Replicate

Tempo

Predict4 endpointsFrom $0.0010 /req

Run open-source AI models on demand. Access thousands of models for image generation, LLMs, video, audio, and more — Stable Diffusion, LLaMA, Whisper, and the entire Replicate model catalog. Pay per prediction.

View documentation

When should an agent use this?

Use Replicate when your agent needs to run open-source AI models without managing infrastructure — generating images with Stable Diffusion, running LLaMA for text generation, transcribing audio with Whisper, or any of thousands of community models. Ideal for AI pipelines that need flexible model access, rapid prototyping, and any workflow that benefits from the open-source model ecosystem.

Endpoints

Click any endpoint to see parameters, pricing, and a ready-to-use curl example.

Paid (3)

Run a model prediction — specify the model owner/name and input parameters. Price varies by model and compute time.

Path/services/replicate/replicate/run

MethodPOST

PriceDynamic (varies per request)

Parameters

Name	Type	Required	Description
model_owner	string	Yes	Model owner/organization (e.g. 'stability-ai', 'meta')
model_name	string	Yes	Model name (e.g. 'sdxl', 'llama-2-70b-chat')
input	object	Yes	Model-specific input parameters (varies by model)
version	string	No	Specific model version hash (optional, uses latest if omitted)

Example Request

curl

curl -X POST \
  "https://api.indiegent.com/services/replicate/replicate/run" \
  -H "Authorization: Bearer <your-token>" \
  -H "X-Agent-Wallet: my-agent" \
  -H "Content-Type: application/json" \
  -d '{
  "model_owner": "stability-ai",
  "model_name": "sdxl",
  "input": {
    "prompt": "A futuristic city skyline at sunset, photorealistic"
  }
}'

Free (1)

IndieGent Endpoint

api.indiegent.com/services/replicate

Payment

USDC · Automatic

Payment protocols handled by IndieGent

Network

Tempo

Get Started ← Back to Ecosystem Browse Marketplace →