Name: Jina-CLIP v2 API: Multilingual Text and Image Embeddings
Brand: magicapi
SKU: api-magicapi-multilingual-image-embedding-api-zsxkib-jina-clip-v2
Availability: InStock
Author: API Market

Shashank Agarwal

# 🌍 Multilingual Text and Image Embedding API (Jina AI Jina-CLIP v2)

## Overview
Jina-CLIP v2 is a multimodal embedding model from Jina AI. Its developer describes it as a 0.9B model with multilingual support for 89 languages, 512x512 image resolution and Matryoshka representations. This listing is packaged by zsxkib.

Send a `text`, an `image`, or both. The API returns a list of embeddings: when you send both, the text embedding is first and the image embedding second. `embedding_dim` sets the vector length from 64 to 1024, and `output_format` returns each vector as a base64 string (default) or as a list of numbers.

## Features
- **Text and image in one space**: compare text vectors with image vectors directly for text-to-image and image-to-text search.
- **Multilingual text**: its developer describes support for 89 languages; `text` can be up to 8192 tokens.
- **Adjustable length**: `embedding_dim` from 64 (default) to 1024. Shorter vectors (Matryoshka representations) need less storage.
- **Output format**: `base64` (default) for compact strings or `array` for plain lists of numbers.

## Use Cases
1. **Text-to-image search**: find images that match a query written in any supported language.
2. **Multilingual product search**: match product photos and descriptions across languages.
3. **Image deduplication and clustering**: compare image vectors to group similar pictures.
4. **Retrieval for AI apps**: store text and image vectors in a vector database for retrieval.

## Visual Examples
### Example Input
The text "A cute fox" and one image, with `embedding_dim` 64 and `output_format` `base64`:

![Jina-CLIP v2 example input image](https://blog.api.market/wp-content/uploads/2026/10/jina-clip-v2-input-api-market.jpg)

```json
{
  "text": "A cute fox",
  "image": "https://blog.api.market/wp-content/uploads/2026/10/jina-clip-v2-input-api-market.jpg",
  "embedding_dim": 64,
  "output_format": "base64"
}
```

### Example Output
Two base64 strings: the text embedding first, then the image embedding. Each decodes to 256 bytes (64 values of 4 bytes).

```json
[
  "uAhEvoVqwDyFtDg+aP6rvHA6xD1iKvY9dBz/vBJCXz4xFSY92mw/vl3zSz5xY0e8ugd0vmo/Ij4X/N09yuLcOxs+nb0fJcU8CgtDPqJKKr3mXLO9Zm6DvTobtT1Evk++mzNqvLbZJT6YEDw+ngaOvXOaab2gofQ8qrAGvkkrgD67Dws+6nKbvnk34L2bAvI9FlNKOsW6W73YY5K+bVmkvWj2Lj3TyUK7EYxAPj4/4Ly0mY294LcePeQggTzc89e9gMUNvpyvujtA/hi9O40APAwixL25WwM+b7jzO9cHvj0gboc9bxyUvTXXXL0VoQQ9cwQnPUpHHj5pH7i9eRNgvg==",
  "E0ezvaPVFT73Nr48lDgFPtWAFb6CIYg8XnjcvccZsrrgG5+90lnwvHh+hTxwysO9Zp9IvplaKT4WLk+7A/GBPfyIFz1cUqY96L8iPjmp/r2x3yO9LzaFvbU/qr0fUqq9wCvqPdKL0L2KiGy9anewvTYRsrwF1Q8+oU9Zve6PMj7iHWc9z95GviG+YL6ooeI9wt0JPFc2iL2XbVo8E28LPlesBz6K5s49Qo07PkhPk70079e9WE8nPhvcMT2IF2++6EXzPXwqlr3IdD6+X/XwPMuBKr6l4Qa+Evs3PVtWLD2xoiK9rcA0PvrGib6/WZ2+4IkxvRUbFj7QrzW+Gug+vg=="
]
```

## Input Parameters
| Field | Type | Required | Default | Allowed values | Description |
| --- | --- | --- | --- | --- | --- |
| `text` | string | No | none |  | Text to embed (up to 8192 tokens). If both text and image are sent, the text embedding is first in the returned list. |
| `image` | string (URL) | No | none |  | Image URL to embed (optimal size 512x512). If both text and image are sent, the image embedding is second in the returned list. |
| `embedding_dim` | integer | No | `64` | `64` to `1024` | Output embedding dimension (Matryoshka dimension), 64 to 1024 |
| `output_format` | string | No | `base64` | `base64`, `array` | Format of each embedding in the output: a base64 string or a list of numbers |

## Pricing
- **Pay As You Go (PAYG) pricing**: you only pay for what you use.
- **Price**: $0.001 per API unit.
- **1 API unit = 1 successful request with up to 4 seconds of processing.** A request that takes longer is billed one more unit for each started block of 4 seconds (for example, 9 seconds of processing is 3 units, $0.003).
- A text and an image together usually finish within one unit.
- **Example cost**: the example request above took 1.5 seconds of processing, so it used 1 API unit and cost $0.001.
- **Failed or cancelled predictions are not billed.**
- **GET requests to check prediction status** are free and don't count toward API unit usage.
- **No monthly subscription fee.**

## API Documentation

### Base URL
All API requests go to: `https://prod.api.market/api/v1/magicapi/multilingual-image-embedding-api-zsxkib-jina-clip-v2`

### Authentication
Send your api.market API key in the `x-api-market-key` header:
```
x-api-market-key: YOUR_API_MARKET_KEY
```

### Asynchronous Processing
**IMPORTANT**: This API is asynchronous. The flow is:
1. Send a POST request to `/predictions`. A successful request returns **201 Created** with a prediction `id` and a `status` of `starting` or `processing`.
2. Poll GET `/predictions/{id}` with that ID.
3. Keep polling while `status` is `starting` or `processing`.
4. Stop when `status` is `succeeded` (read `output`), `failed` or `canceled` (read `error`).

A polling interval of 1 second and an overall timeout of 600 seconds (10 minutes) work well.

### Endpoints

#### Create a Prediction
```bash
curl -X POST "https://prod.api.market/api/v1/magicapi/multilingual-image-embedding-api-zsxkib-jina-clip-v2/predictions" \
  -H "Content-Type: application/json" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY" \
  -d '{
    "version": "5050c3108bab23981802011a3c76ee327cc0dbfdd31a2f4ef1ee8ef0d3f0b448",
    "input": {
      "text": "A cute fox",
      "image": "https://blog.api.market/wp-content/uploads/2026/10/jina-clip-v2-input-api-market.jpg",
      "embedding_dim": 64,
      "output_format": "base64"
    }
  }'
```

Response (201 Created):
```json
{
  "id": "rjr4hapmshrga0d1d1d93wa6n8",
  "version": "5050c3108bab23981802011a3c76ee327cc0dbfdd31a2f4ef1ee8ef0d3f0b448",
  "status": "starting",
  "created_at": "2026-10-23T10:42:25.799Z"
}
```

#### Check Prediction Status
```bash
curl -X GET "https://prod.api.market/api/v1/magicapi/multilingual-image-embedding-api-zsxkib-jina-clip-v2/predictions/{id}" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY"
```

Response when the prediction has finished (200 OK):
```json
{
  "id": "rjr4hapmshrga0d1d1d93wa6n8",
  "status": "succeeded",
  "output": [
    "uAhEvoVqwDyFtDg+aP6rvHA6xD1iKvY9dBz/vBJCXz4xFSY92mw/vl3zSz5xY0e8ugd0vmo/Ij4X/N09yuLcOxs+nb0fJcU8CgtDPqJKKr3mXLO9Zm6DvTobtT1Evk++mzNqvLbZJT6YEDw+ngaOvXOaab2gofQ8qrAGvkkrgD67Dws+6nKbvnk34L2bAvI9FlNKOsW6W73YY5K+bVmkvWj2Lj3TyUK7EYxAPj4/4Ly0mY294LcePeQggTzc89e9gMUNvpyvujtA/hi9O40APAwixL25WwM+b7jzO9cHvj0gboc9bxyUvTXXXL0VoQQ9cwQnPUpHHj5pH7i9eRNgvg==",
    "E0ezvaPVFT73Nr48lDgFPtWAFb6CIYg8XnjcvccZsrrgG5+90lnwvHh+hTxwysO9Zp9IvplaKT4WLk+7A/GBPfyIFz1cUqY96L8iPjmp/r2x3yO9LzaFvbU/qr0fUqq9wCvqPdKL0L2KiGy9anewvTYRsrwF1Q8+oU9Zve6PMj7iHWc9z95GviG+YL6ooeI9wt0JPFc2iL2XbVo8E28LPlesBz6K5s49Qo07PkhPk70079e9WE8nPhvcMT2IF2++6EXzPXwqlr3IdD6+X/XwPMuBKr6l4Qa+Evs3PVtWLD2xoiK9rcA0PvrGib6/WZ2+4IkxvRUbFj7QrzW+Gug+vg=="
  ],
  "error": null,
  "created_at": "2026-10-23T10:42:25.799Z",
  "started_at": "2026-10-23T10:42:25.821Z",
  "completed_at": "2026-10-23T10:42:27.301Z"
}
```

`output` is a list of embeddings: the text embedding first and the image embedding second when you send both. Each embedding is a base64 string (`output_format` `base64`) or a list of `embedding_dim` numbers (`output_format` `array`).

### Status Codes
- **201 Created**: prediction created (POST `/predictions`). This is the normal success response.
- **200 OK**: prediction details returned (GET `/predictions/{id}`).
- **400 Bad Request**: invalid input, for example an `embedding_dim` outside 64 to 1024 or an `output_format` other than `base64` or `array`.
- **401 Unauthorized**: missing or invalid API key.
- **404 Not Found**: no prediction with that ID.
- **429 Too Many Requests**: rate limit exceeded.
- **500 Internal Server Error** or **503 Service Unavailable**: temporary server problem; retry later.

## Rate Limits
All plans allow 10 requests per second. Requests above that return `429 Too Many Requests`; back off before retrying and honour any `Retry-After` header. Polling a prediction with GET is free but still counts toward the per-second limit, so poll every 1 to 5 seconds rather than in a tight loop.

## Error Handling
- Check the HTTP status code of every request and read the response body for the error message.
- A prediction can also end with `status` set to `failed`; the `error` field then explains why. Failed predictions are not billed.
- Retry 429, 500 and 503 responses with exponential backoff. Fix the input before retrying a 400.

## Implementation Guide
### Example Code

#### JavaScript
```javascript
const apiKey = "YOUR_API_MARKET_KEY";
const baseUrl = "https://prod.api.market/api/v1/magicapi/multilingual-image-embedding-api-zsxkib-jina-clip-v2";

async function createAndWaitForPrediction(input) {
  const response = await fetch(`${baseUrl}/predictions`, {
    method: "POST",
    headers: {
      "Content-Type": "application/json",
      "x-api-market-key": apiKey
    },
    body: JSON.stringify({ version: "5050c3108bab23981802011a3c76ee327cc0dbfdd31a2f4ef1ee8ef0d3f0b448", input })
  });

  if (response.status !== 201) {
    throw new Error(`API error: ${response.status} ${await response.text()}`);
  }

  const prediction = await response.json();
  return pollForResults(prediction.id);
}

const delay = (ms) => new Promise((resolve) => setTimeout(resolve, ms));

async function pollForResults(predictionId) {
  const maxTimeout = 600000;
  const pollInterval = 1000;
  const startTime = Date.now();

  while (Date.now() - startTime < maxTimeout) {
    const response = await fetch(`${baseUrl}/predictions/${predictionId}`, {
      headers: { "x-api-market-key": apiKey }
    });

    if (!response.ok) {
      throw new Error(`API error: ${response.status} ${await response.text()}`);
    }

    const prediction = await response.json();

    if (prediction.status === "succeeded") {
      return prediction.output;
    }

    if (prediction.status === "failed" || prediction.status === "canceled") {
      throw new Error(`Prediction ${prediction.status}: ${prediction.error || "Unknown error"}`);
    }

    await delay(pollInterval);
  }

  throw new Error("Prediction timed out after 10 minutes");
}

createAndWaitForPrediction({
  "text": "A cute fox",
  "image": "https://blog.api.market/wp-content/uploads/2026/10/jina-clip-v2-input-api-market.jpg",
  "embedding_dim": 64,
  "output_format": "base64"
}).then((output) => console.log(output));
```

#### Python
```python
import time
import requests

API_KEY = "YOUR_API_MARKET_KEY"
BASE_URL = "https://prod.api.market/api/v1/magicapi/multilingual-image-embedding-api-zsxkib-jina-clip-v2"


def create_and_wait_for_prediction(input_data):
    headers = {"Content-Type": "application/json", "x-api-market-key": API_KEY}
    response = requests.post(
        f"{BASE_URL}/predictions",
        headers=headers,
        json={"version": "5050c3108bab23981802011a3c76ee327cc0dbfdd31a2f4ef1ee8ef0d3f0b448", "input": input_data},
    )

    if response.status_code != 201:
        raise Exception(f"API error: {response.status_code} {response.text}")

    return poll_for_results(response.json()["id"])


def poll_for_results(prediction_id):
    max_timeout = 600
    poll_interval = 1
    headers = {"x-api-market-key": API_KEY}
    start_time = time.time()

    while time.time() - start_time < max_timeout:
        response = requests.get(f"{BASE_URL}/predictions/{prediction_id}", headers=headers)

        if response.status_code != 200:
            raise Exception(f"API error: {response.status_code} {response.text}")

        prediction = response.json()

        if prediction["status"] == "succeeded":
            return prediction["output"]

        if prediction["status"] in ("failed", "canceled"):
            raise Exception(f"Prediction {prediction['status']}: {prediction.get('error') or 'Unknown error'}")

        time.sleep(poll_interval)

    raise Exception("Prediction timed out after 10 minutes")


print(create_and_wait_for_prediction({
    "text": "A cute fox",
    "image": "https://blog.api.market/wp-content/uploads/2026/10/jina-clip-v2-input-api-market.jpg",
    "embedding_dim": 64,
    "output_format": "base64"
}))
```

## FAQ
- **Can I send only text or only an image?**
  - Yes. Both fields are optional; send one or both. With both, the output list has the text embedding first and the image embedding second.
- **How do I read the base64 output?**
  - Each string is the raw bytes of one vector. In the example, each 64-value vector decodes to 256 bytes (4 bytes per value). Set `output_format` to `array` to get plain lists of numbers instead.
- **Which `embedding_dim` should I use?**
  - 64 (the default) is the most compact; values up to 1024 keep more detail. Use the same value for everything you compare.
- **Which languages are supported?**
  - Its developer describes support for 89 languages. Text and images share one space, so a query in one language can match images and texts in others.
- **How is a request billed?**
  - $0.001 per request for up to 4 seconds of processing, plus one unit for each further started block of 4 seconds. The example with one text and one image took 1.5 seconds and cost $0.001.
- **Is the 201 response from POST an error?**
  - No. 201 Created means the prediction was accepted. Use the returned `id` to poll GET `/predictions/{id}` until `status` is `succeeded`, `failed` or `canceled`.
- **What if my prediction fails?**
  - Failed predictions are not billed. Read the `error` field, adjust the input and try again.

## Contact Us
If you have any questions, reach out to us through the chat on the bottom right of the page. You can also email our support team at hello@magicapi.com.


Get text and image embeddings in one shared space with Jina-CLIP v2: multilingual text up to 8192 tokens, 64 to 1024 dimensions. Pay as you go, no monthly fee.