Kagi

Kagi is a privacy-focused premium search engine that also operates a commercial APIs portfolio for developers. The Kagi APIs Portal exposes Search, Enrichment, Universal Summarizer, and FastGPT endpoints, plus a free Small Web RSS feed for non-commercial use. The portal includes an API Playground, usage dashboard, and API key management with IP allowlists and per-product scopes. Kagi publishes an OpenAPI specification and ships official client libraries in Python, Go, Rust, and TypeScript. Billing is pay-per-use with monthly invoicing and a Discord community for developer support.

Kagi publishes 6 API contracts indexed on the APIs.io network, including Extract API, Search API, and 4 more. Tagged areas include Search, Premium Search, AI Search, Summarization, and FastGPT.

The Kagi catalog on APIs.io includes 1 Spectral governance ruleset.

Kagi’s developer surface includes authentication, documentation, engineering blog, pricing, changelog, and 13 more developer resources.

🌐 Visit website 📡 Profile data on GitHub

38.8/100 thin ▬ flat Agent 20/100 agent aware Front door AI 5/6 prominent Heartbeat 96/100 alive saas Full breakdown ↓
scored 2026-11-13 · rubric v0.28.0 · Show this score on your site →

AccessFreeSelf serve⚡ Free to try

1 published contract

SearchPremium SearchAI Search SummarizationFastGPTData Enrichment OpenAPI Pay-per-use Privacy LLMWeb Index

Kin Score

Kin Score How this is scored →
scored 2026-11-13 · rubric v0.28.0

Composite quality — 38.8/100 · thin

Contract Quality 9.6 / 19

Developer Ergonomics 4.7 / 15

Access Clarity 5.4 / 15

Operational Transparency 3.2 / 10

Contract Governance 1.2 / 9

Discoverability 5.0 / 8

Regulatory Posture 3.0 / 15

Create-or-Update Ergonomics 0.0 / 10

Agent readiness — 20/100 · agent aware

Machine-Readable Contract 18 / 18

Agentic Access Contract 10 / 10

Documented Reversibility 0 / 6

MCP Server 0 / 12

Machine-Readable Auth 10 / 10

Idempotency 0 / 9

Stable Error Semantics 0 / 8

Request/Response Examples 0 / 7

Rate-Limit Signaling 7 / 7

Typed Event Surface 0 / 6

Agent Skills 0 / 5

Well-Known Catalog 0 / 4

Consent & Bot Identity 0 / 3

A2A Agent Card 0 / 8

Dry-Run / Simulate Mode 0 / 4

Delegated User Identity 0 / 6

Protected Resource Metadata 0 / 5

Registration Without a Human 0 / 6

Agentic Commerce Well-Known Document 0 / 5

Pagination 5 / 5

Distinct Operations 3 / 3

MCP Tool Quality 6 / 6

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/kagi/"><img src="https://apis.io/badge/kagi/card.svg" alt="Kagi 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):

MCP Server +12 pts — deployment.mode + probe verdict on the mcp/ manifest, not the pointer; an unprobed slug falls back to authorship Ask about this →
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) Ask about this →
Stable Error Semantics +8 pts — OpenAPI $refs a shared error schema across 4xx/5xx responses (verified), else common[].type includes ErrorCatalog / ErrorCodes / DeclineCodes Ask about this →
A2A Agent Card +8 pts — a2a/-a2a.yml manifest, graded on conformance.grade against A2A 1.0.0 Ask about this →
Request/Response Examples +7 pts — share of operations carrying request/response examples; else an Examples / Code Samples link Ask about this →
Registration Without a Human +6 pts — a `registration_endpoint` in the served RFC 8414 / OIDC discovery document Ask about this →

9 more unmet checks in the Agent Readiness table above.

Kin Score — facets with the most composite points still available (weight × headroom):

Developer Ergonomics scores 31.0 — up to +13.8 composite points Ask about this →
Access Clarity scores 36.2 — up to +12.8 composite points Ask about this →
Contract Quality scores 51.2 — up to +12.2 composite points Ask about this →

Each check links to what satisfies it. Publish the artifact, or tell us where it already lives, and the score moves on the next scoring run.

Not sure how this applies to your stack? Ask about any one item. Kin Lane reads every question, looks at your profile and your situation, and replies with what a fix would take — scoped to that one area, priced up front, yours whether you ship it or not. Ask a question →

Improve this rating by publishing the missing artifacts — every area above can be raised, and the full rubric is at apis.io/rating/. Every facet and dimension name above is a link: it opens that measurement's own page — what it means, the exact checks that feed it, how the whole catalog distributes on it, and the providers at the top of it. This rating is computed from the provider profile at artifacts.apis.io/kagi/apis.yml: open an issue on github.com/api-evangelist/kagi to ask a question or point us at an artifact you publish. Submit an artifact on GitHub — free → Manage your own listing — the Influence plan, $499/mo →

Markets this provider is in provisional

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.

Market	Position	Depth	Registered MCP server	Declares compatibility
x402 Micropayments & Agentic Pay-per-Call	covered	23.9	-	-
Browser Extension Stores (company-published Firefox add-ons; Chrome Web Store unreadable)	covered	23.9	-	-
Raycast Store Extensions (first-party publishers + community-wrapped products)	covered	23.9	-	-

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 implemented 1

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.

OpenAPI

measured — observed by APIs.io (published)

APIs 6

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

Kagi Search API

The Kagi Search API delivers premium, ad-free web search results powered by the Kagi index, designed for AI agents, research workflows, and applications that demand high-quality...

Kagi Enrichment API

The Kagi Enrichment API provides access to Kagi's Teclis non-commercial web index and TinyGem news index for specialized retrieval and discovery workloads.

Kagi Universal Summarizer API

The Universal Summarizer API condenses URLs, documents, audio, and video into structured summaries using Kagi's hosted models.

Kagi FastGPT API

FastGPT is Kagi's LLM-powered question answering API that combines a hosted model with live Kagi web search for grounded, cited answers.

Kagi Extract API

Extract markdown content from web URLs.

Kagi Search API

Perform Kagi web searches.

Open Collections 3

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

Kagi Search Extract API

OPEN COLLECTION

Kagi Extract Search API

OPEN COLLECTION

Kagi Search API

OPEN COLLECTION

Kagi API pricing

Not yet checked against Kagi'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.

Plan	Price
Free freemium	Free

Plan details, limits and sources →

Rate limits

Free Tier Default: 10 requests per minute
Pro Tier Default: 120 requests per minute

Compiled by API Evangelist, not yet checked against Kagi's documentation. Rate-limit details →

Pricing Plans 1

Published pricing tiers and plan structures.

Kagi Plans Pricing

1 plans

PLANS

Rate Limits 1

Documented rate limits and quota policies.

Kagi Rate Limits

2 limits

RATE LIMITS

Privacy & Data 1

Its role, the data it processes, retention and transfers, quoted from its own privacy page.

Kagi

17 quoted statements, read from Kagi's own page on 2026-11-09.

PRIVACY

FinOps 1

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

Kagi Finops

FINOPS

Spectral Rules 1

Spectral governance rulesets for linting and validating these APIs. Counts are the severity each rule declares, not results of running them.

Kagi API Rules

56 rules · 54 error-severity 1 warn-severity 1 info-severity

SPECTRAL

Security Posture 3

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

Kagi Authentication

http · 1 scheme

SECURITY

Kagi Domain Security

TLSv1.3 · HSTS · DNSSEC · DMARC

SECURITY

Kagi Vulnerability Disclosure

security.txt · contact published

SECURITY

Agentic Access (API Evangelist recommendations) 1

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

Kagi Agentic Access

3 operations · 1 acting

AGENTIC

Resources

Documentation 1

Reference material describing how the API behaves

Documentation

Documentation

Agent Surfaces 1

MCP servers, agent skills, and machine-readable catalogs

AgenticAccess

AgenticAccess

Build 1

SDKs, sample code, and the tooling you integrate with

GitHubOrganization

GitHubOrganization

Access & Security 3

Authentication, authorization, and security posture

VulnerabilityDisclosure

VulnerabilityDisclosure

DomainSecurity

DomainSecurity

Authentication

Authentication

Operate 3

Status, limits, changes, and where to get help

RateLimits

RateLimits

Discord

Discord

ChangeLog

ChangeLog

Commercial 5

Pricing, plans, and the legal terms of use

Plans

FinOps

Pricing

TermsOfService

PrivacyPolicy

Company 2

The organization behind the API

Website

Website

Blog

Blog

Other 2

Properties that don't map to a standard resource type

DataProcessing

DataProcessing

Source (apis.yml)

aid: kagi
name: Kagi
description: Kagi is a privacy-focused premium search engine that also operates a commercial APIs portfolio for developers.
  The Kagi APIs Portal exposes Search, Enrichment, Universal Summarizer, and FastGPT endpoints, plus a free Small Web RSS
  feed for non-commercial use. The portal includes an API Playground, usage dashboard, and API key management with IP allowlists
  and per-product scopes. Kagi publishes an OpenAPI specification and ships official client libraries in Python, Go, Rust,
  and TypeScript. Billing is pay-per-use with monthly invoicing and a Discord community for developer support.
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: '2026-11-13'
  method: derived
position: Producing
access: 3rd-Party
image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/icons/kagi.png
x-docs-platform: vitepress
x-docs-platform-confidence: medium
x-docs-platform-checked: 2026-10-03
tags:
- Search
- Premium Search
- AI Search
- Summarization
- FastGPT
- Data Enrichment
- OpenAPI
- Pay-per-use
- Privacy
- LLM
- Web Index
tags_raw:
- Search
- Premium Search
- AI Search
- Summarization
- FastGPT
- Enrichment
- OpenAPI
- Pay-Per-Use
- Privacy
- LLMs
- Web Index
url: https://raw.githubusercontent.com/api-evangelist/kagi/refs/heads/main/apis.yml
created: '2026-05-23'
modified: '2026-05-23'
specificationVersion: '0.23'
apis:
- aid: kagi:search-api
  name: Kagi Search API
  description: The Kagi Search API delivers premium, ad-free web search results powered by the Kagi index, designed for AI
    agents, research workflows, and applications that demand high-quality results.
  humanURL: https://help.kagi.com/kagi/api/search.html
  baseURL: https://kagi.com/api/v0
  tags:
  - Search
  - Web
  - REST
  properties:
  - type: Documentation
    url: https://help.kagi.com/kagi/api/search.html
  - type: GettingStarted
    url: https://help.kagi.com/kagi/api/intro.html
  - type: Signup
    url: https://kagi.com/signup
  - type: APIReference
    url: https://help.kagi.com/kagi/api/search.html
  - type: SDKs
    url: https://github.com/kagisearch
  - type: Pricing
    url: https://help.kagi.com/kagi/api/overview.html
  - type: Authentication
    url: https://help.kagi.com/kagi/api/intro.html
  features:
  - name: Premium Search Results
    description: Ad-free, privacy-focused web search results sourced from the Kagi index.
  - name: Structured Responses
    description: JSON responses with title, URL, snippet, and metadata for easy consumption.
  - name: API Playground
    description: Test requests directly in the browser from the API portal.
  - name: Pay-Per-Use Billing
    description: Pay only for requests made, invoiced monthly or at a $100 threshold.
  useCases:
  - name: Agent Web Search Tool
    description: Use as a high-quality web search tool inside AI agents.
  - name: Research Workflows
    description: Power research pipelines that need premium, low-noise results.
  - name: Internal Knowledge Apps
    description: Embed premium search inside internal portals and assistants.
  integrations:
  - name: Python
  - name: Go
  - name: Rust
  - name: TypeScript
  - name: Model Context Protocol
  authentication:
  - type: API Key
    description: Bot API token sent via the Authorization header.
- aid: kagi:enrichment-api
  name: Kagi Enrichment API
  description: The Kagi Enrichment API provides access to Kagi's Teclis non-commercial web index and TinyGem news index for
    specialized retrieval and discovery workloads.
  humanURL: https://help.kagi.com/kagi/api/enrich.html
  baseURL: https://kagi.com/api/v0
  tags:
  - Data Enrichment
  - Teclis
  - TinyGem
  - News
  - Web Index
  tags_raw:
  - Enrichment
  - Teclis
  - TinyGem
  - News
  - Web Index
  properties:
  - type: Documentation
    url: https://help.kagi.com/kagi/api/enrich.html
  - type: APIReference
    url: https://help.kagi.com/kagi/api/enrich.html
  - type: Pricing
    url: https://help.kagi.com/kagi/api/overview.html
  features:
  - name: Teclis Index Access
    description: Query Kagi's curated non-commercial Teclis web index.
  - name: TinyGem News Index
    description: Access the TinyGem news index for fresh news content.
  - name: JSON Responses
    description: Lightweight JSON responses suited for agent and pipeline use.
  useCases:
  - name: Small-Web Discovery
    description: Surface high-quality, non-commercial sources for research and content discovery.
  - name: News Monitoring
    description: Track fresh news content for alerts and briefings.
  - name: Niche RAG Backends
    description: Use specialized indexes to ground RAG pipelines in curated sources.
  integrations:
  - name: Python
  - name: TypeScript
  - name: Go
  - name: Rust
  authentication:
  - type: API Key
    description: Bot API token sent via the Authorization header.
- aid: kagi:summarizer-api
  name: Kagi Universal Summarizer API
  description: The Universal Summarizer API condenses URLs, documents, audio, and video into structured summaries using Kagi's
    hosted models.
  humanURL: https://help.kagi.com/kagi/api/summarizer.html
  baseURL: https://kagi.com/api/v0
  tags:
  - Summarization
  - Documents
  - Audio
  - Video
  - LLM
  tags_raw:
  - Summarization
  - Documents
  - Audio
  - Video
  - LLMs
  properties:
  - type: Documentation
    url: https://help.kagi.com/kagi/api/summarizer.html
  - type: APIReference
    url: https://help.kagi.com/kagi/api/summarizer.html
  - type: Pricing
    url: https://help.kagi.com/kagi/api/overview.html
  features:
  - name: URL Summarization
    description: Summarize the content of a public URL into structured text.
  - name: Multi-Format Input
    description: Handle web pages, documents, audio, and video sources.
  - name: Selectable Engines
    description: Choose summary engines tuned for different output styles.
  useCases:
  - name: Article TLDRs
    description: Generate TLDRs of news articles and blog posts.
  - name: Meeting Recaps
    description: Summarize recorded meetings and long-form audio.
  - name: Document Triage
    description: Quickly surface key points from long documents.
  integrations:
  - name: Python
  - name: TypeScript
  - name: Go
  - name: Rust
  authentication:
  - type: API Key
    description: Bot API token sent via the Authorization header.
- aid: kagi:fastgpt-api
  name: Kagi FastGPT API
  description: FastGPT is Kagi's LLM-powered question answering API that combines a hosted model with live Kagi web search
    for grounded, cited answers.
  humanURL: https://help.kagi.com/kagi/api/fastgpt.html
  baseURL: https://kagi.com/api/v0
  tags:
  - FastGPT
  - QA
  - Grounded Answers
  - LLM
  - Search
  tags_raw:
  - FastGPT
  - QA
  - Grounded Answers
  - LLMs
  - Search
  properties:
  - type: Documentation
    url: https://help.kagi.com/kagi/api/fastgpt.html
  - type: APIReference
    url: https://help.kagi.com/kagi/api/fastgpt.html
  - type: Pricing
    url: https://help.kagi.com/kagi/api/overview.html
  features:
  - name: Grounded Answers
    description: LLM answers grounded in live Kagi search results with citations.
  - name: Low Latency
    description: Optimized for fast question answering in interactive agents.
  - name: Citation Sources
    description: Return source URLs and snippets alongside each answer.
  useCases:
  - name: Q&A Agents
    description: Build chat agents that answer factual questions with citations.
  - name: Knowledge Assistants
    description: Power knowledge assistants that need grounded responses.
  - name: Search-Backed Chat
    description: Replace bare LLMs with search-grounded chat experiences.
  integrations:
  - name: Python
  - name: TypeScript
  - name: Go
  - name: Rust
  authentication:
  - type: API Key
    description: Bot API token sent via the Authorization header.
- aid: kagi:kagi-extract-api
  name: Kagi Extract API
  description: Extract markdown content from web URLs.
  humanURL: https://help.kagi.com/kagi/api/search.html
  baseURL: https://kagi.com/api/v0
  tags:
  - Extract
  properties:
  - type: OpenAPI
    url: openapi/kagi-extract-api-openapi.yml
- aid: kagi:kagi-search-api
  name: Kagi Search API
  description: Perform Kagi web searches.
  humanURL: https://help.kagi.com/kagi/api/search.html
  baseURL: https://kagi.com/api/v0
  tags:
  - Search
  properties:
  - type: OpenAPI
    url: openapi/kagi-search-api-openapi.yml
common:
- type: Plans
  url: plans/kagi-plans-pricing.yml
- type: RateLimits
  url: rate-limits/kagi-rate-limits.yml
- type: FinOps
  url: finops/kagi-finops.yml
- type: AgenticAccess
  url: agentic-access/kagi-agentic-access.yml
- type: VulnerabilityDisclosure
  url: security/kagi-vulnerability-disclosure.yml
- type: DomainSecurity
  url: security/kagi-domain-security.yml
- type: Authentication
  url: authentication/kagi-authentication.yml
- type: Website
  url: https://kagi.com
- type: Documentation
  url: https://help.kagi.com/kagi/api/overview.html
- type: Blog
  url: https://blog.kagi.com
- type: GitHubOrganization
  url: https://github.com/kagisearch
- type: Pricing
  url: https://help.kagi.com/kagi/api/overview.html
- type: TermsOfService
  url: https://kagi.com/terms
- type: PrivacyPolicy
  url: https://kagi.com/privacy
- type: Discord
  url: https://kagi.com/discord
- type: X
  url: https://x.com/kagihq
- type: ChangeLog
  url: https://kagi.com/changelog
- type: DataProcessing
  url: privacy/kagi-privacy-policy.yml
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com

Kagi API — frequently asked questions

Does Kagi have an API?

Yes. APIs.io lists 6 APIs from Kagi, including Kagi Search API, Kagi Enrichment API and Kagi Universal Summarizer API, and 3 more.

Is there an OpenAPI specification for the Kagi API?

Yes. APIs.io indexes 2 OpenAPI specifications for Kagi, each linked for download from this page.

How do I authenticate with the Kagi API?

Kagi uses bearer-token authentication (http · 1 scheme). The details are profiled on APIs.io as Kagi Authentication.

How much does the Kagi API cost?

APIs.io lists 1 pricing plan for Kagi, with each plan's price, limits and inclusions under Pricing on this page.

Is the Kagi API ready for AI agents?

Kagi has a Kin Score of 38.8 out of 100 (thin) and an Agent Readiness score of 19.6 (agent-aware), scored by API Evangelist on 2026-11-13.

Work with this as data

Every provider here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for providers

9 MCP tools reach this

find_providersBrowse and filter every provider in the catalog.
get_provider_artifactsEvery artifact this provider publishes, grouped by type.
get_provider_operationsEvery operation across all of their OpenAPIs — one call instead of parsing every spec.
get_provider_toolsEvery MCP tool they ship, with the operation each wraps.
get_provider_evidenceHow each part of their score was established. Free — the basis for a claim should not sit behind it.
get_provider_ratingPRO — composite, band, trend and facet scores.
apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
resolveTurn a domain, URL or GitHub org into the provider it belongs to.
find_cohortsEvery scored population of providers in the catalog.

All 92 tools →

Call it yourself

curl for this page

This provider

curl "https://apis.io/api/v1/providers/kagi"

All providers

curl "https://apis.io/api/v1/providers?limit=25"

Every operation they expose

curl "https://apis.io/api/v1/providers/kagi/operations?limit=25"

How their score was established

curl "https://apis.io/api/v1/providers/kagi/evidence"

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.

GitHub Google LinkedIn

A second provider on the same verified email joins the account you already have.