# ModelRunner

> ModelRunner — ai-modelrunner-mcp. Use this tool when you need to streamline the deployment and execution of multiple AI models across various media types, such as images, videos, audio, and 3D models. ModelRunner solves the problem of managing numerous models and billing complexities by providing a unified API with pay-per-use billing. It takes in media inputs and returns model outputs, making it ideal for applications requiring flexible and scalable AI model execution.

Canonical page: https://skillsregistry.net/skills/ai-modelrunner-mcp  
JSON: https://api.skillsregistry.net/v1/skills/ai-modelrunner-mcp

## Description

Run 100+ AI models — image, video, audio, 3D — through one API with pay-per-use billing.

## Trust

- **Trust score (0–1):** 0.70
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** media
- **Updated:** 2026-09-28

## Source

- **Source listing:** [MCP Registry](https://registry.modelcontextprotocol.io/v0/servers/ai.modelrunner%2Fmcp)
- **Repository:** <https://github.com/modelrunner/modelrunner-mcp>

## Use it

MCP endpoint published by the skill: `https://mcp.modelrunner.run/mcp`

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "ai-modelrunner-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/ai-modelrunner-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/ai-modelrunner-mcp/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt