Kagi Search API

"The Search API gives programmable access to Kagi's premium search results." [1]

kagi.com/api/docs · By Kagi · Agent JSON · Suggest an edit · Last verified 2026-06-14 · Source confidence: high

Kagi Search API provides programmable access to Kagi's premium search index, covering web, image, news, video, podcast, and content extraction endpoints, with built-in summarization and citation-grounded answers suited for RAG pipelines and AI agents. Pricing is usage-based at $12 per 1,000 searches with no sales call required, and an enterprise plan is available. The API is GDPR compliant, supports Python, Go, Rust, and TypeScript SDKs, and ships an MCP server for agent tooling integrations.

Best for / Avoid if

Best for: AI agents and automation - an agent-ready surface (MCP / llms.txt); Teams needing broad API coverage out of the box; Cost-sensitive teams - low, transparent entry price

Avoid if: You want to try it free before paying; You have strict compliance requirements

Scores

  • 40 / 100
    Agent friendliness
  • 85 / 100
    Pricing transparency
  • 60 / 100
    Setup speed
  • 30 / 100
    Docs quality
  • 85 / 100
    Procurement ease
  • 15 / 100
    Trust readiness

Scores are computed deterministically from this profile's published, sourced fields (pricing, compliance, capabilities, docs and developer-surface signals) - not from reviews or paid placement. Each axis is 0-100; an unknown signal scores 0 for that axis. Procurement ease is the inverse of buying friction (higher = easier to adopt).

Pricing & procurement

Pricing model
Usage-based [2]
Published pricing
Yes [3]
Free tier
No [4]
Self-serve signup
Yes
Requires sales call
No
Enterprise plan
Yes [5]
Published prices
PlanItemPerAmountSource
Search API1,000 requests$12source
Extract API1,000 pages$4source
FastGPT API (with web search)1,000 queries$15source
FastGPT API (without web search)1,000 queries$1.5source
Enrichment API (Teclis web + TinyGem news)1,000 searches$2source
Universal Summarizer — Cecil & Agnes models (per 1k tokens)1,000 tokens processed$0.03source
Ultimate subscriberUniversal Summarizer — Cecil & Agnes models (per 1k tokens, discounted)1,000 tokens processed$0.025source
Universal Summarizer — Muriel model (flat per summary)summary$1source
EnterpriseSearch API (volume discount, custom rate limits, enterprise SLA) - source

Capabilities

  • AI answer
  • Full content for RAG
  • News search
  • Agent-ready / MCP
Supported actions
web_search, image_search, news_search, video_search, podcast_search, get_contents, enrich_web, enrich_news, summarize, answer_with_citations [6]
Regions
Global - any valid ISO 3166-1 Alpha-2 country code supported as region filter; 'no_region' for general results [7]
Input types
natural language query, keywords, URL (for extract and summarizer endpoints), text (for summarizer endpoint), lens filters, domain filters, date range filters, region filters, file type filters
Output types
JSON, Markdown, answer + citations (FastGPT), full page contents (extract), structured result objects (url, title, snippet, timestamp, image thumbnail, metadata)
Webhooks
No
Sandbox / test mode
No [8]
SDK languages
Python, Go, Rust, TypeScript [9]
MCP server
Yes [10]

Trust & compliance

SOC 2
None [11]
HIPAA
No [12]
GDPR
Yes [13]
ISO 27001
No [14]
PCI DSS
No [15]
Published SLA
No [16]
Known restrictions
Extract endpoint is limited to 10 URLs per request, Only Kagi API products are licensed for commercial use; non-API frontend products (e.g. Universal Summarizer UI) are non-commercial only, On Family and Team plans, only the account owner can access the API portal, API keys can be IP-whitelisted, restricting access to configured addresses, Search queries temporarily logged for debugging and automatically purged after a short period, HTTP(S) URLs only for extract endpoint, Enrichment API only billed when non-zero results are returned, FastGPT web_search parameter currently mandatory (disabling it returns an error) [17]

Developer surface

Docs rendering: client_rendered

Integration

API style
rest
Base URL
https://kagi.com/api/v1
Version
v1
Versioning
url
Stability
beta
Auth methods
api_key
Error format
vendor-specific (meta.trace field + X-Kagi-Trace response header)

SDKs

  • Python kagi-api-python · repo
  • Go kagi-api-golang · repo
  • Rust kagi-api-rust · repo
  • TypeScript kagi-api-typescript · repo

Adoption & maturity

Launched
2018-01-01

Other Web Search APIs

  • Firecrawl

    The API to search, scrape, and interact with the web at scale.

    Subscription · free tier · public pricing · self-serve

  • Exa

    "Web search, built for AI agents. One API for search, crawling, and research agents."

    Usage · free tier · public pricing · self-serve

  • Brave Search API

    "The Brave Search API provides developers with access to Brave Search results and enables building AI products, chatbots, coding assistants, and AI-search engines with real-time web data."

    Usage · public pricing · self-serve

  • Tavily Search API

    "Real-time search, extraction, research, and web crawling through a single, secure API."

    Hybrid · free tier · public pricing · self-serve

  • Linkup

    "Production-grade Web Search API for AI"

    Usage · free tier · public pricing · self-serve

  • Jina AI Search Foundation (DeepSearch / Reader)

    "Your Search Foundation, Supercharged."

    Usage · public pricing · self-serve

Kagi Search API alternatives · Kagi Search API vs Firecrawl · All Web Search APIs APIs

References

Each field above carries a numbered source - hover for a preview, click to jump here.

  1. Description: help.kagi.com
  2. Pricing model: kagi.com · kagi.com
  3. Published pricing: kagi.com · kagi.com
  4. Free tier: help.kagi.com · kagi.com
  5. Enterprise plan: kagi.com
  6. Supported actions: kagi.com · help.kagi.com
  7. Regions: help.kagi.com
  8. Sandbox: kagi.com
  9. SDK languages: kagi.com
  10. MCP server: kagi.com · github.com
  11. SOC 2: help.kagi.com · blog.kagi.com
  12. HIPAA: help.kagi.com · kagi.com
  13. GDPR: kagi.com
  14. ISO 27001: help.kagi.com
  15. PCI DSS: kagi.com
  16. Published SLA: kagi.com · help.kagi.com
  17. Known restrictions: kagi.com · help.kagi.com · help.kagi.com

Change history

Every field change, who made it, and when - from our audited data pipeline and editors.

  1. 2026-06-15 Score Agent Friendliness: 3040
  2. 2026-06-15 Score Docs Quality: 1030
  3. 2026-06-14 Has Structured Data: (none)No
  4. 2026-06-14 API Reference URL: (none)https://kagi.com/signin?r=/api
  5. 2026-06-14 Robots Allows Agents: (none)Yes
  6. 2026-06-14 Capabilities: {}{"news":true,"ai_answer":true,"agent_ready":true,"content_extraction":true}
  7. 2026-06-14 Summary Md: (none)Kagi Search API provides programmable access to Kagi's premium search index, co…
  8. 2026-06-14 Avoid If: (none)You want to try it free before paying, You have strict compliance requirements
  9. 2026-06-14 Scoring Methodology: (none)Scores are computed deterministically from this profile's published, sourced fi…
  10. 2026-06-14 Best For: (none)AI agents and automation - an agent-ready surface (MCP / llms.txt), Teams needi…
  11. 2026-06-14 Score Agent Friendliness: (none)30
  12. 2026-06-14 Score Pricing Transparency: (none)85
  13. 2026-06-14 Score Setup Speed: (none)60
  14. 2026-06-14 Score Docs Quality: (none)10
  15. 2026-06-14 Score Procurement Friction: (none)85
  16. 2026-06-14 Score Trust Readiness: (none)15
  17. 2026-06-14 Llms Txt Present: (none)No
  18. 2026-06-14 Changelog URL: (none)https://kagi.com/changelog
  19. 2026-06-14 Status Page URL: (none)https://status.kagi.com
  20. 2026-06-14 Rendering: (none)client_rendered
  21. 2026-06-14 Supported Actions: set to web_search, image_search, news_search, video_search, podcast_search, get_conten…
  22. 2026-06-14 Supported Regions: set to Global - any valid ISO 3166-1 Alpha-2 country code supported as region filter; …
  23. 2026-06-14 Supported Languages: set to (none)
  24. 2026-06-14 Input Types: set to natural language query, keywords, URL (for extract and summarizer endpoints), t…
  25. 2026-06-14 Output Types: set to JSON, Markdown, answer + citations (FastGPT), full page contents (extract), str…
  26. 2026-06-14 Webhooks Supported: set to No
  27. 2026-06-14 Sandbox Available: set to No
  28. 2026-06-14 SDK Languages: set to Python, Go, Rust, TypeScript
  29. 2026-06-14 Auth Methods: set to api_key
  30. 2026-06-14 SDK Packages: set to Python, Go, Rust, TypeScript
  31. 2026-06-14 MCP Server Available: set to Yes
  32. 2026-06-14 Auth Docs URL: set to https://help.kagi.com/kagi/api/overview.html
  33. 2026-06-14 API Style: set to rest
  34. 2026-06-14 Base URL: set to https://kagi.com/api/v1
  35. 2026-06-14 API Version: set to v1
  36. 2026-06-14 Versioning Scheme: set to url
  37. 2026-06-14 Stability: set to beta
  38. 2026-06-14 MCP URL: set to https://mcp.kagi.com/mcp
  39. 2026-06-14 Quickstart URL: set to https://help.kagi.com/kagi/api/api-portal.html
  40. 2026-06-14 Error Format: set to vendor-specific (meta.trace field + X-Kagi-Trace response header)
  41. 2026-06-14 Requires Verification: set to Yes
  42. 2026-06-14 Starting Price Usd: set to 12
  43. 2026-06-14 Price Basis: set to 1,000 searches
  44. 2026-06-14 Pricing Model: set to usage_based
  45. 2026-06-14 Notable Customers: set to (none)
  46. 2026-06-14 Fields Not Found: set to documented_rate_limits, sla_published (SLAs mentioned for enterprise tier only,…
  47. 2026-06-14 Source Confidence: set to high
  48. 2026-06-14 Extractor: set to claude-subagent:sonnet
  49. 2026-06-14 Last Verified At: set to 2026-06-14T00:00:00.000Z
  50. 2026-06-14 Status: set to published

Suggest an edit / leave a review

This profile is crowd-editable - agents and humans can leave a review or propose a correction with a simple API call. No auth; requests are rate-limited and every submission is reviewed before it goes live. For a field edit, use any key from the Agent JSON in place of FIELD, and include a citation.

Leave a review or comment

curl -X POST https://apio.sh/api/feedback/kagi-search \
  -H 'Content-Type: application/json' \
  -d '{"kind":"review","rating":5,"body":"Your experience with this API…"}'

Suggest a correction to a field (cite a source)

curl -X POST https://apio.sh/api/suggest/kagi-search/FIELD \
  -H 'Content-Type: application/json' \
  -d '{"value":"corrected value","citations":[{"url":"https://source.example/page","excerpt":"supporting quote"}],"note":"what changed and why"}'

All the ways to contribute →