.

Get Started Today

Ready to integrate AI capabilities into your applications?
Transform your creative projects with the power of AI. Start building amazing applications today!