Jina AI

aid: jina-ai
name: Jina AI
description: Jina AI provides Search Foundation APIs for AI-powered applications, offering embeddings, reranking, and web
  reading capabilities. Their Reader API converts URLs to LLM-friendly input by simply adding r.jina.ai in front.
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: freemium
  onboarding: self-serve
  trial: false
  try_now: true
  public: false
  gated: none
  gated_source:
  - onboarding
  label: Freemium · Self-serve signup
  confidence: medium
  source:
  - plans
  - authentication
  - security
  generated: '2026-11-06'
  method: derived
position: Consuming
access: 3rd-Party
image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/icons/jina-ai.png
tags:
- Artificial Intelligence
- Embeddings
- Machine Learning
- Reranking
- Search
tags_raw:
- AI
- Embeddings
- Machine Learning
- Reranking
- Search
- Machine-Learning
created: '2025-02-06'
modified: '2026-10-06'
url: https://raw.githubusercontent.com/api-evangelist/jina-ai/refs/heads/main/apis.yml
specificationVersion: '0.23'
apis:
- aid: jina-ai:jina-ai-batch-api
  name: Jina AI Batch API
  description: Asynchronous batch embedding jobs
  humanURL: https://jina.ai/embeddings/
  baseURL: https://api.jina.ai/v1
  tags:
  - Batch
  properties:
  - type: OpenAPI
    url: openapi/jina-ai-batch-api-openapi.yml
  - type: Documentation
    url: https://docs.jina.ai/
  - type: Documentation
    url: https://jina.ai/reader/
- aid: jina-ai:jina-ai-embeddings-api
  name: Jina AI Embeddings API
  description: Synchronous embedding generation
  humanURL: https://jina.ai/embeddings/
  baseURL: https://api.jina.ai/v1
  tags:
  - Embeddings
  properties:
  - type: OpenAPI
    url: openapi/jina-ai-embeddings-api-openapi.yml
  - type: Documentation
    url: https://docs.jina.ai/
  - type: Documentation
    url: https://jina.ai/reader/
- aid: jina-ai:jina-ai-reader-api
  name: Jina AI Reader API
  description: URL-to-markdown extraction
  humanURL: https://jina.ai/embeddings/
  baseURL: https://api.jina.ai/v1
  tags:
  - Reader
  properties:
  - type: OpenAPI
    url: openapi/jina-ai-reader-api-openapi.yml
  - type: Documentation
    url: https://docs.jina.ai/
  - type: Documentation
    url: https://jina.ai/reader/
- aid: jina-ai:jina-ai-reranker-api
  name: Jina AI Reranker API
  description: Cross-encoder reranking
  humanURL: https://jina.ai/embeddings/
  baseURL: https://api.jina.ai/v1
  tags:
  - Reranker
  properties:
  - type: OpenAPI
    url: openapi/jina-ai-reranker-api-openapi.yml
  - type: Documentation
    url: https://docs.jina.ai/
  - type: Documentation
    url: https://jina.ai/reader/
- aid: jina-ai:jina-ai-batch-embeddings-api
  name: Jina AI Batch Embeddings API
  description: 'Asynchronous embedding for large workloads: up to 50,000 inputs from a GCS file URL, or 10,000 inline.


    Submit with `POST /v1/batch/embeddings`, poll `GET /v1/batch/{batch_id}` until the status is `completed`, then fetch `GET
    /v1/batch/{batch_id}/output`. Input is OpenAI-compatible JSONL with `custom_id` and `body.input`. Output files expire
    after 24 hours, and a webhook can be called on completion.'
  humanURL: https://jina.ai/embeddings/
  baseURL: https://api.jina.ai
  tags:
  - Batch Embeddings
  properties:
  - type: OpenAPI
    url: openapi/jina-ai-batch-embeddings-api-openapi.yml
- aid: jina-ai:jina-ai-generative-models-api
  name: Jina AI Generative Models API
  description: 'Document transcription over the OpenAI chat completions schema. Point any OpenAI-compatible client at the
    server URL above with `/v1` appended, set `model`, and send a page image; the response is the page as text or markdown,
    tables and layout preserved.


    `stream: true` returns server-sent events. `response_format` with a `json_schema` constrains the output to that schema
    instead of prose. Parameters outside the supported set are accepted and ignored rather than rejected, so an SDK-generated
    payload always works.'
  humanURL: https://jina.ai/embeddings/
  baseURL: https://api.jina.ai
  tags:
  - Generative Models
  properties:
  - type: OpenAPI
    url: openapi/jina-ai-generative-models-api-openapi.yml
- aid: jina-ai:jina-ai-model-list-api
  name: Jina AI Model List API
  description: 'Every model this API serves, in OpenRouter-compatible form: identifiers, input and output modalities, context
    lengths and prices. Read it before hardcoding a model name — the catalogue moves.'
  humanURL: https://jina.ai/embeddings/
  baseURL: https://api.jina.ai
  tags:
  - Model List
  properties:
  - type: OpenAPI
    url: openapi/jina-ai-model-list-api-openapi.yml
- aid: jina-ai:jina-ai-search-api
  name: Jina AI Search API
  description: Search the web and get the result pages back in an LLM-friendly format.
  humanURL: https://jina.ai/embeddings/
  baseURL: https://api.jina.ai
  tags:
  - Search
  properties:
  - type: OpenAPI
    url: openapi/jina-ai-search-api-openapi.yml
- aid: jina-ai:jina-ai-search-foundation-models-api
  name: Jina AI Search Foundation Models API
  description: '**Embeddings** turn text, images, audio, video and PDFs into dense vectors for semantic search, RAG, clustering
    and classification. Task-specific variants (`retrieval.query`, `retrieval.passage`, `text-matching`, `clustering`, `classification`)
    are selected per request rather than per model, and `dimensions` truncates the output where a model supports it.


    **Reranking** scores a query against a candidate set and returns it reordered, which is more accurate than embedding similarity
    and slower — the usual shape is embeddings to retrieve, reranking to refine.


    Each endpoint''s `model` field lists the models it accepts.'
  humanURL: https://jina.ai/embeddings/
  baseURL: https://api.jina.ai
  tags:
  - Search Foundation Models
  properties:
  - type: OpenAPI
    url: openapi/jina-ai-search-foundation-models-api-openapi.yml
common:
- type: Plans
  url: plans/jina-ai-plans-pricing.yml
- type: RateLimits
  url: rate-limits/jina-ai-rate-limits.yml
- type: FinOps
  url: finops/jina-ai-finops.yml
- url: https://jina.ai/news/
  type: Blog
- type: CapabilityMap
  url: capabilities/jina-ai-capability-edges.yml
  name: Jina AI Business Capability Map
- type: AgenticAccess
  url: agentic-access/jina-ai-agentic-access.yml
- type: DomainSecurity
  url: security/jina-ai-domain-security.yml
- type: Authentication
  url: authentication/jina-ai-authentication.yml
- type: LinkedIn
  url: https://www.linkedin.com/company/jinaai
- type: Website
  url: https://jina.ai
- type: Portal
  url: https://jina.ai/api-dashboard/
- type: Documentation
  url: https://docs.jina.ai/
- type: GettingStarted
  url: https://docs.jina.ai/
- type: GitHubOrganization
  url: https://github.com/jina-ai
- type: Signup
  url: https://jina.ai/api-dashboard/
- name: MCP Server
  url: https://github.com/jina-ai/MCP
  type: MCPServer
- type: LlmsText
  url: https://docs.jina.ai/llms.txt
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com