apimodels MCP
An MCP server that aggregates 150+ AI models for image, video, LLM, and audio generation. It allows agents to call models from providers like OpenAI, Anthropic, and Google through a unified API with automatic failover and pay-as-you-go billing.
Package and access
Local package with source-attributed installation metadata. Koskamo does not execute packages during review.
Checks and signals
Each line is separate evidence, not a trust score.
- Popularity 1 GitHub star
What you can do with it
- Generate images using models like GPT Image 2.5 or Nano Banana
- Create video content with Seedance 2.5 or Wan 3.0
- Generate speech and audio via ElevenLabs or Grok Voice
- Chat with LLMs like Claude Opus 5.5 or GPT-6
Source and maintenance
- Last repository push
- Maintenance checked
Packages and installation
Source-provided package data. Koskamo has not executed or live-probed this package.
apimodels-mcp 0.7.0
{
"version": "0.7.0",
"transport": "stdio",
"identifier": "apimodels-mcp",
"registryType": "npm",
"environmentVariables": [
{
"name": "APIMODELS_API_KEY",
"format": "string",
"isRequired": true,
"description": "Your sk_… API key from https://apimodels.app/console/api-keys"
},
{
"name": "APIMODELS_BASE_URL",
"format": "string",
"description": "API base URL. Default https://api.apimodels.app/v1"
},
{
"name": "APIMODELS_WAIT_SECONDS",
"format": "string",
"description": "Default wait_seconds for generate_image / generate_video / text_to_speech / get_task before they hand back a task id. Default 50 (Codex aborts tool calls at 60 s)."
},
{
"name": "APIMODELS_TIMEOUT_MS",
"format": "string",
"description": "Deprecated: same wait in milliseconds, honoured for old configs."
}
]
}Tools
Reported by the attributed source; not independently observed by Koskamo.
Maintenance history
Public check and source-refresh events. Editorial and ownership records remain private.
- · repository · passed · metadata changed · updated
- · backfill · recorded · Pre-expansion baseline; unobserved rich metadata remains unknown
Connect from your client
Each snippet configures the same source-provided package; replace placeholders before use.
Cursor
{
"mcpServers": {
"apimodels-mcp-mcp": {
"command": "npx",
"args": [
"-y",
"apimodels-mcp@0.7.0"
],
"env": {
"APIMODELS_API_KEY": "<YOUR_APIMODELS_API_KEY>",
"APIMODELS_BASE_URL": "<YOUR_APIMODELS_BASE_URL>",
"APIMODELS_WAIT_SECONDS": "<YOUR_APIMODELS_WAIT_SECONDS>",
"APIMODELS_TIMEOUT_MS": "<YOUR_APIMODELS_TIMEOUT_MS>"
}
}
}
}Cline
{
"mcpServers": {
"apimodels-mcp-mcp": {
"command": "npx",
"args": [
"-y",
"apimodels-mcp@0.7.0"
],
"env": {
"APIMODELS_API_KEY": "<YOUR_APIMODELS_API_KEY>",
"APIMODELS_BASE_URL": "<YOUR_APIMODELS_BASE_URL>",
"APIMODELS_WAIT_SECONDS": "<YOUR_APIMODELS_WAIT_SECONDS>",
"APIMODELS_TIMEOUT_MS": "<YOUR_APIMODELS_TIMEOUT_MS>"
}
}
}
}VS Code
{
"servers": {
"apimodels-mcp-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"apimodels-mcp@0.7.0"
],
"env": {
"APIMODELS_API_KEY": "<YOUR_APIMODELS_API_KEY>",
"APIMODELS_BASE_URL": "<YOUR_APIMODELS_BASE_URL>",
"APIMODELS_WAIT_SECONDS": "<YOUR_APIMODELS_WAIT_SECONDS>",
"APIMODELS_TIMEOUT_MS": "<YOUR_APIMODELS_TIMEOUT_MS>"
}
}
}
}Claude Desktop
{
"mcpServers": {
"apimodels-mcp-mcp": {
"command": "npx",
"args": [
"-y",
"apimodels-mcp@0.7.0"
],
"env": {
"APIMODELS_API_KEY": "<YOUR_APIMODELS_API_KEY>",
"APIMODELS_BASE_URL": "<YOUR_APIMODELS_BASE_URL>",
"APIMODELS_WAIT_SECONDS": "<YOUR_APIMODELS_WAIT_SECONDS>",
"APIMODELS_TIMEOUT_MS": "<YOUR_APIMODELS_TIMEOUT_MS>"
}
}
}
}Let your agent find its tools
Find servers like apimodels MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.