How AI is applied across API Evangelist and APIs.io. Read my AI disclosure →
API Evangelist API Evangelist
Discovery
Learnings
Guidance
Toolbox
Alignment
API Evangelist LLC
Marqo website screenshot

Marqo

Marqo is an open-source, multimodal vector search engine that lets developers index text and images, generate embeddings on the fly, and run tensor, lexical, and hybrid search through a single REST API. Built on Vespa for storage and retrieval and FastAPI for the HTTP surface, Marqo bundles model inference (Sentence Transformers, OpenCLIP, ONNX) inside the engine so a single `docker run` produces a working semantic search stack. The Apache 2.0 open-source engine has been marked deprecated by the maintainers as Marqo pivots to a hosted ecommerce search product, but the project remains widely forked, downloaded, and self-hosted, with active sibling repositories for the Python client, Terraform provider, InstantSearch client, ecommerce embedding models, and Generalised Contrastive Learning research.

agent aware

Limited machine-readable signal and partial portal coverage — documentation a human can read, but little a machine or agent can consume without scraping.

Kin Score

API Evangelist profiles Marqo the way a machine reads it — 49 machine-readable artifacts across 1 API, pulled from the provider's own public surface and indexed so a developer, an analyst, or an AI agent can evaluate it against every other provider on the network.

Every provider in the network is reduced to the same set of machine-readable artifacts — OpenAPI contracts, event specifications, GraphQL schemas, runnable collections, pricing and rate-limit signals, security posture, OAuth scopes, and the agent surfaces (MCP servers and skills) that let software drive the API on its own. We profile them because the interface is the part of a company you can actually inspect: it is a truer signal of what a provider does than any marketing page. From those artifacts we compute the Kin Score — Marqo scores 38.7/100 (thin), with a separate agent-readiness read of 21/100 (agent aware). The full breakdown is below, followed by every artifact we hold — each card links through to its machine-readable definition on apis.io.

Kin Score

This is the API Evangelist rating — a single, repeatable read computed from the artifacts on this page. Green fill is points earned; the red track is points possible, so every bar shows earned-versus-possible at a glance. Every facet and dimension name is a link: it opens that measurement's page on APIs.io, where the rating runs across the whole catalog — the exact checks that feed it, how every profiled provider distributes on it, and who is at the top of it.

Kin Score Kin Score How this is scored →
scored 2026-09-08 · rubric v0.20.0
Marqo Kin Score — API readiness rating by API Evangelist

Put this on your own site. The badge is drawn live from Marqo's current Kin Score — paste it once and it updates itself every time the score is recomputed. It follows your visitor's light or dark setting, and it links back here so anyone who sees it can read the full breakdown.

<!-- Kin Score · API Evangelist -->
<a href="https://providers.apievangelist.com/providers/marqo/"
   title="Marqo on API Evangelist — API profile and Kin Score">
  <img src="https://apis.io/badge/marqo.svg"
       alt="Marqo Kin Score — API readiness rating by API Evangelist" width="150" height="150" loading="lazy">
</a>

More shapes, themes and sizes → · Score as JSON · How badges work

How we profile Marqo

Each block below is one kind of artifact we hold for Marqo. For each we say what it is and why it earns a place in the profile, then list every one we've indexed — capped at two rows, scroll within the panel for the rest.

APIs 7

Each API is captured as its own OpenAPI definition — every operation, parameter, and response. This is the single most useful machine-readable description of what an API does, and it's what lets us score, lint, mock, and generate against it without asking the provider for anything.

Individual APIs this provider publishes, each with its own machine-readable definition.

Marqo Documents API

Add, update, get, and delete documents in an index.

Marqo Embeddings API

Generate embedding vectors using engine-loaded models.

Marqo Indexes API

Create, list, inspect, and delete tensor / lexical indexes.

Marqo Models API

Inspect, load, and eject embedding models from the engine.

Marqo Recommendations API

Return documents similar to one or more reference documents.

Marqo Search API

Tensor, lexical, and hybrid search across an index.

Marqo Telemetry API

Health, readiness, and engine-level metadata.

Scroll within the panel for all 7 ·

Open Collections 9

Open, tool-agnostic collections carry the same runnable value as Postman without locking you to one client — the portable, forkable form of the same exercise.

Open, tool-agnostic API collections (OpenAPI-derived and Bruno).

Scroll within the panel for all 9 ·

Pricing Plans 1

Pricing is part of the interface. Machine-readable plans tell you what a tier costs and includes before you commit — one of the things the Kin Score reads for access clarity — renamed from commercial clarity in rubric 0.12, because a free statutory interface has access terms and no commercial ones.

Published pricing tiers and plan structures.

Marqo Plans Pricing

1 plans

PLANS

Rate Limits 1

Rate limits are the difference between a demo that works and a production integration that doesn't fall over. Publishing them is an operational-transparency signal — and a hard requirement for any agent that plans its own throughput.

Documented rate limits and quota policies.

Marqo Rate Limits

1 limits

RATE LIMITS

FinOps 1

Cost, billing, and metering signals let a buyer model the financial operations of an API before it's live. We profile them for the same reason we profile pricing: the money is part of the contract.

Cost, billing, and metering signals for API financial operations.

Marqo Finops

FINOPS

Features 12

The notable capabilities this provider advertises, captured as structured features so they can be searched and compared instead of read one landing page at a time.

Notable capabilities this provider offers.

Open-source Apache 2.0 vector search engine (project marked deprecated by maintainers; still 5,000+ stars and actively forked)
Single `docker run` install bundling Vespa storage and embedding model inference
Tensor, lexical, and hybrid search through a unified REST API
Multimodal indexing of text and images with on-engine inference
Embedding generation via Sentence Transformers, OpenCLIP, and ONNX models
Generalised Contrastive Learning (GCL) framework for fine-tuned retrieval
Marqo-FashionCLIP and marqo-ecommerce-embeddings open-weight models
Recommendations, filters, and structured + unstructured fields
FastAPI runtime exposing live `/openapi.json` and Swagger UI at `/docs`
Compose files for inference, model management, and Triton-backed serving
Python client (py-marqo), Terraform provider, and InstantSearch client
Hosted Marqo Cloud surface preserves API parity for legacy users

Scroll within the panel for all 12 ·

Security Posture 2

Authentication, domain security, vulnerability disclosure, and trust-center signals — the evidence that a provider takes security seriously enough to document it. We profile it because you can't govern what you can't see.

Authentication, domain security, vulnerability disclosure, and trust-center signals.

Marqo Authentication

http · 1 scheme

SECURITY

Marqo Domain Security

TLSv1.3 · HSTS · DNSSEC · DMARC

SECURITY

Agentic Access 1

An x-agentic-access contract marks which operations are safe for an agent to run on its own and which need a human in the loop. It is the difference between an API an agent can use and one it can use safely.

Recommended x-agentic-access execution contracts for AI agents.

Marqo Agentic Access

16 operations · 8 acting

16 operations · 8 acting

AGENTIC

Use Cases 5

What developers actually build with this provider — captured so the catalogue answers 'what is this for', not just 'what does this expose'.

What developers build with this provider.

Multimodal Semantic Search

Index text and images into a single tensor store and query with natural-language or image inputs, with embedding inference running inside the engine.

Retrieval-Augmented Generation

Power RAG pipelines by serving the nearest-neighbor retrieval layer for LLM context windows over private corpora.

Ecommerce Product Discovery

Drive product search, recommendations, and merchandising-aware ranking using semantic relevance plus structured filters and boosts.

Visual Search

Search product catalogs and image libraries using image-to-image and text-to-image similarity through OpenCLIP / Marqo-FashionCLIP.

Self-Hosted Vector Backend

Stand up an Apache 2.0 vector search service alongside your application stack with `docker run`, no separate embedding service required.

Integrations 10

Pre-built integrations with other platforms tell you where this provider already fits in a stack.

Pre-built integrations with other platforms and tools.

Vespa

Vespa is the underlying storage and retrieval engine that backs every Marqo index.

Sentence Transformers

Default text embedding model family loaded by the engine for tensor search.

OpenCLIP

Multimodal text-and-image embedding family used for visual and cross-modal search.

Hugging Face

Models are pulled from Hugging Face hubs at first use unless preloaded.

NVIDIA Triton

`compose-triton.yaml` ships a Triton-backed model server profile for GPU inference.

Terraform

terraform-provider-marqo manages Marqo Cloud indexes as infrastructure-as-code.

Algolia InstantSearch

marqo-instantsearch-client adapts Marqo to the InstantSearch.js front-end conventions.

Shopify

Hosted Marqo product offers one-click integration for Shopify catalogs.

Adobe Commerce

Hosted Marqo product offers Adobe Commerce / Magento connector.

Salesforce Commerce Cloud

Hosted Marqo product offers Salesforce Commerce Cloud connector.

Scroll within the panel for all 10 ·

Resources

Every other property we hold for Marqo — documentation, portals, status pages, policies, and corporate surface — grouped by the job it does, following the integrator's arc from getting started to running in production.

Get Started 1

Portal, sign-up, and the first successful call

Documentation 2

Reference material describing how the API behaves

Agent Surfaces 1

MCP servers, agent skills, and machine-readable catalogs

Access & Security 3

Authentication, authorization, and security posture

Learn 1

Tutorials, courses, talks, and written guidance

Operate 3

Status, limits, changes, and where to get help

Commercial 4

Pricing, plans, and the legal terms of use

Company 3

The organization behind the API

Other 3

Properties that don't map to a standard resource type

← All providers · Data indexed from github.com/api-evangelist/marqo · machine-readable index on apis.io

Where this information came from

This is an independent, third-party profile of Marqo, published by API Evangelist. We do not operate, host, resell, or support these APIs, and we are not affiliated with or endorsed by the company unless stated above. Everything here is built from publicly available information — the company's own site, developer portal, documentation, public repositories, and the specifications it publishes for public use. Nothing is obtained by breaching a system, defeating an access control, or using credentials.

The Kin Score and Agent Readiness rating are independently calculated assessments of a company's public API artifacts, scored against a published rubric. They are not certifications, endorsements, security assessments, or audits.

Corrections, re-scores, and removal are free — no partnership or purchase required, and you do not need to justify the request. A removed company is recorded as unrated, never scored zero for having asked. Acknowledgement within one business day; removal within two.

info@apievangelist.com · Read the full data-sourcing policy →
On a security or compliance team? Put security in the subject line and you will get a person, not a form — we will tell you exactly which public URLs this profile was built from.