Jina AI Search Foundation (DeepSearch / Reader)

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

• █████▒░░░░
  55 / 100
  Agent friendliness
• ████████▒░
  85 / 100
  Pricing transparency
• █████▒░░░░
  55 / 100
  Setup speed
• █████▒░░░░
  55 / 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 model

Usage-based

Published pricing

✓ Yes

Free tier

✗ No

Free tier details

10 million tokens one-time on new API key creation (shared across all APIs - Reader, Search, DeepSearch, Embeddings, Reranker, Classifier). No credit card required. This is a one-time welcome grant, not a recurring monthly allowance; once exhausted, tokens must be purchased. The Segmenter API does not consume tokens.

Self-serve signup

✓ Yes [2]jina.ai/contact-sales/“most of our customers self-serve with pay-as-you-go pricing”

Requires sales call

✗ No

Enterprise plan

✓ Yes [3]jina.ai/embeddings/“contact our sales team to get customized Kubernetes deployments for your Virtual Private Cloud and on-premises servers. Commercial deployment available via AWS SageMaker, Azure, and Google Cloud marketplaces.”

• AI answer
• Semantic / neural
• Full content for RAG
• Agent-ready / MCP

Supported actions

read_url (r.jina.ai - convert any URL to clean LLM-friendly text/Markdown), search_web (s.jina.ai - web search returning LLM-friendly results), deep_search (deepsearch.jina.ai/v1/chat/completions - iterative reasoning + search), ground_fact (g.jina.ai - fact-checking with factuality score and citations), create_embeddings (api.jina.ai/v1/embeddings), batch_embeddings (api.jina.ai/v1/batch/embeddings), rerank (api.jina.ai/v1/rerank), classify (api.jina.ai/v1/train and classify), segment (api.jina.ai/v1/segment - tokenize and chunk long text), search_arxiv (MCP tool - academic paper search), search_images (MCP tool - image search), capture_screenshot_url (MCP tool), expand_query (MCP tool - query rewriting and expansion), deduplicate_strings (MCP tool), deduplicate_images (MCP tool), sort_by_relevance (MCP tool - reranking), primer (MCP tool - localized/time-aware context)

Regions

Global (standard endpoints at r.jina.ai, s.jina.ai, api.jina.ai), EU (dedicated endpoints at eu.r.jina.ai and eu.s.jina.ai)

Languages

Multilingual - embeddings models support 100+ languages, Reranker v2/v3 supports 100+ languages, ReaderLM-v2 supports 29 languages for structured extraction, Segmenter API supports 100+ languages including CJK

Input types

URL (any publicly accessible webpage or PDF), Natural language query (Search API, DeepSearch), Plain text (embeddings, reranker, segmenter), Images (WebP, PNG, JPEG - DeepSearch and multimodal embeddings), Files (TXT, PDF up to 10MB - DeepSearch), HTML/PDF upload via POST (Reader API), Multi-message conversation with role-based structure (DeepSearch)

Output types

JSON (URL, title, content, timestamp), Markdown (clean web content), Structured data / JSON schema (via ReaderLM-v2), Fixed-length embedding vectors, Ranked document list with relevance scores, Answer with visited/read URL citations (DeepSearch), Factuality score + verdict + source quotes (Grounding API), Streaming server-sent events (DeepSearch reasoning steps), Image captions / alt text (Reader API auto-captioning)

Webhooks

✗ No

Sandbox / test mode

✗ No

SDK languages

JavaScript/Node.js, MCP (remote server)

MCP server

✓ Yes [4]jina.ai/news/agentic-workflow-with-jina-remote-mcp-server/“This is the official Jina AI Remote MCP Server, recently released by Jina AI and available at https://mcp.jina.ai/sse”

SOC 2

– Unknown

HIPAA

– Unknown

GDPR

✓ Yes [5]jina.ai/legal/“Legal Basis for Processing: Consent, Contract, Legal Obligation, Vital Interests, Public Task, and Legitimate Interests (Art. 6 GDPR); Standard Contractual Clauses (SCCs) for non-EU transfers; EU-U.S. Data Privacy Framework compliance where applicable”

ISO 27001

– Unknown

PCI DSS

– Unknown

Published SLA

✗ No

Rate limits

Reader API: 20 RPM (no key), 500 RPM (paid), 5,000 RPM (premium); Search API: 100 RPM (paid), 1,000 RPM (premium); DeepSearch: 50 RPM (free/paid), 500 RPM (premium); Embeddings/Reranker: 500 RPM & 2M TPM (paid), 5,000 RPM & 50M TPM (premium); Classifier: 125 RPM & 500K TPM (paid), 1,250 RPM & 12M TPM (premium); Free key baseline: 100 RPM & 100K TPM & 2 concurrent requests across most APIs; IP ceiling: 10,000 requests per 60 seconds across all APIs [6]jina.ai/reader/“Reader API: 20 RPM (no key), 500 RPM (paid), 5,000 RPM (premium); Search API: 100 RPM (paid), 1,000 RPM (premium). Free API Key: 100 RPM, 100K TPM, 2 concurrent requests”jina.ai/deepsearch/“Free API Key: 50 RPM; Paid API Key: 50 RPM; Premium API Key: 500 RPM”jina.ai/classifier/“Paid: 125 RPM, 500,000 TPM, 50 concurrent; Premium: 1,250 RPM, 12,000,000 TPM, 500 concurrent”

Known restrictions

API data (inputs, outputs, requests) is never used to train Jina's models, Cannot access login-protected or paywalled content (Reader API), Does not circumvent anti-bot protections, Competitive application development using API Output is prohibited per ToS, Reverse engineering or decompilation of services is prohibited, Automated scraping of Jina's own services is prohibited per ToS, Reader API caches URL content for 5 minutes by default, Open-source model licenses are CC-BY-NC 4.0 (non-commercial); commercial use requires Elastic customer license or contacting Elastic Sales, As of October 2025 Jina AI GmbH was acquired by Elastic; new contracts paused during integration; most customers remain on self-serve pay-as-you-go, Customers solely responsible for safeguarding API keys and all activity on them

• Docs
• API reference
• llms.txt
• Changelog
• Status page

Docs rendering: static · llms.txt present

API style

rest

Base URL

https://r.jina.ai (Reader); https://s.jina.ai (Search); https://deepsearch.jina.ai/v1 (DeepSearch); https://api.jina.ai/v1 (Embeddings/Reranker)

Version

v1

Versioning

url

Stability

ga

Auth methods

api_key

Idempotency keys

✗ No

Rate limit

500 / minute

SDKs

• JavaScript/Node.js node-DeepResearch · repo
• MCP (remote server) · repo

• Auth docs
• Quickstart
• MCP server

Launched

2020-01-01

GA

2025-02-02

Notable customers

Singapore Airlines, Salesforce, Alibaba, AWS, Elastic, Databricks, Weaviate, Comcast

• 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

• Parallel Search API

  "The highest accuracy web search for your AI"

  Usage · public pricing · self-serve

Jina AI Search Foundation (DeepSearch / Reader) alternatives · Jina AI Search Foundation (DeepSearch / Reader) vs Firecrawl · All Web Search APIs APIs

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

1. ↑Description: jina.ai
2. ↑Self-serve signup: jina.ai
3. ↑Enterprise plan: jina.ai
4. ↑MCP server: jina.ai
5. ↑GDPR: jina.ai
6. ↑Rate limits: jina.ai · jina.ai · jina.ai

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

1. 2026-06-15 Score Agent Friendliness: 30 → 55
2. 2026-06-15 Score Docs Quality: 15 → 55
3. 2026-06-14 Changelog URL: (none) → https://docs.jina.ai/changelog
4. 2026-06-14 API Reference URL: (none) → https://docs.jina.ai/reference
5. 2026-06-14 Has Structured Data: (none) → No
6. 2026-06-14 Robots Allows Agents: (none) → Yes
7. 2026-06-14 Llms Txt Present: No → Yes
8. 2026-06-14 Llms Txt URL: (none) → https://docs.jina.ai/llms.txt
9. 2026-06-14 Capabilities: {} → {"semantic":true,"ai_answer":true,"agent_ready":true,"content_extraction":true}
10. 2026-06-14 Summary Md: (none) → Jina AI Search Foundation is a suite of LLM-oriented search and retrieval APIs …
11. 2026-06-14 Avoid If: (none) → You want to try it free before paying, You have strict compliance requirements
12. 2026-06-14 Score Agent Friendliness: (none) → 30
13. 2026-06-14 Score Pricing Transparency: (none) → 85
14. 2026-06-14 Score Setup Speed: (none) → 55
15. 2026-06-14 Score Docs Quality: (none) → 15
16. 2026-06-14 Score Procurement Friction: (none) → 85
17. 2026-06-14 Score Trust Readiness: (none) → 15
18. 2026-06-14 Best For: (none) → AI agents and automation - an agent-ready surface (MCP / llms.txt), Teams needi…
19. 2026-06-14 Scoring Methodology: (none) → Scores are computed deterministically from this profile's published, sourced fi…
20. 2026-06-14 Llms Txt Present: (none) → No
21. 2026-06-14 Docs URL: (none) → https://docs.jina.ai
22. 2026-06-14 Status Page URL: (none) → https://status.jina.ai
23. 2026-06-14 Rendering: (none) → static
24. 2026-06-14 GDPR: set to Yes
25. 2026-06-14 SLA Published: set to No
26. 2026-06-14 SLA URL: set to https://status.jina.ai/
27. 2026-06-14 Data Retention Policy URL: set to https://jina.ai/legal/#privacy-policy
28. 2026-06-14 Documented Rate Limits: set to Reader API: 20 RPM (no key), 500 RPM (paid), 5,000 RPM (premium); Search API: 1…
29. 2026-06-14 Rate Limit Requests: set to 500
30. 2026-06-14 Rate Limit Window: set to minute
31. 2026-06-14 Known Restrictions: set to API data (inputs, outputs, requests) is never used to train Jina's models, Cann…
32. 2026-06-14 Auth Methods: set to api_key
33. 2026-06-14 Auth Docs URL: set to https://docs.jina.ai/
34. 2026-06-14 API Style: set to rest
35. 2026-06-14 Base URL: set to https://r.jina.ai (Reader); https://s.jina.ai (Search); https://deepsearch.jina…
36. 2026-06-14 API Version: set to v1
37. 2026-06-14 Versioning Scheme: set to url
38. 2026-06-14 Stability: set to ga
39. 2026-06-14 MCP URL: set to https://mcp.jina.ai/v1
40. 2026-06-14 Quickstart URL: set to https://jina.ai/reader/
41. 2026-06-14 Idempotency Supported: set to No
42. 2026-06-14 Requires Verification: set to No
43. 2026-06-14 Starting Price Usd: set to 0.05
44. 2026-06-14 Price Basis: set to 1,000,000 tokens
45. 2026-06-14 Free Tier Limit: set to 10,000,000 tokens (shared across all APIs)
46. 2026-06-14 Launched At: set to 2020-01-01
47. 2026-06-14 GA Date: set to 2025-02-02
48. 2026-06-14 Slug: set to jina-search
49. 2026-06-14 Fields Not Found: set to SOC2 certification status (not stated on legal/security pages), HIPAA complianc…
50. 2026-06-14 Source Confidence: set to high

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.

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

curl -X POST https://apio.sh/api/suggest/jina-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 →