Every premium and members-only resource for $9.99/month, as a no-commitment subscription. See the plans

PalateKit

Sign in
Menu

Request a resource

Describe the resource you are missing in one sentence. We will email you when it is published.

0 / 280

A page, a video or an image online.

Unlock PalateKit

Unlock everything

Plan

Paying means accepting our terms of sale.

Secure payment by Stripe. Receipts and invoices sent by email.

Welcome back

Sign in to install, download or save this resource. A free account is enough for free resources.

Calling an LLM through Caffeine Inference v1.0.0

Use this resource to call an LLM from a Caffeine app without a user-supplied API key

New

  • 531 downloads
  • 152 likes
  • 167 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install llm-caffeine-inference-client

With no option, the skill goes to ~/.agents/skills/; add --agent claude-code (or codex, cursor…) to target an agent.

First time: connect the CLI with

npx --yes palatekit@latest login

The agent sets up the backend to call a model through the caffeineai-inference-client package, whose configuration the platform supplies. The app never asks for, stores or returns a key, and model routing is left to the platform.

Mostly picked by

Updated November 2, 2026

Card for the “Calling an LLM through Caffeine Inference” skill

Details

Works in
Install guides
Generates with
Your agent's model
Licence
Apache-2.0

Similar resources

View all

What you get

  • SKILL.md: adding the package and platform-supplied configuration
  • SKILL.md: call shapes, model choice and common pitfalls

Good fit for

  • Your app must summarize, classify or answer through a chatbot
  • You do not want to ask your users for an OpenAI key

Not for

    Tags

    • llm
    • chatbot
    • motoko
    • inference

    About

    You say

    “Add an automatic summary of customer reviews to my app.”

    Card for the “Calling an LLM through Caffeine Inference” skill

    Skill published by caffeinelabs under the Apache-2.0 license, delivered in its original version.

    Show more

    How to use it

    1. Install the skill in your agent's skills folder
    2. Ask your agent to call an LLM from a Caffeine app without a user-supplied API key
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE10.7 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • SKILL.md8.6 KB

    Origin and licence

    Listed unmodified

    Author
    caffeinelabs
    Source
    github.com/caffeinelabs/skills/tree/d03174cc42ab2833293ba1cb313b7593a611a73f/skills/extension-inference
    Licence
    Apache-2.0

    Notice

    « extension-inference » (caffeinelabs, Apache-2.0) livré dans sa version d'origine : fiche en français et en anglais par PalateKit.

    User reviews

    –

    No ratings yet

    Loading reviews…

    Delete your review?

    Your rating and comment will be removed from the page.