Tavily Search API

"Real-time search, extraction, research, and web crawling through a single, secure API." [1]

tavily.com · By Tavily · Agent JSON · Suggest an edit · Last verified 2026-06-14 · Source confidence: high

Tavily Search API is a REST API built for AI applications that need real-time web access, offering search, content extraction, crawling, site mapping, and async deep-research tasks in a single service. It targets RAG pipelines, LLM grounding, and AI agents across 195+ countries, with SDKs for Python and JavaScript/TypeScript and an MCP server available. Pricing starts at $0.008 per credit with 1,000 free credits per month, self-serve signup, and an enterprise plan. The service is SOC 2 Type II certified and GDPR compliant, and its customer list includes AWS, IBM, Mastercard, MongoDB, and LangChain.

Best for / Avoid if

Best for: Prototypes and side projects - free to start, no sales call; Regulated or enterprise workloads - compliance attestations and an enterprise plan; AI agents and automation - an agent-ready surface (MCP / llms.txt)

Scores

  • 80 / 100
    Agent friendliness
  • 100 / 100
    Pricing transparency
  • 80 / 100
    Setup speed
  • 75 / 100
    Docs quality
  • 100 / 100
    Procurement ease
  • 60 / 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
Hybrid (base + usage) [2]
Published pricing
Yes [3]
Free tier
Yes [4]
Free tier details
Researcher (Free) plan: 1,000 API credits / month recurring, no credit card required.
Self-serve signup
Yes [5]
Requires sales call
No
Enterprise plan
Yes [6]
Published prices
PlanItemPerAmountSource
Researcher (Free)Monthly subscriptionmonth$0source
Researcher (Free)API credits included (recurring)1,000 credits/month$0source
Pay As You GoAPI creditcredit$0.008source
ProjectMonthly subscriptionmonth$30source
ProjectAPI credits included4,000 credits/month - source
BootstrapMonthly subscriptionmonth$100source
BootstrapAPI credits included15,000 credits/month - source
StartupMonthly subscriptionmonth$220source
StartupAPI credits included38,000 credits/month - source
GrowthMonthly subscriptionmonth$500source
GrowthAPI credits included100,000 credits/month - source
EnterpriseMonthly subscriptionmonth (custom) - source
All plansBasic Search (search_depth=basic/fast/ultra-fast)1 credit per request - source
All plansAdvanced Search (search_depth=advanced)2 credits per request - source
All plansBasic Extract (URL content extraction)1 credit per 5 successful URL extractions - source
All plansAdvanced Extract (URL content extraction)2 credits per 5 successful URL extractions - source
All plansMap (standard web mapping)1 credit per 10 successful pages - source
All plansMap with instructions2 credits per 10 successful pages - source
All plansResearch — model=pro (deep research)15–250 credits per request - source
All plansResearch — model=mini (deep research)4–110 credits per request - source

Capabilities

  • Full content for RAG
  • Agent-ready / MCP
Supported actions
POST /search - web search (basic/advanced/fast/ultra-fast depth), POST /extract - extract content from URLs, POST /crawl - crawl webpages, POST /map - map website structure, POST /research - create async deep-research task, GET /research/{id} - poll research task status, GET /usage - get credit usage [7]
Regions
global, 195+ countries supported via country filter parameter
Input types
natural language query, URL, search_depth (basic/advanced/fast/ultra-fast), topic (general/news/finance), country filter (195+ countries), time_range / date range, include_domains / exclude_domains, include_answer (basic/advanced LLM answer), include_raw_content (markdown/text), include_images, safe_search (enterprise-only), auto_parameters [8]
Output types
JSON, answer (LLM-generated, basic or advanced), full page contents (markdown or text), images, relevance scores, citations, research report with citations, SSE stream (research endpoint) [9]
Webhooks
No
Sandbox / test mode
No [10]
SDK languages
Python, JavaScript/TypeScript [11]
MCP server
Yes [12]

Trust & compliance

SOC 2
SOC 2 Type II [13]
HIPAA
No [14]
GDPR
Yes [15]
ISO 27001
Unknown
PCI DSS
Unknown
Published SLA
Yes [16]
Rate limits
Default endpoints: 100 RPM (development), 1,000 RPM (production). Crawl endpoint: 100 RPM (both). Research endpoint: 20 RPM (both). Usage endpoint: 10 requests per 10 minutes (both). [17]
Known restrictions
No HIPAA-covered protected health information may be submitted, No children's data (under 13, or 16 in EU) without prior written consent, No government IDs, payment card info, or biometric data without prior written consent, Outputs may not be transferred, assigned, or shared with third parties without written consent, No building of competitive products using the service, No reverse engineering of the service, safe_search parameter is enterprise-only, Zero data retention policy on search queries per FAQ, Customer input may be used by Tavily and third-party AI providers for model training/improvement, SLA of 99.99% uptime is enterprise-tier only; standard ToS provides service AS IS with no uptime warranty [18]

Developer surface

Docs rendering: static · llms.txt present

Integration

API style
rest
Base URL
https://api.tavily.com
Versioning
none
Stability
ga
Auth methods
api_key, oauth2
Idempotency keys
No
Error format
vendor-specific
Rate limit
1000 / minute

SDKs

  • Python tavily-python · repo
  • JavaScript/TypeScript @tavily/core · repo

Adoption & maturity

Launched
2023-01-01
Notable customers
LangChain, MongoDB, Groq, Writer, Cohere, AWS, IBM, Mastercard, JetBrains, Monday

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

  • 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

  • Parallel Search API

    "The highest accuracy web search for your AI"

    Usage · public pricing · self-serve

Tavily Search API alternatives · Tavily 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: tavily.com
  2. Pricing model: help.tavily.com · help.tavily.com
  3. Published pricing: help.tavily.com · docs.tavily.com
  4. Free tier: help.tavily.com · docs.tavily.com
  5. Self-serve signup: help.tavily.com
  6. Enterprise plan: help.tavily.com
  7. Supported actions: docs.tavily.com · docs.tavily.com
  8. Input types: docs.tavily.com
  9. Output types: docs.tavily.com · docs.tavily.com
  10. Sandbox: help.tavily.com
  11. SDK languages: docs.tavily.com
  12. MCP server: docs.tavily.com
  13. SOC 2: trust.tavily.com · docs.tavily.com
  14. HIPAA: tavily.com
  15. GDPR: tavily.com · tavily.com
  16. Published SLA: tavily.com · tavily.com
  17. Rate limits: docs.tavily.com · docs.tavily.com
  18. Known restrictions: tavily.com · tavily.com · docs.tavily.com

Change history

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

  1. 2026-06-15 Score Docs Quality: 4575
  2. 2026-06-15 Score Agent Friendliness: 6080
  3. 2026-06-14 Has Structured Data: (none)Yes
  4. 2026-06-14 Changelog URL: (none)https://docs.tavily.com/changelog
  5. 2026-06-14 Robots Allows Agents: (none)Yes
  6. 2026-06-14 Llms Txt URL: https://tavily.com/llms.txthttps://docs.tavily.com/llms.txt
  7. 2026-06-14 API Reference URL: (none)https://docs.tavily.com/documentation/api-reference/introduction
  8. 2026-06-14 Capabilities: {}{"agent_ready":true,"content_extraction":true}
  9. 2026-06-14 Summary Md: (none)Tavily Search API is a REST API built for AI applications that need real-time w…
  10. 2026-06-14 Score Trust Readiness: (none)60
  11. 2026-06-14 Score Agent Friendliness: (none)60
  12. 2026-06-14 Score Pricing Transparency: (none)100
  13. 2026-06-14 Score Setup Speed: (none)80
  14. 2026-06-14 Score Docs Quality: (none)45
  15. 2026-06-14 Score Procurement Friction: (none)100
  16. 2026-06-14 Best For: (none)Prototypes and side projects - free to start, no sales call, Regulated or enter…
  17. 2026-06-14 Scoring Methodology: (none)Scores are computed deterministically from this profile's published, sourced fi…
  18. 2026-06-14 Llms Txt Present: (none)Yes
  19. 2026-06-14 Docs URL: (none)https://docs.tavily.com
  20. 2026-06-14 Status Page URL: (none)https://status.tavily.com
  21. 2026-06-14 Openapi Spec URL: (none)https://tavily.com/.well-known/openapi.json
  22. 2026-06-14 Rendering: (none)static
  23. 2026-06-14 Llms Txt URL: (none)https://tavily.com/llms.txt
  24. 2026-06-14 Enterprise Plan Available: set to Yes
  25. 2026-06-14 SOC 2: set to type_2
  26. 2026-06-14 HIPAA: set to No
  27. 2026-06-14 GDPR: set to Yes
  28. 2026-06-14 SLA Published: set to Yes
  29. 2026-06-14 Data Retention Policy URL: set to https://www.tavily.com/privacy
  30. 2026-06-14 Documented Rate Limits: set to Default endpoints: 100 RPM (development), 1,000 RPM (production). Crawl endpoin…
  31. 2026-06-14 Rate Limit Requests: set to 1000
  32. 2026-06-14 Rate Limit Window: set to minute
  33. 2026-06-14 Known Restrictions: set to No HIPAA-covered protected health information may be submitted, No children's d…
  34. 2026-06-14 Auth Methods: set to api_key, oauth2
  35. 2026-06-14 Auth Docs URL: set to https://docs.tavily.com/documentation/api-reference/introduction
  36. 2026-06-14 API Style: set to rest
  37. 2026-06-14 Base URL: set to https://api.tavily.com
  38. 2026-06-14 Versioning Scheme: set to none
  39. 2026-06-14 Stability: set to ga
  40. 2026-06-14 MCP URL: set to https://mcp.tavily.com/mcp/
  41. 2026-06-14 Quickstart URL: set to https://docs.tavily.com/documentation/quickstart
  42. 2026-06-14 Error Format: set to vendor-specific
  43. 2026-06-14 Requires Verification: set to No
  44. 2026-06-14 Starting Price Usd: set to 0.008
  45. 2026-06-14 Price Basis: set to credit
  46. 2026-06-14 Free Tier Limit: set to 1,000 API credits/month
  47. 2026-06-14 Launched At: set to 2023-01-01
  48. 2026-06-14 Slug: set to tavily
  49. 2026-06-14 Fields Not Found: set to iso_27001, pci_dss, specific supported_languages list (no explicit list publish…
  50. 2026-06-14 Source Confidence: set to high

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/tavily \
  -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/tavily/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 →