apimodels runs on your own machine — the client starts it, so there is no endpoint to ping. 624 installs a week from npm. Last commit 18 Sep 2026.
Image, video, chat and speech models with one API key. The model can review its own images.
Today is the operative word: we check apimodels every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add apimodels-mcp -- npx -y apimodels-mcp
{
"mcpServers": {
"apimodels-mcp": {
"args": [
"-y",
"apimodels-mcp"
],
"command": "npx"
}
}
}
[mcp_servers.apimodels-mcp]
command = "npx"
args = ["-y", "apimodels-mcp"]
{
"mcpServers": {
"apimodels-mcp": {
"args": [
"-y",
"apimodels-mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"apimodels-mcp": {
"args": [
"-y",
"apimodels-mcp"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
APIMODELS_API_KEY (Your sk_… API key from https://apimodels.app/console/api-keys), APIMODELS_BASE_URL (API base URL. Default https://api.apimodels.app/v1), APIMODELS_TIMEOUT_MS (Max milliseconds to wait for an image / video / audio task. Default 300000).
The author declared them in the registry entry; get the values from the project itself.
One API for 100+ AI video, image, music and speech models.
One key, 100+ models — chat with any LLM and generate video, images, speech. Free trial at 370.ai.
Generate text, images, speech, music, and video with any AI model, from one credit balance.
Generate images, video, music, speech and text with 60+ models through your MostAI account.
Generate video, images, audio and speech with Vidofy — Veo 3.1, Kling 3.0, Flux 2 and 570+ models.
AI image, video, and audio generation for MCP — one API key, every model, wiring never changes.
Create images & video from any MCP agent — 17 models, spend limits, one URL.
AI model releases, price changes and deprecations in one feed: chat, embedding, speech, video.
Answers built from our own checks of this server.