For AI agents: a documentation index is available at the root level at /llms.txt and /llms-full.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
BlogLog InRequest Demo
HomeProductDevelopersSelf-HostingChangelog
HomeProductDevelopersSelf-HostingChangelog
  • Getting Started
    • Overview
  • Agent Builder
    • Using the Agent Builder
  • Prompts
    • Prompt Engineering
    • Collaboration
    • Custom Models
    • Multimodality
    • Prompt Caching
  • Workflows
    • Introduction
    • Experimenting
    • Integrating
    • Function Calling
  • Evaluation & Test Suites
    • Quantitative Evaluation
    • Evaluating RAG Pipelines
    • Online Evaluations
  • Metrics
    • Out of the Box Metrics
    • Custom Metrics
    • Reusing Metrics in Test Suites
  • Deployments
    • Deployment Lifecycle Management
    • Observability in Production
    • Environments
    • Release Tags
    • Release Reviews
  • Monitoring
    • Monitoring Production Trends
    • Track Workflow Execution Costs
    • Datadog Integration
    • Webhook Integration
    • Execution URLs
  • Documents
    • Uploading Documents
    • Integrating w/ Search API
    • Metadata Filtering
  • Security
    • Data Privacy and Storage
    • HMAC Authentication
    • Role-Based Access Control (RBAC)
    • Static IPs
  • Organizations
    • Manage Organization Access
    • Data Retention Policies
LogoLogo
BlogLog InRequest Demo
On this page
  • Adding Private Models
  • Adding Public Models
  • Request a Model
Prompts

Integrate Custom Models in Your Vellum Workspace Easily

Was this page helpful?
Previous

Input Images and Documents in Prompts and Workflows

Next
Built with

Vellum supports several of the industry’s most popular models by default available in your workspace right away. However, you may wish to use a custom model that gives your business some additional advantage not provided by these off the shelf models, such as higher rate limits or more domain-specific training. These models can also be set up for use within Vellum!

Custom models fall under two categories: private models and public models. Both could be added via the Models tab within Vellum.

Models Tab

Adding Private Models

Private models are new instances of models that were created by you outside of Vellum and are looking to integrate into the platform. When you navigate to the models page, the supported types of private models will be accessible from a section on the top of the page:

Adding Private Custom Models

Clicking on one of the templates will take you to an onboarding flow on how to connect your private model to Vellum. Once you’ve completed the pre-requisite steps and add in the requested form info, your model should be successfully added to your workspace!

We currently support the following private Model Templates:

  • OpenAI models hosted on Azure
  • OpenAI fine-tuned models
  • Fine-tuned models hosted on Fireworks AI

Adding Public Models

Public models are shared instances of models that are hosted by model providers and are granted access to them by various authentication schemes, most commonly via an API Token. Some are enabled in your workspace by default when you create a new workspace in Vellum. To find other public models not yet enabled in your workspace, navigate to the models page and scroll down to the Available Models section:

Adding Public Custom Models

To help filter the options, you could select just Available in the drop down on the right or use the search bar to look for the specific model of interest.

While most of these models require just adding your API key from the relevant model provider, some like those from AWS Bedrock will require some additional steps taken within your account. These directions will be laid out within each model’s onboarding modal when you click to enable them in your workspace.

Request a Model

Don’t see a custom model listed here but want to try it within Vellum? Reach out to us on Slack for support!