Pricing

Vellum has two plans: Base (free) and Pro (paid). Pro comes in three preset packages (Mighty, Super, Ultra) that bundle machine size, storage, and monthly credits, or you can build a Custom configuration by selecting each component individually.

Base

Free, forever. Includes everything you need to run an assistant:

• Small machine size (1 vCPU, 2 GiB RAM)
• 6 GiB of persistent storage
• Pay-as-you-go credits (no monthly minimum)
• Managed LLM credentials (Vellum covers the API keys)

Pro packages

Three preset packages that bundle a machine size, storage tier, and monthly credit allowance into a single monthly price. Each package is a starting point: you can adjust individual tiers afterward, which converts your plan to a Custom configuration.

Mighty is the entry-level Pro package. You get 10 GiB of storage and $25 in monthly credits on the standard Small machine. The $10/mo platform fee is not included, so there is no custom subdomain, static IP, or priority support.

Super steps up to a Medium machine with 30 GiB of storage and $45 in monthly credits. The platform fee is included, so you get a custom subdomain, static IP, and priority support.

Ultra is the most powerful package: a Large machine, 60 GiB of storage, and $115 in monthly credits, with the platform fee included.

Custom

Prefer to pick your own components? The Custom plan lets you select a machine size, storage tier, and optional credit bundle individually. Your monthly total is the sum of:

• Platform fee ($10/mo): custom subdomain, static IP, priority support
• Machine tier: $35, $60, or $125/mo (Medium, Large, or XL)
• Storage tier: $5 to $30/mo (10 to 120 GiB)
• Credit bundle (optional): $10 to $200/mo

The minimum Custom configuration is $50/mo (Medium machine + 10 GiB storage, no credit bundle). Credits are still pay-as-you-go on top of any bundle you choose. If you start on a package and later change any individual tier, your plan automatically becomes Custom.

Machine sizes

Sets the maximum compute for assistants in your org. The Small machine is included with Base and the Mighty package. Medium, Large, and XL are available on the Custom plan and the Super and Ultra packages. Resizable anytime from the assistant's settings page.

Storage

Persistent disk for files, notes, and conversation history. Storage grows online, no assistant restart needed. Base includes 6 GiB. Pro packages and the Custom plan offer the following tiers:

250 GiB and 500 GiB tiers are available only to existing subscribers who already have them. New subscriptions and tier changes are limited to the tiers listed above.

Credit bundles

Pro packages include a monthly credit allowance (for example, $25 with Mighty, $45 with Super). On the Custom plan, you can add an optional recurring credit bundle to your subscription:

Credit bundles are charged as a recurring subscription line item. They are separate from pay-as-you-go credit top-ups: bundles give you a set amount each month, while pay-as-you-go credits let you add more anytime. One Vellum Credit equals one US dollar.

Changing your plan

All plan changes are in Settings → Billing.

• Upgrade to Pro. Pick a package (Mighty, Super, or Ultra) or start with a Custom configuration. Complete Stripe Checkout. Active immediately.
• Change tiers. Switch machine, storage, or credit tier anytime. Changes are prorated. Modifying any tier on a package converts your plan to Custom.
• Cancel. Takes effect at period end. Pro features stay active until then.

Vellum uses a prepaid credit balance: usage is deducted from your credits as you use the assistant. You can add credits anytime from the Billing page via Stripe Checkout. Applicable taxes may be added during checkout.

In the app, your Billing screen shows a Credit Balance plus a breakdown of settled and pending amounts:

• Credit Balance: the current amount available after pending compute is considered.
• Settled Balance: charges that have already settled.
• Pending Usage: estimated in-flight compute that may not be fully settled yet.

The purchase and use of Vellum Credits is governed by Section 6 of our Terms of Service.

Vellum makes available certain features and functionalities within the Services, as designated by Vellum from time to time, that are accessible exclusively through the use of prepaid credits (“Vellum Credits”). These designated features and functionalities are referred to as “Credit-Eligible Features.” Credit-Eligible Features currently include inference, web search, image creation, and paid third-party APIs accessed through Vellum's managed OAuth (for example, Twitter). No alternative direct-payment method is available for Credit-Eligible Features.

You may fund your Vellum Credit balance (“Vellum Balance”) by purchasing Vellum Credits in ten-dollar ($10.00 USD) increments, up to one hundred dollars ($100.00 USD) per top-up, through the payment methods made available in the Services, or at such other amounts as determined by Vellum from time to time.

Four categories of work consume credits today: LLM inference (the biggest line item by far), web search, image generation, and paid third-party APIsyou reach through Vellum's managed OAuth (for example, Twitter).

Inference is itself broken into a set of Actions you'll see attributed in your usage dashboard. Here's what each one does:

Conversation with your assistant

• Main agent.Your assistant's response when you chat with them. The biggest chunk for most people when actively using the app.
• Inference.One-off model calls from skills or utilities that don't fit a more specific category.

Memory subsystem (mostly background)

• Memory consolidation. Promoting short-term observations into long-term memory pages.
• Memory extraction. Pulling concrete facts, preferences, and entities out of a conversation so they can be remembered.
• Memory retrieval. Looking up relevant memories when you ask a question or start a task.
• Recall. Targeted, deeper memory lookups across notes, knowledge base, and past conversations.

Conversation polish (background)

• Conversation summarization. Summarizing finished or long conversations so your assistant can refer back to them efficiently.
• Conversation title. Auto-generating a short title for each new conversation.
• Conversation starters. Suggested prompts the app surfaces when idle.
• Empty-state greeting. The hello your assistant shows when you open the app with no active conversation.
• Context compactor.Shrinking a long conversation's context so it still fits in the model's window without dropping anything important.

Autonomy (background)

• Heartbeat agent. Periodic check-ins where your assistant reflects, plans, and decides whether anything needs your attention.
• Filing agent. Filing notes, decisions, and learnings into your personal knowledge base.
• Notification decision. Deciding whether to push you a notification or stay quiet.

Other

• Unknown Task.LLM calls that haven't been tagged with a specific subsystem yet. We're cleaning up the remaining attribution gaps.

A lot of background work is configurable. You can ask your assistant to disable or reduce the frequency of “heartbeats” and “memory compaction,” or to use a less expensive model for these actions. We're actively working on making background spend more visible and easier to control.