replicate-runner

Replicate Runner

When to Use

Trigger phrases:

• "replicate runner"

• "Run AI models on Replicate cloud API"

• When running AI models without managing GPU infrastructure

• When generating images, videos, or audio with state-of-the-art models

• When deploying custom models to a cloud API

• When chaining multiple AI models in a pipeline

Anti-Rationalization Table

Excuse	Reality	Rule
"I'll just use the API directly"	Replicate API changes; runner abstraction insulates your code	One integration point, not N scattered calls
"Docker is enough"	Docker lacks model versioning, caching, cost tracking	Runner adds observability and governance
"I don't need model routing"	Different models excel at different tasks	Route automatically; don't hardcode

Trigger phrases:

• "replicate runner"

• "Run AI models on Replicate cloud API"

• When running AI models without managing GPU infrastructure

• When generating images, videos, or audio with state-of-the-art models

• When deploying custom models to a cloud API

• When chaining multiple AI models in a pipeline

When NOT to Use

• For local inference (use Ollama skills)
• For OpenAI-compatible endpoints (use OpenAI skills)
• For fine-tuning (use training-specific skills)

Overview

Access 1000+ AI models via Replicate API. Run Flux, Stable Diffusion, Whisper, and custom models with a single API call. Pay per second of compute.

Setup & Configuration

1. Get API Token

Sign up at replicate.com, then create an API token in your account settings.

2. Environment Variable

export REPLICATE_API_TOKEN=r8_xxxxxxxxxxxxxxxxxxxx

Or store in .env:

REPLICATE_API_TOKEN=r8_xxxxxxxxxxxxxxxxxxxx

3. Install SDK

Python:

pip install replicate

Node.js:

npm install replicate

4. SDK Initialization

Python:

import replicate
# Token auto-reads from REPLICATE_API_TOKEN env var