Search overlay panel for performing site-wide searches

Boost Performance & Scale with Postgres Advanced. Join Pilot Now!

Heroku AI

Heroku AI: Accelerating AI Development With New Models, Performance Improvements, and Messages API

This month marks significant expansion for Heroku Managed Inference and Agents, directly accelerating our AI PaaS framework. We’re announcing a substantial addition to our model catalog, providing access to leading proprietary AI models such as Claude Opus 4.5, Nova 2, and open-weight models such as Kimi K2 thinking, MiniMax M2, and Qwen3. These resources are fully managed, secure, and accessible via a single CLI command. We have also refreshed aistudio.heroku.com, please navigate to aistudio.heroku.com from your Managed Inference and Agents add-on to access the models you have provisioned.

Whether you are building complex reasoning agents or high-performance consumer …

Faster Agents with Automatic Prompt Caching

Heroku is launching automatic prompt caching starting December 18, 2025. Prompt caching delivers a notable, zero-effort performance increase for Heroku Managed Inference and Agents. Enabled by default, this feature is designed to deliver significantly faster responses for common workloads. We have taken a pragmatic approach and currently only enabled this to cache system prompts and tool definition, and not user messages or conversation history. You can disable caching for any request by setting X-Heroku-Prompt-Caching: false.

Heroku Introduces New Innovations to Expand the Capabilities of Every Salesforce Org

Today’s businesses face a tremendous amount of complexity in tools, data silos, and systems that teams need to navigate to deliver unique and engaging experiences to their customers. Meanwhile developers are only able to spend a fraction of their time coding due to the cognitive load of technology complexity, constant context switching, and figuring out how to adopt AI effectively into their daily work.

The Heroku AI PaaS is the Cloud Native Application Platform from Salesforce to seamlessly build and scale any custom service for greenfield app development, modernizing existing apps, and as part of a Salesforce cloud implementation.

At Dreamforce, we are excited to introduce new innovations to our AI PaaS that expand the capabilities of every Salesforce org and empower new builders. Today’s announcement includes innovations in three key areas:

  1. Expanding the capabilities of every Salesforce org with the flexibility of more pro-code and elastic compute with enterprise performance, scale and security enhancements.
  2. Enhancing and expanding the data foundation to empower our customers’ modern and AI app strategies.
  3. Delivering new vibes using AI to make the process of building new applications as accessible as sending a text message.

Welcome to Heroku Vibes

Introducing the pilot of Heroku Vibes, your collaborative agent for turning ideas into running apps.

For those who have been with us on this journey for a while, the name “Heroku Garden” might stir up a bit of nostalgia. It was the web experience that enabled developers to become immediately productive in creating and deploying Rails applications with a turnkey, opinionated environment, with the goal of making software easier and more accessible. That seed of an idea that would grow into the platform powering millions of mission-critical apps. We’re thrilled to announce the pilot of Heroku Vibes, a reimagining …

Heroku AI Studio is Your Workspace for Smarter, Faster AI Apps

Ever found yourself in the endless loop of tweaking a prompt, running your code, and waiting to see if you finally got the output you wanted? That slow, frustrating feedback cycle is a common headache for AI developers. What if you could speed that up and get back to what you do best? Let’s focus on building amazing applications.

We're excited to introduce Heroku AI Studio, a new set of tools designed to streamline your generative AI development from prompt to production. We've focused on creating a more intuitive and efficient workflow, so you can focus on innovation instead of wrestling with your development environment. When using the Heroku Managed Inference and Agents add-on, this new tool is about to become an essential part of your workflow.

Discover How Heroku’s AI PaaS Delivers Real-World Results at Dreamforce

The AI revolution presents a critical challenge: moving from experimentation to production. This year, Heroku has evolved beyond a traditional PaaS to become an AI PaaS, a fully managed platform designed to solve this problem and accelerate the delivery of AI-powered apps. With new capabilities like AppLink, Managed Inference and Agents, and MCP on Heroku, Heroku now provides a fully managed platform designed for the AI era.

This evolution accelerates the delivery of AI-powered apps and intelligent agents, bringing a new level of speed and simplicity to your development process. Dreamforce 2025 is your chance to see firsthand how the Heroku AI PaaS is delivering business value faster and with less complexity.

Amazon Nova Models: Now Available on Heroku

Building intelligent applications requires powerful, cost-effective AI. Today, we’re simplifying that process by making Amazon’s cutting-edge Nova models directly available via Heroku Managed Inference and Agents. Provisioning these models is as simple as attaching the add-on to your Heroku application, providing a direct, managed path for developers and businesses to leverage a new class of powerful and cost-effective AI models with unparalleled simplicity.

Heroku AI Expands Model Offering with OpenAI’s gpt-oss-120b

Start building with OpenAI’s new open-weight model, gpt-oss-120b, now available on Heroku Managed Inference and Agents. This gives developers a powerful, transparent, and flexible way to build and deploy AI applications on the platform they already trust. Access gpt-oss-120b with our OpenAI-compatible chat completions API, which you can drop into any OpenAI-compatible SDK or framework.

Building Data-Aware AI Applications with Heroku AI and LlamaIndex

Building AI applications that can interact with private data is a common goal for many organizations. The challenge often lies in connecting large language models (LLMs) with proprietary datasets. A combination of Heroku Managed Inference and Agents and LlamaIndex provides an elegant stack for this purpose.

This post explores how to use these tools to build retrieval-augmented generation (RAG) applications. We’ll cover the technical components, Use Cases and the development process, and how to get started.

Building Agents With Heroku AI and Pydantic AI

Building production-grade AI applications can be complex, but with Heroku and Pydantic AI, developers gain a powerful and reliable solution for integrating advanced AI capabilities. Heroku makes it easy to integrate AI into your applications with Heroku Managed Inference and Agents. With a single click, you can attach powerful Large Language Models like Anthropic’s Claude 4 Sonnet to your apps. Heroku AI also provides built-in tools like secure code execution and an OpenAI-compatible API that you can drop directly into popular frameworks and SDKs.

Subscribe to the full-text RSS feed for Heroku AI.