How much does Vellum cost in 2026?
Quick Answer: As of July 2026, vellum.ai presents a product described as "Vellum: Your Personal Intelligence," priced on compute (vCPU/RAM) plus storage add-ons plus pay-as-you-go credits ($1 = 1 credit): a Base (Free) tier (1 vCPU / 2 GiB machine + 4 GiB storage), a Pro tier from about $50/month (larger machine), and a self-hosted open-source option. This is a different model from the earlier LLM-application-development platform (Prompt IDE, Evaluations, Workflows) that carried a roughly $500/month Pro tier — the product pivoted in May 2026 to a personal AI assistant (free Base plan; Pro from a $10/month platform fee plus compute add-ons), so verify the current offering at the source before relying on either framing.
Vellum Pricing (as of July 2026)
Note on a product change: as of July 2026, vellum.ai presents a product described as "Vellum: Your Personal Intelligence" — an assistant-style product priced on compute + credits, which is a different model from the LLM-application-development platform (Prompt IDE, Evaluations, Workflows) that earlier carried a ~$500/month Pro tier. The pricing below reflects what vellum.ai currently publishes; if you are evaluating the LLM-ops/prompt-engineering Vellum, confirm the current product directly.
| Plan | Price | Model |
|---|---|---|
| Base (Free) | $0 | Small machine (1 vCPU, 2 GiB) + 4 GiB storage + pay-as-you-go credits |
| Pro | From ~$50/month | Larger machine + storage add-ons + PAYG credits |
| Self-hosted | Open source (free) | You run the infrastructure |
Pricing is now on compute (vCPU/RAM) plus storage add-ons plus pay-as-you-go credits ($1 = 1 credit), replacing the earlier request-quota tiers. Model/token spend to the underlying providers (OpenAI, Anthropic, etc.) is still separate and paid directly, and can dominate the bill for high-volume use.
Cost considerations
- Compute + credits: the subscription buys a machine size and storage; credits meter usage on top.
- Model spend is separate: the underlying LLM API cost is paid to the provider directly.
- Self-hosting: the open-source option removes the subscription in exchange for running your own infrastructure.
Editor's Note: Re-checked July 2026: vellum.ai now presents a "Personal Intelligence" product priced on compute plus pay-as-you-go credits (Base free, Pro from ~$50/month, or self-hosted open source) — a marked change from the LLM-application-development platform with a ~$500/month Pro tier that this page previously described. We have flagged the apparent product change for review; if you are choosing an LLM-ops platform specifically, verify Vellum's current product and compare against alternatives, because the entry price and the model both look different from a year ago. — Rafal Fila, ShadowGen
Related Questions
Related Tools
Vellum
Repositioned in 2026 to a "Personal Intelligence" product priced on compute plus credits. Through early 2026 it was an LLM application development platform (Prompt IDE, evaluations, workflows).
AI Agent PlatformsRelevance AI
No-code AI agent builder for business tasks with multi-step workflows, knowledge base integration, and team collaboration.
AI Agent PlatformsLangflow
Visual low-code platform for building AI agents and RAG applications with drag-and-drop components
AI Agent PlatformsCrewAI
Open-source Python framework for building and orchestrating multi-agent AI systems
AI Agent PlatformsRelated Rankings
Best AI Agent Builders for Non-Developers in 2026
A ranked list of the best AI agent builders for non-developers in 2026. This ranking evaluates platforms that let operations, marketing, and customer-success teams construct multi-step AI agents without writing production code. The shortlist includes Lindy, Gumloop, Relay.app, Relevance AI, and Dust. Tools were evaluated on visual agent design, model and tool integration, observability and debugging, pricing accessibility, and documentation depth. Stack AI and Magic Loops were considered but excluded where the platform was not present in the database at evaluation time.
Best LLM App Platforms for Building AI Agents in 2026
A ranked list of platforms for building LLM-powered applications and AI agents in 2026. This ranking covers tools that combine prompt engineering, model orchestration, retrieval-augmented generation, tool calling, and deployment into a single workflow for product and engineering teams. Entries span low-code agent builders (Gumloop, Lindy, Relevance AI), code-first orchestration (CrewAI), open-source visual builders (Langflow), enterprise prompt engineering platforms (Vellum), and team-oriented agent suites (Dust). Scoring reflects developer experience, model and integration breadth, pricing, governance posture, and runtime reliability.