Managed Inference and Agents API Model Cards
Last updated July 17, 2025
Table of Contents
Our model cards contain documentation for each available AI model.
Available Models
The Heroku Managed Inference and Agent add-on is hosted in two regions: us and eu. However, the add-on can be provisioned and accessed from apps in any Heroku region.
Each region offers slightly different models.
Region: us
| Model Documentation | Type | API Endpoint | Model Source | Description |
|---|---|---|---|---|
| claude-4-sonnet | text → text |
v1/chat/completions | Anthropic | A state-of-the-art large language model that supports chat and tool-calling. |
| claude-3-7-sonnet | text → text |
v1/chat/completions | Anthropic | A state-of-the-art large language model that supports chat and tool-calling. |
| claude-3-5-sonnet-latest | text → text |
v1/chat/completions | Anthropic | A state-of-the-art large language model that supports chat and tool-calling. |
| claude-3-5-haiku | text → text |
v1/chat/completions | Anthropic | A faster, more affordable large language model that supports chat and tool-calling. |
| cohere-embed-multilingual | text → embedding |
v1/embeddings | Cohere | A state-of-the-art embedding model that supports multiple languages. This model is helpful for developing RAG (Retrieval Augmented Generation) search. |
| stable-image-ultra | text → image |
v1/images/generations | Stability AI | A state-of-the-art diffusion (image generation) model. |
Region: eu
| Model Documentation | Type | API Endpoint | Model Source | Description |
|---|---|---|---|---|
| claude-4-sonnet | text → text |
v1/chat/completions | Anthropic | A state-of-the-art large language model that supports chat and tool-calling. |
| claude-3-7-sonnet | text → text |
v1/chat/completions | Anthropic | A state-of-the-art large language model that supports chat and tool-calling. |
| claude-3-haiku | text → text |
v1/chat/completions | Anthropic | A faster, more affordable large language model that supports chat and tool-calling. |
| cohere-embed-multilingual | text → embedding |
v1/embeddings | Cohere | A state-of-the-art embedding model that supports multiple languages. This model is helpful for developing RAG (Retrieval Augmented Generation) search. |