Read our latestState of AI development report– explore trends, usage, and emerging patterns!Read the results →
All Posts
Mar 7, 2025
Product Updates
Vellum Product Update | February 2025
2 min

This month we improved how you find models, preview Workflows SDK code, and more!

No items found.

Authors:

No items found.

⚡New Model Support & Workflow Enhancements

💡 It may have been a shorter month, but that didn’t stop us from shipping! We improved how you find models, preview Workflows SDK code, and more.

This month we’re also launching our customer referral program so if you would like to receive a $250 giftcard - sign up to participate!

🔨 Key New Features

  • Workflow SDK Code Preview – If you’re in the beta, you can now preview your Workflow’s code representation directly in the UI!

Just hit the preview button to open a side panel with full code visibility.

Which will open a side panel with a full representation of your Workflow in code form.
  • Restore Button Moved – Now relocated to the History Cards for easier access when reverting Prompts and Workflows to a prior state.
  • Workflow Node Layout Improvements – Input variables now appear above output types, making Workflows easier to read at a glance. Code Execution, Templating, and Final Output Nodes are all affected by this change.
  • Model Picker Enhancements – Find the right model faster with sorting options (by name, introduction date, or last use). Plus, filter and sort preferences are now saved across sessions.

🗂 Multiple Chat History Variables – You can now include more than one Chat History variable in Prompts where needed.

Application-Wide Performance Boosts – We did some big overhauls on our backend resulting in faster page load times across the board.

🧠 New Model Support:

GPT-4.5 Preview via OpenAI

Llama 3.2 and Llama 3.3 models via AWS Bedrock (us-west-2)

xAI’s Grok Models (Grok Beta, Grok Vision Beta, Grok 2 1212, and Grok 2 Vision 1212)

Multiple Gemini Models via Vertex AI (Gemini 2.0 Flash 001, Flash Lite, Pro, Flash Experimental, and Gemini 1.5 Flash)

DeepSeek V3 via Fireworks AI (More model flexibility for your AI workflows)

OpenAI’s o3-mini (2025-01-31 Snapshot) via Azure (supported for self-hosting)

More choices, better performance—pick the model that fits your needs!

💰 Customer Referral Program:

Know of 5+ people in your network who would also love Vellum? This month we’re offering a $250 Amazon gift card if you connect 5 people in your network who would also love to use Vellum.

Sign up here to participate and we’ll email you with next steps.

If you’re ready to explore these updates, log in to Vellum now and start building!

As always, we’d love your feedback!

Changelog: https://docs.vellum.ai/changelog/2025/2025-02

ABOUT THE AUTHOR
Sharon Toh
Product and Growth Marketing

Sharon brings a background in product marketing and a proven ability to help SaaS companies achieve remarkable growth. With a well-established history of crafting strategies that resonate with audiences, she’s passionate about bridging the gap between cutting-edge AI solutions and the people who need them most. As part of Vellum's GTM team, Sharon focuses on connecting businesses and people with the right solutions that deliver impact, making advanced technology accessible and effective.

No items found.
The Best AI Tips — Direct To Your Inbox

Latest AI news, tips, and techniques

Specific tips for Your AI use cases

No spam

Oops! Something went wrong while submitting the form.

Each issue is packed with valuable resources, tools, and insights that help us stay ahead in AI development. We've discovered strategies and frameworks that boosted our efficiency by 30%, making it a must-read for anyone in the field.

Marina Trajkovska
Head of Engineering

This is just a great newsletter. The content is so helpful, even when I’m busy I read them.

Jeremy Hicks
Solutions Architect
Related Posts
View More

Experiment, Evaluate, Deploy, Repeat.

AI development doesn’t end once you've defined your system. Learn how Vellum helps you manage the entire AI development lifecycle.