Jina AI Search Foundation APIs

https://docs.jina.ai/
Admin
Jina AI Search Foundation APIs offer a comprehensive suite of tools for LLMs to perform tasks such...
Tokens:4,808
Snippets:35
Trust Score:10
Update:2 months ago
Show doc for...
Tokens:
Raw
### GET /v1/batch/{batch_id}

Source: https://docs.jina.ai

Poll the status of a submitted batch job.

```APIDOC
## GET /v1/batch/{batch_id}

### Description
Check the status of a batch job using its batch_id.

### Method
GET

### Endpoint
https://api.jina.ai/v1/batch/{batch_id}

### Parameters
#### Path Parameters
- **batch_id** (string) - Required - The ID of the batch job

### Response
#### Success Response (200)
- **batch_id** (string) - The batch ID
- **status** (string) - Status (submitted, processing, completed, failed, cancelled)
- **stats** (object) - Statistics of the job
- **output_url** (string) - URL to download the output
```

--------------------------------

### Fetch Jina AI Documentation via cURL

Source: https://docs.jina.ai

Commands to retrieve the programmatic documentation content for specific or default versions.

```bash
curl docs.jina.ai/v13
```

```bash
curl docs.jina.ai
```

--------------------------------

### Jina AI Meta-Prompt System Instructions

Source: https://docs.jina.ai

The core system prompt defining the behavior, model versions, and API constraints for AI agents.

```text
You are an AI engineer designed to help users use Jina AI Search Foundation API's for their specific use case.

It is 2026. Jina AI's latest embedding models are jina-embeddings-v5-text-nano and jina-embeddings-v5-text-small. The latest reranker is jina-reranker-v3.5.

# Core principles

0. Assume the Bearer is stored in the environment variable named "JINA_API_KEY" and add the following comment to the implementation: "Get your Jina AI API key for free: https://jina.ai/?sui=apikey".
1. Use the simplest solution possible (use single API's whenever possible, do not overcomplicate things);
2. Answer "can't do" for tasks outside the scope of Jina AI Search Foundation;
3. Choose built-in features over custom implementations whenever possible;
4. Leverage multimodal models when needed;
5. You must use the Jina APIs for the implementation;
6. Never decline an implementation because of its complexity;
7. Generate production-ready code that follows exactly the requirements;
8. Never use placeholder data;
9. For every request to any of the Jina APIs, you must include the header -H "Accept: application/json" to specify that the response should be in JSON format;
```

--------------------------------

### POST https://r.jina.ai/

Source: https://docs.jina.ai

Retrieves and parses content from a specified URL, returning it in a format optimized for LLMs.

```APIDOC
## POST https://r.jina.ai/

### Description
Retrieves and parses content from a URL in a format optimized for downstream tasks like LLMs. Use https://eu.r.jina.ai/ for EU-based processing.

### Method
POST

### Endpoint
https://r.jina.ai/

### Parameters
#### Request Body
- **url** (string) - Required - The URL to retrieve and parse.
- **viewport** (object) - Optional - Sets browser viewport dimensions (width, height).
- **injectPageScript** (string) - Optional - Executes preprocessing JS code.

### Response
#### Success Response (200)
- **data.content** (string) - The parsed content of the page.
- **data.links** (array) - Extracted links (if requested).
- **data.images** (array) - Extracted images (if requested).
```

--------------------------------

### POST https://s.jina.ai/

Source: https://docs.jina.ai

Performs a web search based on the provided query and configuration headers.

```APIDOC
## POST https://s.jina.ai/

### Description
Search the web for information and return results in a format optimized for downstream tasks like LLMs and other applications.

### Method
POST

### Endpoint
https://s.jina.ai/ (or https://eu.s.jina.ai/ for EU jurisdiction)

### Parameters
#### Headers
- **Authorization** (string) - Required - Bearer $JINA_API_KEY
- **Content-Type** (string) - Required - application/json
- **Accept** (string) - Required - application/json
- **X-Site** (string) - Optional - Limit search to a specific domain
- **X-With-Links-Summary** (string) - Optional - 'all' or 'true' to gather links
- **X-With-Images-Summary** (string) - Optional - 'all' or 'true' to gather images
- **X-Retain-Images** (string) - Optional - 'none' to remove images
- **X-No-Cache** (string) - Optional - 'true' to bypass cache
- **X-With-Generated-Alt** (string) - Optional - 'true' to generate image captions
- **X-Respond-With** (string) - Optional - 'no-content' to exclude page content
- **X-With-Favicon** (string) - Optional - 'true' to include favicon
- **X-Return-Format** (string) - Optional - 'markdown', 'html', 'text', 'screenshot', or 'pageshot'
- **X-Engine** (string) - Optional - 'browser' or 'direct'
- **X-With-Favicons** (string) - Optional - 'true' to fetch favicons for SERP URLs
- **X-Timeout** (number) - Optional - Max time in seconds to wait for page load
- **X-Set-Cookie** (string) - Optional - Custom cookie settings
- **X-Proxy-Url** (string) - Optional - Proxy URL to access targets
- **X-Locale** (string) - Optional - Browser locale

#### Request Body
- **q** (string) - Required - The search query
- **gl** (string) - Optional - Two-letter country code
- **location** (string) - Optional - Origin location for the search
- **hl** (string) - Optional - Two-letter language code
- **num** (number) - Optional - Maximum results returned
- **page** (number) - Optional - Result offset for pagination

### Request Example
{
  "q": "Jina AI features",
  "gl": "US"
}
```

--------------------------------

### POST /v1/batch/embeddings

Source: https://docs.jina.ai

Submit a batch job for asynchronous embedding of large volumes of text.

```APIDOC
## POST /v1/batch/embeddings

### Description
Submit a batch job to asynchronously embed large volumes of text. Returns a batch_id immediately.

### Method
POST

### Endpoint
https://api.jina.ai/v1/batch/embeddings

### Parameters
#### Request Body
- **model** (string) - Required - Identifier of the model to use (jina-embeddings-v5-text-small, jina-embeddings-v5-text-nano)
- **input** (array) - Optional - Array of input strings (up to 10,000 items)
- **input_file** (string) - Optional - GCS URI to a JSONL file (up to 50,000 lines)
- **task** (string) - Optional - Task type (retrieval.query, retrieval.passage, text-matching, classification, clustering)
- **dimensions** (integer) - Optional - Truncates output embeddings to the specified size
- **normalized** (boolean) - Optional - If true, embeddings are normalized to unit L2 norm

### Request Example
{
  "model": "jina-embeddings-v5-text-small",
  "input": ["text1", "text2"]
}

### Response
#### Success Response (202)
- **batch_id** (string) - Unique identifier for the batch job
- **status** (string) - Current status of the job
- **created_at** (integer) - Timestamp of creation
```

--------------------------------

### POST /rerank (Multimodal Model)

Source: https://docs.jina.ai

Request body schema for the jina-reranker-m0 multimodal reranker model.

```APIDOC
## POST /rerank

### Description
Reranks a list of text and/or image documents based on a provided query using the jina-reranker-m0 model.

### Request Body
- **model** (string) - Required - Must be set to 'jina-reranker-m0'.
- **query** (string, TextDoc, or image) - Required - The search query (string, TextDoc, or image URL/base64).
- **documents** (array) - Required - A list of objects with keys 'text' and/or 'image'.
- **top_n** (integer) - Optional - The number of most relevant documents to return.
- **return_documents** (boolean) - Optional - If true, returns index, text, and score; if false, returns only index and score.
```

--------------------------------

### POST /embeddings (jina-embeddings-v3 or jina-clip-v2)

Source: https://docs.jina.ai

Generates embeddings using jina-embeddings-v3 or jina-clip-v2 models.

```APIDOC
## POST /embeddings

### Description
Generates embeddings for input strings or objects using jina-embeddings-v3 or jina-clip-v2 models.

### Request Body
- **model** (string) - Required - Identifier of the model (jina-clip-v2, jina-embeddings-v3).
- **input** (array) - Required - Array of input strings or objects to be embedded.
- **embedding_type** (string or array) - Optional - The format of the returned embeddings (float, base64, binary, ubinary).
- **task** (string) - Optional - Specifies the intended downstream application (retrieval.query, retrieval.passage, text-matching, classification, separation).
- **dimensions** (integer) - Optional - Truncates output embeddings to the specified size.
- **normalized** (boolean) - Optional - If true, embeddings are normalized to unit L2 norm.
- **late_chunking** (boolean) - Optional - If true, treats input as a single input for late chunking.
- **truncate** (boolean) - Optional - If true, automatically drops tail exceeding context length.
```

--------------------------------

### POST /embeddings (jina-code-embeddings)

Source: https://docs.jina.ai

Generates code embeddings using jina-code-embeddings-0.5b or jina-code-embeddings-1.5b models.

```APIDOC
## POST /embeddings

### Description
Generates code embeddings for input strings using jina-code-embeddings-0.5b or jina-code-embeddings-1.5b models.

### Request Body
- **model** (string) - Required - Identifier of the model (jina-code-embeddings-0.5b, jina-code-embeddings-1.5b).
- **input** (array) - Required - Array of input strings to be embedded.
- **embedding_type** (string or array) - Optional - The format of the returned embeddings (float, base64, binary, ubinary).
- **task** (string) - Optional - Specifies the intended downstream application (nl2code.query, nl2code.passage, code2code.query, code2code.passage, code2nl.query, code2nl.passage, code2completion.query, code2completion.passage, qa.query, qa.passage).
- **dimensions** (integer) - Optional - Truncates output embeddings to the specified size.
- **truncate** (boolean) - Optional - If true, automatically drops tail exceeding context length.
```

--------------------------------

### POST /rerank (Text Models)

Source: https://docs.jina.ai

Request body schema for text-based reranker models including jina-reranker-v3.5, jina-reranker-v3, jina-reranker-v2-base-multilingual, and jina-colbert-v2.

```APIDOC
## POST /rerank

### Description
Reranks a list of text documents based on a provided query using specified Jina AI text models.

### Request Body
- **model** (string) - Required - Identifier of the model to use (jina-reranker-v3.5, jina-reranker-v3, jina-reranker-v2-base-multilingual, jina-colbert-v2).
- **query** (string or TextDoc) - Required - The search query.
- **documents** (array) - Required - A list of text strings or TextDocs to rerank.
- **top_n** (integer) - Optional - The number of most relevant documents to return.
- **return_documents** (boolean) - Optional - If true, returns index, text, and score; if false, returns only index and score.
```

--------------------------------

### POST /embeddings (jina-embeddings-v4)

Source: https://docs.jina.ai

Generates embeddings using the jina-embeddings-v4 model.

```APIDOC
## POST /embeddings

### Description
Generates embeddings for input strings or objects using the jina-embeddings-v4 model.

### Request Body
- **model** (string) - Required - Identifier of the model to use (jina-embeddings-v4).
- **input** (array) - Required - Array of input strings or objects to be embedded.
- **embedding_type** (string or array) - Optional - The format of the returned embeddings (float, base64, binary, ubinary).
- **task** (string) - Optional - Specifies the intended downstream application (retrieval.query, retrieval.passage, text-matching, code.query, code.passage).
- **dimensions** (integer) - Optional - Truncates output embeddings to the specified size.
- **late_chunking** (boolean) - Optional - If true, treats input as a single input for late chunking.
- **truncate** (boolean) - Optional - If true, automatically drops tail exceeding context length.
- **return_multivector** (boolean) - Optional - If true, returns NxD multi-vector embeddings.
```

--------------------------------

### POST https://api.jina.ai/v1/embeddings

Source: https://docs.jina.ai

Converts input text into fixed-length vectors using specified embedding models.

```APIDOC
## POST https://api.jina.ai/v1/embeddings

### Description
Convert text into fixed-length vectors for use in semantic search, similarity matching, or clustering.

### Method
POST

### Endpoint
https://api.jina.ai/v1/embeddings

### Parameters
#### Request Body
- **model** (string) - Required - Identifier of the model to use (e.g., jina-embeddings-v5-text-small, jina-embeddings-v5-text-nano).
- **input** (array) - Required - Array of input strings to be embedded.
- **embedding_type** (string or array) - Optional - The format of the returned embeddings (float, base64, binary, ubinary).
- **task** (string) - Optional - Specifies the intended downstream application (retrieval.query, retrieval.passage, text-matching, classification, clustering).
- **dimensions** (integer) - Optional - Truncates output embeddings to the specified size.
- **normalized** (boolean) - Optional - If true, embeddings are normalized to unit L2 norm.
- **late_chunking** (boolean) - Optional - If true, concatenates all sentences in input and treats as a single input for late chunking.
- **truncate** (boolean) - Optional - If true, automatically drops the tail that extends beyond the maximum context length.

### Request Example
{
  "model": "jina-embeddings-v5-text-small",
  "input": ["Your text here"]
}
```

--------------------------------

### POST /v1/rerank

Source: https://docs.jina.ai

Refine search results using a reranker model.

```APIDOC
## POST /v1/rerank

### Description
Find the most relevant search results by reranking candidates against a query.

### Method
POST

### Endpoint
https://api.jina.ai/v1/rerank

### Request Example
{
  "model": "jina-reranker-v3.5",
  "query": "What is Jina AI?",
  "documents": ["Jina AI is a search foundation company.", "Jina AI provides embedding models."]
}
```
Tokens:
Raw