Deep Infra

AI API token

Run inference against DeepInfra's hosted models — text, embeddings, images, audio — from any Windmill script, flow or app.

Set up in 3 steps

Create an API token

In the DeepInfra dashboard, open API Tokens and create one. Copy it — it is shown only once.

Add the resource in Windmill

Open Resources, add a resource of type deep_infra, and paste the token.

Run your first script

Fork any script below and read before writing anything. There are dozens here, so search by the verb you need.

Scripts

Building blocks, if none of the projects above fit. Fork one, run it, or call it as a step inside your own flow.

Resource type

deep_infra — the shape of the credential every script on this page expects.

View raw schema →

Field	Type	Required	What it is
token	string	Yes	Some of the APIs are accessible using the API key on the dashboard, others require the JWT token copied from the network tab.

Questions

Inference is billed per token

Every call draws on your DeepInfra balance. A flow that retries on failure can spend more than you expect — cap the retries.

Can it power Windmill AI?

Not directly through this resource. DeepInfra exposes an OpenAI-compatible endpoint, so an openai resource with base_url pointed at it is the way to use it as an AI provider.

Is my token stored on the hub?

Never. It lives only in your own Windmill workspace, encrypted at rest.

Set up in 3 steps

Create an API token

Add the resource in Windmill

Run your first script

Scripts

Usage Api Token

Usage

Upload Lora Model

Update Lora

Text To Speech

Submit Feedback

Set Config

Retrieve Openai Batches

Retrieve Openai Batch

Request Rate Limit Increase

Private Models List

Openai Models

Openai Embeddings

Openai Completions

Openai Chat Completions

Openai Audio Speech

Models List

Models Info

Models Featured

Model Versions

Model Schema

Model Publicity

Model Meta Update

Model Delete

Me

Logs Query

List Files

Inference Model

Inference Deploy

Get Voices

Resource type

Questions