Vellum AI is an LLM development platform that helps product and engineering teams build, evaluate, deploy, and monitor LLM-powered applications. The platform centers on prompt engineering, a visual Workflows builder for agentic and multi-step pipelines, evaluation suites with dataset management, retrieval-augmented generation, and production observability with logs, traces, and metrics. Target customers are AI product teams at startups and enterprises that need version control, collaboration, and vendor-neutral access across OpenAI, Anthropic, Google, Mistral, and open models. Vellum exposes a REST API plus Python and TypeScript SDKs, runs in cloud and self-hosted deployments, and offers tiered pricing for Pro/Business/Enterprise. Note: as of 2026 the vellum.ai marketing surface has been refocused on a personal AI assistant product; the developer platform documented here remains the LLM application stack.
Vellum AI publishes 23 API contracts indexed on the APIs.io network, including Subpackage Deployments API, Subpackage Document Indexes API, Subpackage Documents API, and 20 more. Tagged areas include LLM Platform, Prompt Engineering, Workflows, Evaluation, and LLMOps.
The Vellum AI catalog on APIs.io includes 1 Spectral governance ruleset.
Vellum AI’s developer surface includes authentication, documentation, engineering blog, pricing, signup flow, and 14 more developer resources.
Regulatory Posture applies to this provider. Its tags matched the
Horizontal (data, software, accessibility, platform) regime, so
Regulatory Posture carries 15 points of the composite.
If this regime is wrong for your business, say so on your
provider repo — the
applicability map is public and we will correct it.
Create-or-Update Ergonomics applies to this provider. This API accepts writes, so it
carries 10 points of the composite. It is scored from the published contracts
themselves: whether a caller can create-or-update in one call, whether the write accepts a key the caller already
holds, and whether the response says which branch ran. Without that, every write needs a search-and-branch in
front of it, and the first time that check is skipped a duplicate record is created.
Scored against the observed mean rather than raw — a provider at the catalog average is unchanged by this facet,
not penalised by it.
The six quality facets above are damped to 75 points between them,
because the conditional facet above carries the other
25. That is why each facet's contribution is shown against a damped
maximum: raising a quality facet moves the composite by 75% of its nominal
weight, not 100%. The full arithmetic is at apis.io/rating/.
Show this score on your site.
It updates itself when the score changes. Paste this where you link to your API docs:
<a href="https://apis.io/providers/vellum/"><img src="https://apis.io/badge/vellum/card.svg" alt="Vellum AI on APIs.io — Kin Score by API Evangelist"></a>
Other styles, a README pill and a shields.io endpoint are on the badge page.
Raise your score.
Agent readiness — checks not met, largest first (exact, from this profile):
Idempotency+9 pts — OpenAPI mutating operations declare an idempotency key — a header, a request-body property, or a named de-duplication token whose own description says so (verified); else common[].type matches /idempoten/i (documented)
A2A Agent Card+8 pts — a2a/-a2a.yml manifest, graded on conformance.grade against A2A 1.0.0
Request/Response Examples+7 pts — share of operations carrying request/response examples; else an Examples / Code Samples link
Delegated User Identity+6 pts — a served discovery document listing authorization_code in grant_types_supported (served), else an oauth2 authorizationCode flow or openIdConnect declared in an OpenAPI (documented)
Typed Event Surface+6 pts — AsyncAPI document, OR webhooks/callbacks objects in the as-published OpenAPI, OR common[].type includes Webhooks
7 more unmet checks in the Agent Readiness table above.
Kin Score — facets with the most composite points still available (weight × headroom):
Access Clarityscores 22.4 — up to +15.5 composite points
The Kin Score Market layer reads a provider inside its market:
its position, and how deep its integrations go. Depth is only comparable within a position. Provisional and unweighted:
not part of the Kin Score or agent readiness.
Registered MCP server and declares compatibility are report only — not weighted.
Undeclared means we found nothing we can read, so there is no number: we never infer integrations.
Standards this provider implements or carries. De facto ones are profiled and measured by the API Commons; formal ones come from the standards directory and are linked by the provider's own tags. The evidence column says how each claim was established — not that it was made.
The Vellum REST API exposes prompts, workflows, evaluations, datasets, document indexes, deployments, and execution endpoints so developers can run versioned LLM pipelines from ...
Remote MCP server at docs.vellum.ai over HTTP; 1 tool listed.
MCP SERVER
Vellum AI API pricing
Not yet checked against Vellum AI's own pricing page. Compiled by API Evangelist on 2026-05-22; confirm before you rely on a figure. A free plan or tier is listed.
aid: vellum
name: Vellum AI
description: 'Vellum AI is an LLM development platform that helps product and engineering teams build, evaluate, deploy, and
monitor LLM-powered applications. The platform centers on prompt engineering, a visual Workflows builder for agentic and
multi-step pipelines, evaluation suites with dataset management, retrieval-augmented generation, and production observability
with logs, traces, and metrics. Target customers are AI product teams at startups and enterprises that need version control,
collaboration, and vendor-neutral access across OpenAI, Anthropic, Google, Mistral, and open models. Vellum exposes a REST
API plus Python and TypeScript SDKs, runs in cloud and self-hosted deployments, and offers tiered pricing for Pro/Business/Enterprise.
Note: as of 2026 the vellum.ai marketing surface has been refocused on a personal AI assistant product; the developer platform
documented here remains the LLM application stack.'
type: Index
deliveryModel:
model: saas
open_source: false
commercial: true
callable_host: true
label: Hosted service · you call their endpoint
confidence: high
source:
- openapi
- pricing
generated: '2026-08-28'
method: derived
accessModel:
pricing: free
onboarding: self-serve
trial: false
try_now: true
public: false
gated: none
gated_source:
- onboarding
label: Free · Self-serve signup
confidence: medium
source:
- plans
- authentication
- security
generated: '2026-11-06'
method: derived
position: Producing
access: 3rd-Party
image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/icons/vellum.png
x-docs-platform: fern
x-docs-platform-confidence: medium
x-docs-platform-checked: 2026-10-17
x-docs-hosting: vercel
tags:
- LLM Platform
- Prompt Engineering
- Workflows
- Evaluation
- LLMOps
- RAG
- Observability
- Datasets
- Deployment
- Multi-Provider
- Agent Builder
- Self-Hosted
tags_raw:
- LLM Platform
- Prompt Engineering
- Workflows
- Evaluations
- LLM Ops
- RAG
- Observability
- Datasets
- Deployments
- Multi-Provider
- Agent Builder
- Self-Hosted
url: https://raw.githubusercontent.com/api-evangelist/vellum/refs/heads/main/apis.yml
created: '2026-05-23'
modified: '2026-05-23'
specificationVersion: '0.23'
apis:
- aid: vellum:llm-platform
name: Vellum LLM Platform API
description: The Vellum REST API exposes prompts, workflows, evaluations, datasets, document indexes, deployments, and execution
endpoints so developers can run versioned LLM pipelines from their own backends and capture logs and metrics for production
monitoring.
humanURL: https://docs.vellum.ai
baseURL: https://api.vellum.ai
tags:
- Prompts
- Workflows
- Evaluation
- Datasets
- Documents
- Deployment
- Execution
- Monitoring
tags_raw:
- Prompts
- Workflows
- Evaluations
- Datasets
- Documents
- Deployments
- Executions
- Monitoring
properties:
- type: Documentation
url: https://docs.vellum.ai
- type: APIReference
url: https://docs.vellum.ai/api-reference
- type: GettingStarted
url: https://docs.vellum.ai/welcome/getting-started
- type: Signup
url: https://app.vellum.ai/signup
- type: SDKs
url: https://github.com/vellum-ai/vellum-client-python
- type: SDKs
url: https://github.com/vellum-ai/vellum-client-typescript
- type: GitHubOrganization
url: https://github.com/vellum-ai
- type: Pricing
url: https://www.vellum.ai/pricing
- type: Blog
url: https://www.vellum.ai/blog
features:
- name: Prompt Engineering Workbench
description: Versioned prompts, side-by-side model comparisons, and structured prompt variables.
- name: Workflows Builder
description: Visual builder for multi-step LLM pipelines including branching, tools, and RAG nodes.
- name: Evaluation Suites
description: Run dataset-driven evals with built-in and custom metrics for prompts and workflows.
- name: Dataset Management
description: Store labeled test cases and production examples to drive evaluations and fine-tuning.
- name: Document Indexes / RAG
description: Managed document ingestion, embeddings, and retrieval for grounded generation.
- name: Deployments and Versioning
description: Promote prompts and workflows through environments with rollback and traffic splits.
- name: Production Monitoring
description: Logs, traces, latency, cost, and quality metrics for every execution.
- name: Multi-Provider Routing
description: Vendor-neutral access to OpenAI, Anthropic, Google, Mistral, and open models.
- name: SDKs for Python and TypeScript
description: First-class SDKs for invoking prompts, workflows, and datasets from application code.
- name: Self-Hosted Option
description: Deploy Vellum into the customer's own cloud for compliance-sensitive workloads.
useCases:
- name: Build Production LLM Apps
description: Iterate on prompts and workflows, then deploy versioned endpoints into apps.
- name: Evaluate LLM Quality
description: Use datasets and evals to measure regressions across models and prompt variants.
- name: Build Agents
description: Compose tools, retrieval, and conditional logic via the visual workflow builder.
- name: RAG Pipelines
description: Ingest documents, index them, and query through Vellum's managed retrieval layer.
- name: Observe and Debug
description: Trace production runs to debug failures and improve quality over time.
integrations:
- name: OpenAI
- name: Anthropic
- name: Google
- name: Mistral
- name: Cohere
- name: AWS Bedrock
- name: Azure OpenAI
- name: Pinecone
- name: Snowflake
- name: LangChain
- name: LlamaIndex
authentication:
- type: API Key
description: Workspace API keys passed via the `X_API_KEY` header authenticate REST and SDK calls.
- aid: vellum:vellum-subpackage-deployments-api
name: Vellum AI Subpackage Deployments API
description: The subpackage_deployments API from Vellum AI — 7 operation(s) for subpackage_deployments.
humanURL: https://docs.vellum.ai
baseURL: https://api.vellum.ai
tags: []
tags_raw:
- subpackage_deployments
properties:
- type: OpenAPI
url: openapi/vellum-subpackage-deployments-api-openapi.yml
- aid: vellum:vellum-subpackage-documentindexes-api
name: Vellum AI Subpackage Document Indexes API
description: The subpackage_documentIndexes API from Vellum AI — 3 operation(s) for subpackage_documentindexes.
humanURL: https://docs.vellum.ai
baseURL: https://api.vellum.ai
tags:
- subpackage_documentIndexes
properties:
- type: OpenAPI
url: openapi/vellum-subpackage-documentindexes-api-openapi.yml
- aid: vellum:vellum-subpackage-documents-api
name: Vellum AI Subpackage Documents API
description: The subpackage_documents API from Vellum AI — 3 operation(s) for subpackage_documents.
humanURL: https://docs.vellum.ai
baseURL: https://api.vellum.ai
tags: []
tags_raw:
- subpackage_documents
properties:
- type: OpenAPI
url: openapi/vellum-subpackage-documents-api-openapi.yml
- aid: vellum:vellum-subpackage-events-api
name: Vellum AI Subpackage Events API
description: The subpackage_events API from Vellum AI — 1 operation(s) for subpackage_events.
humanURL: https://docs.vellum.ai
baseURL: https://api.vellum.ai
tags: []
tags_raw:
- subpackage_events
properties:
- type: OpenAPI
url: openapi/vellum-subpackage-events-api-openapi.yml
- aid: vellum:vellum-subpackage-folderentities-api
name: Vellum AI Subpackage Folder Entities API
description: The subpackage_folderEntities API from Vellum AI — 2 operation(s) for subpackage_folderentities.
humanURL: https://docs.vellum.ai
baseURL: https://api.vellum.ai
tags:
- subpackage_folderEntities
properties:
- type: OpenAPI
url: openapi/vellum-subpackage-folderentities-api-openapi.yml
- aid: vellum:vellum-subpackage-sandboxes-api
name: Vellum AI Subpackage Sandboxes API
description: The subpackage_sandboxes API from Vellum AI — 3 operation(s) for subpackage_sandboxes.
humanURL: https://docs.vellum.ai
baseURL: https://api.vellum.ai
tags: []
tags_raw:
- subpackage_sandboxes
properties:
- type: OpenAPI
url: openapi/vellum-subpackage-sandboxes-api-openapi.yml
- aid: vellum:vellum-subpackage-testsuiteruns-api
name: Vellum AI Subpackage Test Suite Runs API
description: The subpackage_testSuiteRuns API from Vellum AI — 3 operation(s) for subpackage_testsuiteruns.
humanURL: https://docs.vellum.ai
baseURL: https://api.vellum.ai
tags:
- subpackage_testSuiteRuns
properties:
- type: OpenAPI
url: openapi/vellum-subpackage-testsuiteruns-api-openapi.yml
- aid: vellum:vellum-subpackage-testsuites-api
name: Vellum AI Subpackage Test Suites API
description: The subpackage_testSuites API from Vellum AI — 3 operation(s) for subpackage_testsuites.
humanURL: https://docs.vellum.ai
baseURL: https://api.vellum.ai
tags:
- subpackage_testSuites
properties:
- type: OpenAPI
url: openapi/vellum-subpackage-testsuites-api-openapi.yml
- aid: vellum:vellum-subpackage-uploadedfiles-api
name: Vellum AI Subpackage Uploaded Files API
description: The subpackage_uploadedFiles API from Vellum AI — 1 operation(s) for subpackage_uploadedfiles.
humanURL: https://docs.vellum.ai
baseURL: https://api.vellum.ai
tags:
- subpackage_uploadedFiles
properties:
- type: OpenAPI
url: openapi/vellum-subpackage-uploadedfiles-api-openapi.yml
- aid: vellum:vellum-subpackage-workflowdeployments-api
name: Vellum AI Subpackage Workflow Deployments API
description: The subpackage_workflowDeployments API from Vellum AI — 10 operation(s) for subpackage_workflowdeployments.
humanURL: https://docs.vellum.ai
baseURL: https://api.vellum.ai
tags:
- subpackage_workflowDeployments
properties:
- type: OpenAPI
url: openapi/vellum-subpackage-workflowdeployments-api-openapi.yml
- aid: vellum:vellum-subpackage-workflowexecutions-api
name: Vellum AI Subpackage Workflow Executions API
description: The subpackage_workflowExecutions API from Vellum AI — 1 operation(s) for subpackage_workflowexecutions.
humanURL: https://docs.vellum.ai
baseURL: https://api.vellum.ai
tags:
- subpackage_workflowExecutions
properties:
- type: OpenAPI
url: openapi/vellum-subpackage-workflowexecutions-api-openapi.yml
- aid: vellum:vellum-subpackage-workflows-api
name: Vellum AI Subpackage Workflows API
description: The subpackage_workflows API from Vellum AI — 1 operation(s) for subpackage_workflows.
humanURL: https://docs.vellum.ai
baseURL: https://api.vellum.ai
tags: []
tags_raw:
- subpackage_workflows
properties:
- type: OpenAPI
url: openapi/vellum-subpackage-workflows-api-openapi.yml
- aid: vellum:vellum-subpackage-workflowsandboxes-api
name: Vellum AI Subpackage Workflow Sandboxes API
description: The subpackage_workflowSandboxes API from Vellum AI — 1 operation(s) for subpackage_workflowsandboxes.
humanURL: https://docs.vellum.ai
baseURL: https://api.vellum.ai
tags:
- subpackage_workflowSandboxes
properties:
- type: OpenAPI
url: openapi/vellum-subpackage-workflowsandboxes-api-openapi.yml
- aid: vellum:vellum-subpackage-workspacesecrets-api
name: Vellum AI Subpackage Workspace Secrets API
description: The subpackage_workspaceSecrets API from Vellum AI — 1 operation(s) for subpackage_workspacesecrets.
humanURL: https://docs.vellum.ai
baseURL: https://api.vellum.ai
tags:
- subpackage_workspaceSecrets
properties:
- type: OpenAPI
url: openapi/vellum-subpackage-workspacesecrets-api-openapi.yml
- aid: vellum:vellum-execute-prompt-api
name: Vellum AI Execute Prompt API
description: The Execute Prompt API from Vellum AI — 1 operation(s) for execute prompt.
humanURL: https://docs.vellum.ai
baseURL: https://api.vellum.ai
tags:
- Execute Prompt
properties:
- type: OpenAPI
url: openapi/vellum-execute-prompt-api-openapi.yml
- aid: vellum:vellum-execute-prompt-stream-api
name: Vellum AI Execute Prompt Stream API
description: The Execute Prompt Stream API from Vellum AI — 1 operation(s) for execute prompt stream.
humanURL: https://docs.vellum.ai
baseURL: https://api.vellum.ai
tags:
- Execute Prompt Stream
properties:
- type: OpenAPI
url: openapi/vellum-execute-prompt-stream-api-openapi.yml
- aid: vellum:vellum-execute-workflow-api
name: Vellum AI Execute Workflow API
description: The Execute Workflow API from Vellum AI — 1 operation(s) for execute workflow.
humanURL: https://docs.vellum.ai
baseURL: https://api.vellum.ai
tags:
- Execute Workflow
properties:
- type: OpenAPI
url: openapi/vellum-execute-workflow-api-openapi.yml
- aid: vellum:vellum-execute-workflow-async-api
name: Vellum AI Execute Workflow Async API
description: The Execute Workflow Async API from Vellum AI — 1 operation(s) for execute workflow async.
humanURL: https://docs.vellum.ai
baseURL: https://api.vellum.ai
tags:
- Execute Workflow Async
properties:
- type: OpenAPI
url: openapi/vellum-execute-workflow-async-api-openapi.yml
- aid: vellum:vellum-execute-workflow-stream-api
name: Vellum AI Execute Workflow Stream API
description: The Execute Workflow Stream API from Vellum AI — 1 operation(s) for execute workflow stream.
humanURL: https://docs.vellum.ai
baseURL: https://api.vellum.ai
tags:
- Execute Workflow Stream
properties:
- type: OpenAPI
url: openapi/vellum-execute-workflow-stream-api-openapi.yml
- aid: vellum:vellum-search-api
name: Vellum AI Search API
description: The Search API from Vellum AI — 1 operation(s) for search.
humanURL: https://docs.vellum.ai
baseURL: https://api.vellum.ai
tags:
- Search
properties:
- type: OpenAPI
url: openapi/vellum-search-api-openapi.yml
- aid: vellum:vellum-submit-completion-actuals-api
name: Vellum AI Submit Completion Actuals API
description: The Submit Completion Actuals API from Vellum AI — 1 operation(s) for submit completion actuals.
humanURL: https://docs.vellum.ai
baseURL: https://api.vellum.ai
tags:
- Submit Completion Actuals
properties:
- type: OpenAPI
url: openapi/vellum-submit-completion-actuals-api-openapi.yml
- aid: vellum:vellum-submit-workflow-execution-actuals-api
name: Vellum AI Submit Workflow Execution Actuals API
description: The Submit Workflow Execution Actuals API from Vellum AI — 1 operation(s) for submit workflow execution actuals.
humanURL: https://docs.vellum.ai
baseURL: https://api.vellum.ai
tags:
- Submit Workflow Execution Actuals
properties:
- type: OpenAPI
url: openapi/vellum-submit-workflow-execution-actuals-api-openapi.yml
common:
- type: Plans
url: plans/vellum-plans-pricing.yml
- type: RateLimits
url: rate-limits/vellum-rate-limits.yml
- type: FinOps
url: finops/vellum-finops.yml
- type: CapabilityMap
url: capabilities/vellum-capability-edges.yml
name: Vellum AI Business Capability Map
- type: AgenticAccess
url: agentic-access/vellum-agentic-access.yml
- type: DomainSecurity
url: security/vellum-domain-security.yml
- type: Authentication
url: authentication/vellum-authentication.yml
- type: Website
url: https://www.vellum.ai
- type: Documentation
url: https://docs.vellum.ai
- type: Blog
url: https://www.vellum.ai/blog
- type: GitHubOrganization
url: https://github.com/vellum-ai
- type: Pricing
url: https://www.vellum.ai/pricing
- type: Signup
url: https://app.vellum.ai/signup
- type: Login
url: https://app.vellum.ai/login
- type: TermsOfService
url: https://www.vellum.ai/terms-of-service
- type: PrivacyPolicy
url: https://www.vellum.ai/privacy-policy
- type: Twitter
url: https://x.com/vellum_ai
- type: LinkedIn
url: https://www.linkedin.com/company/vellum-ai
- type: LlmsText
url: https://docs.vellum.ai/llms.txt
maintainers:
- FN: Kin Lane
email: kin@apievangelist.com
Vellum AI API — frequently asked questions
Does Vellum AI have an API?
Yes. APIs.io lists 23 APIs from Vellum AI, including Vellum LLM Platform API, Vellum AI Subpackage Deployments API and Vellum AI Subpackage Document Indexes API, and 20 more.
Is there an OpenAPI specification for the Vellum AI API?
Yes. APIs.io indexes 22 OpenAPI specifications for Vellum AI, each linked for download from this page.
How do I authenticate with the Vellum AI API?
Vellum AI uses bearer-token authentication (apiKey · 1 scheme). The details are profiled on APIs.io as Vellum Authentication.
How much does the Vellum AI API cost?
APIs.io lists 1 pricing plan for Vellum AI, with each plan's price, limits and inclusions under Pricing on this page.
Does Vellum AI have an MCP server?
Yes. APIs.io lists 1 MCP server for Vellum AI: Remote MCP server at docs.vellum.ai over HTTP; 1 tool listed.
Is the Vellum AI API ready for AI agents?
Vellum AI has a Kin Score of 37.8 out of 100 (thin) and an Agent Readiness score of 38.5 (agent-ready), scored by API Evangelist on 2026-11-06.
Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.
Get an API key
Free tier, no form to fill in. Signing in shares your email address with us — we
store it to create your key and to recognise you if you sign in with another
provider. See our Privacy Policy and
Terms.
Kin Score
How this is scored →
It updates itself when the score changes. Paste this where you link to your API docs: