Integration
GPU cloud: pods, serverless endpoints and jobs. Your client pastes their RunPod key once, and your agent or your code works with their access.
AI
RunPod is a GPU cloud for AI workloads.
Once your client connects RunPod, your agent can work with pods, serverless endpoints and jobs.
RunPod · AI
GPU cloud: pods, serverless endpoints and jobs
The client pastes their API key from RunPod's settings. We store it encrypted.
Tested against RunPod's live API.
Every tool your agent gets for RunPod. Select one to see its inputs and an example call.
Building with RunPod? The docs have setup steps and code for every tool.
The request tool calls any RunPod endpoint the tools above don't cover, with the client's access attached.
Base URL for request
https://rest.runpod.io/v1
request
HTTPS ANY /v1/clients/{clientId}/runpod/{path}
Any endpoint of RunPod's own API, with the client's access attached.
Over MCP every tool also takes client_id, from list_clients. Over HTTPS send it as clientId to https://api.operate.as/v1.
Related
Get started
Add a client, select the services, copy the link. You'll get an email the moment their access is ready. Start free, no card required. Paid plans are one flat monthly price, and a busy month never takes your agents offline.