apimodels
One account for chat, image, video, speech and music models, via local or hosted MCP
- Pricing
- Paid
- Platforms
- API, CLI
- Runs
- Locally or Remotely
- Version
- 0.9.0
- Listing updated
- 3 days ago
About apimodels
apimodels is a paid MCP server for design and media. It can run locally on your machine or as a hosted remote server.
Instead of a separate key per vendor, apimodels.app is an aggregation API, and its MCP server lets Claude Desktop, Cursor, Codex and other clients generate media and chat with those models. The README names GPT-6.1, Claude, Gemini, GLM, DeepSeek, Qwen, Seedance, Veo, Kling and gpt-image-2, billed in USD on successful generations only.
There are two ways in. A local npx package signs in with a browser authorization and stores a key in ~/.apimodels/credentials.json, and a Claude Code or Codex plugin bundles it with a skill about picking models and asking before spending. A hosted Streamable HTTP server at api.apimodels.app/mcp uses OAuth; it cannot read local files, so the agent calls get_upload_url instead. Long jobs return a task id after about 50 seconds, to be polled with get_task.
The site describes pay-as-you-go top-ups from $10 and claims discounts up to 95% against official prices, and the pricing table shows the model-by-model tiers. These are the vendor's own claims.
Install
Run in a terminal
claude mcp add --transport http apimodels-mcp https://api.apimodels.app/mcpAdd to Settings → Connectors → Add custom connector
https://api.apimodels.app/mcpAdd to ~/.cursor/mcp.json
{
"mcpServers": {
"apimodels-mcp": {
"url": "https://api.apimodels.app/mcp"
}
}
}Add to .vscode/mcp.json
{
"servers": {
"apimodels-mcp": {
"type": "http",
"url": "https://api.apimodels.app/mcp"
}
}
}Add to ~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"apimodels-mcp": {
"serverUrl": "https://api.apimodels.app/mcp"
}
}
}Add to your client's MCP settings (most use this shape)
{
"mcpServers": {
"apimodels-mcp": {
"type": "http",
"url": "https://api.apimodels.app/mcp"
}
}
}Configuration
APIMODELS_API_KEYYour sk_… API key from https://apimodels.app/console/api-keysRequiredAPIMODELS_BASE_URLAPI base URL. Default https://api.apimodels.app/v1APIMODELS_WAIT_SECONDSDefault wait_seconds for generate_image / generate_video / text_to_speech / transcribe_audio / get_task before they hand back a task id. Default 50 (Codex aborts tool calls at 60 s).APIMODELS_TIMEOUT_MSDeprecated: same wait in milliseconds, honoured for old configs.
Tools this server provides (14)
Taken from the project documentation; the running server may differ.
- generate_image
- Generate an image.
- generate_video
- Generate a video.
- text_to_speech
- Convert text to speech.
- get_task
- Check a long-running task by id.
- chat
- Chat with a language model.
- review_image
- Review an image.
- embed
- Create embeddings.
- extract_media
- Extract media.
- upload_asset
- Upload an asset.
- delete_asset
- Delete an asset.
- clone_voice
- Clone a voice.
- delete_voice
- Delete a voice.
- write_lyrics
- Write lyrics.
- get_upload_url
- Get a URL for uploading a file from the hosted server.
What it does
- Media generation
- Generate images, video and speech with a key.
- Chat and embeddings
- Call chat models and embeddings from the same account.
- Task polling
- Long renders return a task id to check later.
- Asset and voice tools
- Upload assets, clone voices and write lyrics.
- Local or hosted
- npx package or OAuth hosted server.
- Spend-aware plugin
- Codex approves calls that spend credits.
Good for
- Render a short video from a prompt
- Generate voice-over for a script
- Pick a model for an image edit
- Plan and render a product video shot by shot
- Chat with several vendors' models via one key
Pricing
Paid
Pay as you go from a $10 top-up; no monthly fee
Prices change. Check apimodels.app before you buy.
apimodels FAQ
How do I sign in?
Run npx -y apimodels-mcp login for a browser authorization, or add the hosted URL and authorize with OAuth.
Am I billed for failures?
The site says billing is success-only; failed requests are not charged.
What is the minimum top-up?
The site says you can start with as little as $10.
Why can the hosted server not read my files?
It runs remotely, so the agent uses get_upload_url to upload.
Is apimodels free?
No. apimodels is a paid product.
How do I add apimodels to Claude Code?
Run this command in your terminal: claude mcp add --transport http apimodels-mcp https://api.apimodels.app/mcp
What are the best alternatives to apimodels?
The closest alternatives to apimodels are HyperFrames by HeyGen, ffmpeg-skill, Claude Code Ultimate Guide, AvatarSay — Fictional Character & Talking Video MCP and ChartAnt.
Alternatives to apimodels

HyperFrames by HeyGen
MCP serverHosted MCP connector for creating and rendering videos from HTML through AI chat
- Remote
- Freemium
- 85.3K GitHub stars
- Design and media

ffmpeg-skill
MCP serverLocal FFmpeg video and audio editing tools for coding agents over MCP
Runs locally- Open source
- 6.9K GitHub stars
- Design and media

Claude Code Ultimate Guide
MCP serverMCP server for searching the Claude Code Ultimate Guide from any MCP client
Runs locally- Open source
- 6.5K GitHub stars
- AI models and LLM tooling

Generate fictional character portraits and lip-synced talking videos from text over MCP
- 10 tools
- Remote
- Freemium
- Design and media

ChartAnt
MCP serverRemote MCP server returning charts, maps and dashboards as hosted PNG links
- 51 tools
- Remote
- Freemium
- Design and media

VfxSmith
MCP serverSearch, generate, refine and export pixel art game effects from Claude Code or Codex
Not checked yet- Remote
- Freemium
- Design and media