Request AccessLLM

Replicate

Run open-source ML models in the cloud

Deploy and run thousands of open-source machine learning models through Replicate's simple API.

Request AccessView Docs

Features

✓Thousands of open-source models
✓Custom model deployment
✓Automatic scaling
✓Streaming predictions
✓Webhook callbacks

Integration Example

Use Replicate through Keystore with zero code changes. Keys are resolved from the vault and injected at request time.

replicate-example.ts
1
2
3
4
5
6
7
8
9
10
11
12
13
14
import Keystore from "@keystore/sdk";

const ks = new Keystore({ agentToken: process.env.KS_TOKEN! });
ks.interceptAll();

const res = await fetch("https://api.replicate.com/v1/predictions", {
  method: "POST",
  headers: { "Content-Type": "application/json" },
  body: JSON.stringify({
    version: "stability-ai/sdxl:latest",
    input: { prompt: "A futuristic city at sunset" },
  }),
});
const prediction = await res.json();

Use Cases

Image generation pipelines
Audio processing agents
Custom ML model serving
Multi-modal AI workflows

Ready to use Replicate?

Request access and our concierge team will provision credentials for you — usually within 24 hours. No setup on your end.

Request Access