Jina AI Generative Models API

openapi: 3.2.0
info:
  title: Jina AI Generative Models API
  description: 'Jina AI APIs on three hosts: Reader (`r.jina.ai`), Search (`s.jina.ai`) and the Search Foundation models (`api.jina.ai`). | I want to | Endpoint |

    |---|---|

    | Read a web page or PDF as LLM-friendly Markdown | GET r.jina.ai/{url} · POST r.jina.ai |

    | Search the web and get the result pages as text | GET s.jina.ai/{q} · POST s.jina.ai/search |

    | Embed text, images, audio, video or PDFs | POST /v1/embeddings |

    | Rerank candidates against a query | POST /v1/rerank |

    | Transcribe a document image (OCR) | POST /v1/chat/completions |

    | Embed a large dataset asynchronously | POST /v1/batch/embeddings |

    | See which models exist and what they cost | GET /v1/models |


    **Authentication.** Send `Authorization: Bearer `. Get a key at https://jina.ai/?sui=apikey. Reader also answers without a key, at a lower rate limit; Search needs one. **EU.** `eu.r.jina.ai` and `eu.s.jina.ai` keep all processing inside the EU. **For LLMs.** `curl docs.jina.ai` returns the meta-prompt, a plain-text guide to these APIs written for coding agents. This reference as Markdown: `curl docs.jina.ai/api.md`. **Rate limits.** r.jina.ai 500 RPM (5k premium), s.jina.ai 100 RPM (1k premium). _Merged from https://api.jina.ai/openapi.json, https://r.jina.ai/openapi.json, https://s.jina.ai/openapi.json. Plain text: https://docs.jina.ai/api.md. Spec: https://docs.jina.ai/openapi.json._


    Best-in-class embeddings, rerankers and document models for multilingual and multimodal search. ## Capabilities


    - **Text embeddings** — dense vectors for semantic search, similarity, clustering and classification, in 100+ languages. - **Multimodal embeddings** — images, video, audio and PDFs embedded into the same space as text, so a query in one modality retrieves another. - **Reranking** — score a query against a candidate set and reorder it; more accurate than embedding similarity, and the usual second stage after it. - **Document OCR** — read a page image and return its content as text or markdown, with tables and layout preserved, over the OpenAI chat completions schema. - **Batch embeddings** — the same embedding models over JSONL, asynchronously, for workloads too large to send inline. ## Authentication


    Every endpoint except `GET /v1/models` requires a key:


    ```

    Authorization: Bearer jina_YOUR_API_KEY

    ```


    Get one at jina.ai/api-dashboard/key-manager. ## Rate limits


    Requests per minute and tokens per minute. Anything over a limit answers `429`. | Endpoint | Free | Paid | Premium |

    |---|---|---|---|

    | `/v1/embeddings` | 500 RPM · 1M TPM | 500 RPM · 10M TPM | 5,000 RPM · 100M TPM |

    | `/v1/rerank` | 500 RPM · 1M TPM | 500 RPM · 10M TPM | 5,000 RPM · 100M TPM |

    | `/v1/chat/completions` | 100 RPM · 500K TPM | 100 RPM · 5M TPM | 1,000 RPM · 50M TPM |


    ## Errors


    Failures carry a `detail`, a `code` from the table below and the `request_id` to quote in a support request. `/v1/chat/completions` is the exception: it answers in OpenAI''s error envelope, with the same code inside it.'
  version: 2026.10.13.1624
servers:
- url: https://api.jina.ai
tags:
- name: Generative Models
  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.'
paths:
  /v1/chat/completions:
    post:
      tags:
      - Generative Models
      summary: Chat Completions
      description: Transcribe a document image. Send the page as an `image_url` content part and the reply is its text; `response_format` with a `json_schema` constrains that to a schema instead.
      operationId: chat_completions_v1_chat_completions_post
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ChatCompletionRequest'
        required: true
      responses:
        '200':
          description: An OpenAI chat completion, or a stream of `chat.completion.chunk` events when `stream` is true.
          content:
            application/json:
              schema: {}
        '400':
          description: 'Bad Request: `INPUT_INVALID_LABELS`, `INPUT_LABEL_LIMIT_EXCEEDED`, `INPUT_MODEL_NOT_FOUND`, `INPUT_TOKEN_LIMIT_EXCEEDED`'
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/OpenAIErrorResponse'
        '401':
          description: 'Unauthorized: `AUTH_INVALID_API_KEY`, `AUTH_INVALID_FORMAT`, `AUTH_MISSING_API_KEY`'
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '403':
          description: 'Forbidden: `AUTHZ_INSUFFICIENT_BALANCE`, `AUTHZ_RESOURCE_LIMIT_EXCEEDED`'
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '404':
          description: 'Not Found: `RESOURCE_NOT_FOUND`'
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/OpenAIErrorResponse'
        '409':
          description: 'Conflict: `CONFLICT_RESOURCE_BUSY`'
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/OpenAIErrorResponse'
        '422':
          description: The request body failed schema validation. `errors` names each field.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '429':
          description: 'Too Many Requests: `RATE_CONCURRENCY_LIMIT_EXCEEDED`, `RATE_IP_LIMIT_EXCEEDED`, `RATE_REQUEST_LIMIT_EXCEEDED`, `RATE_TOKEN_LIMIT_EXCEEDED`'
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '500':
          description: 'Internal Server Error: `INTERNAL_ERROR`'
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/OpenAIErrorResponse'
        '503':
          description: 'Service Unavailable: `SERVICE_UNAVAILABLE`'
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/OpenAIErrorResponse'
        '504':
          description: 'Gateway Timeout: `SERVICE_TIMEOUT`'
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/OpenAIErrorResponse'
      security:
      - HTTPBearer: []
components:
  schemas:
    ErrorResponse:
      properties:
        detail:
          type: string
          title: Detail
          description: Human-readable error message.
          examples:
          - Invalid API key. Verify your API key at https://jina.ai/api-dashboard/key-manager or generate a new one.
        code:
          anyOf:
          - type: string
          - type: 'null'
          title: Code
          description: Machine-readable error code, for programmatic handling.
          examples:
          - AUTH_INVALID_API_KEY
        request_id:
          anyOf:
          - type: string
          - type: 'null'
          title: Request Id
          description: Identifier for this request, quote it in support requests.
          examples:
          - 03f58cd9da22fabf
        errors:
          anyOf:
          - items:
              $ref: '#/components/schemas/FieldError'
            type: array
          - type: 'null'
          title: Errors
          description: Per-field detail. Present on 422 only; `detail` summarises it.
      type: object
      required:
      - detail
      title: ErrorResponse
      description: Failure shape for every endpoint except `/v1/chat/completions`.
    OpenAIErrorResponse:
      properties:
        error:
          $ref: '#/components/schemas/OpenAIError'
      type: object
      required:
      - error
      title: OpenAIErrorResponse
      description: Failure shape for `/v1/chat/completions`, so OpenAI clients parse it.
    ResponseFormatText:
      properties:
        type:
          type: string
          const: text
          title: Type
      type: object
      required:
      - type
      title: ResponseFormatText
    JSONSchemaSpec:
      properties:
        name:
          type: string
          title: Name
        schema:
          anyOf:
          - additionalProperties: true
            type: object
          - type: 'null'
          title: Schema
      type: object
      required:
      - name
      title: JSONSchemaSpec
    FieldError:
      properties:
        field:
          type: string
          title: Field
          description: Path to the field, e.g. `body -> input -> 0`.
        message:
          type: string
          title: Message
          description: Why the value was rejected.
        type:
          type: string
          title: Type
          description: Validator that rejected it, e.g. `string_type`.
        input:
          anyOf:
          - {}
          - type: 'null'
          title: Input
          description: The rejected value. Long strings are truncated and containers dropped.
      type: object
      required:
      - field
      - message
      - type
      title: FieldError
      description: One rejected field, as carried in a 422.
    ImageURL:
      properties:
        url:
          type: string
          title: Url
          description: An `http(s)` URL or a `data:image/...;base64,` URI.
      type: object
      required:
      - url
      title: ImageURL
    ResponseFormatJSONSchema:
      properties:
        type:
          type: string
          const: json_schema
          title: Type
        json_schema:
          $ref: '#/components/schemas/JSONSchemaSpec'
      type: object
      required:
      - type
      - json_schema
      title: ResponseFormatJSONSchema
    ChatCompletionRequest:
      properties:
        messages:
          items:
            $ref: '#/components/schemas/ChatMessage'
          type: array
          minItems: 1
          title: Messages
        model:
          type: string
          const: jina-ocr-v1
          title: Model
          description: The model to use.
        stream:
          type: boolean
          title: Stream
          default: false
        stream_options:
          anyOf:
          - $ref: '#/components/schemas/StreamOptions'
          - type: 'null'
        max_completion_tokens:
          anyOf:
          - type: integer
            minimum: 1
          - type: 'null'
          title: Max Completion Tokens
        temperature:
          anyOf:
          - type: number
            maximum: 2
            minimum: 0
          - type: 'null'
          title: Temperature
        top_p:
          anyOf:
          - type: number
            maximum: 1
            minimum: 0
          - type: 'null'
          title: Top P
        presence_penalty:
          anyOf:
          - type: number
            maximum: 2
            minimum: -2
          - type: 'null'
          title: Presence Penalty
        frequency_penalty:
          anyOf:
          - type: number
            maximum: 2
            minimum: -2
          - type: 'null'
          title: Frequency Penalty
        stop:
          anyOf:
          - type: string
          - items:
              type: string
            type: array
          - type: 'null'
          title: Stop
        seed:
          anyOf:
          - type: integer
          - type: 'null'
          title: Seed
        logprobs:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Logprobs
        top_logprobs:
          anyOf:
          - type: integer
            maximum: 20
            minimum: 0
          - type: 'null'
          title: Top Logprobs
        logit_bias:
          anyOf:
          - additionalProperties:
              type: number
            type: object
          - type: 'null'
          title: Logit Bias
        response_format:
          anyOf:
          - oneOf:
            - $ref: '#/components/schemas/ResponseFormatText'
            - $ref: '#/components/schemas/ResponseFormatJSONObject'
            - $ref: '#/components/schemas/ResponseFormatJSONSchema'
            discriminator:
              propertyName: type
              mapping:
                json_object: '#/components/schemas/ResponseFormatJSONObject'
                json_schema: '#/components/schemas/ResponseFormatJSONSchema'
                text: '#/components/schemas/ResponseFormatText'
          - type: 'null'
          title: Response Format
      type: object
      required:
      - messages
      - model
      title: ChatCompletionRequest
      description: The public request body. Every field here reaches the engine.
    ChatMessage:
      properties:
        role:
          type: string
          enum:
          - system
          - developer
          - user
          - assistant
          title: Role
        content:
          anyOf:
          - type: string
          - items:
              oneOf:
              - $ref: '#/components/schemas/TextContentPart'
              - $ref: '#/components/schemas/ImageContentPart'
              discriminator:
                propertyName: type
                mapping:
                  image_url: '#/components/schemas/ImageContentPart'
                  text: '#/components/schemas/TextContentPart'
            type: array
          - type: 'null'
          title: Content
      type: object
      required:
      - role
      title: ChatMessage
    StreamOptions:
      properties:
        include_usage:
          type: boolean
          title: Include Usage
          description: 'Report token usage in the stream. When set, every chunk carries `usage: null` and a final chunk carries the totals. When unset, no chunk mentions usage and the final chunk is not sent at all.'
          default: false
      type: object
      title: StreamOptions
    ImageContentPart:
      properties:
        type:
          type: string
          const: image_url
          title: Type
        image_url:
          $ref: '#/components/schemas/ImageURL'
      type: object
      required:
      - type
      - image_url
      title: ImageContentPart
    TextContentPart:
      properties:
        type:
          type: string
          const: text
          title: Type
        text:
          type: string
          title: Text
      type: object
      required:
      - type
      - text
      title: TextContentPart
    ResponseFormatJSONObject:
      properties:
        type:
          type: string
          const: json_object
          title: Type
      type: object
      required:
      - type
      title: ResponseFormatJSONObject
    OpenAIError:
      properties:
        message:
          type: string
          title: Message
          description: Human-readable error message.
        type:
          type: string
          title: Type
          description: OpenAI's error class, e.g. `invalid_request_error`.
          examples:
          - invalid_request_error
        param:
          anyOf:
          - type: string
          - type: 'null'
          title: Param
          description: The request field at fault, when one is named.
        code:
          anyOf:
          - type: string
          - type: 'null'
          title: Code
          examples:
          - INPUT_MODEL_NOT_FOUND
        request_id:
          anyOf:
          - type: string
          - type: 'null'
          title: Request Id
          examples:
          - 03f58cd9da22fabf
      type: object
      required:
      - message
      - type
      title: OpenAIError
      description: 'OpenAI''s error object. Our `code` and `request_id` ride inside it because

        the OpenAI SDK keeps `body["error"]` and discards everything beside it.'
  securitySchemes:
    HTTPBearer:
      type: http
      scheme: bearer
x-tagGroups:
- name: Reader API (r.jina.ai)
  tags:
  - Reader
- name: Search API (s.jina.ai)
  tags:
  - Search
- name: Search Foundation API (api.jina.ai)
  tags:
  - Model List
  - Search Foundation Models
  - Generative Models
  - Batch Embeddings