Embeddings

For detailed information on our training processes, data sources, and evaluations, please refer to our technical report available on arXiv.

Jina CLIP jina-clip-v1 is the latest multimodal embedding model that supports text-text, text-image, image-image, and image-text retrieval tasks. Unlike OpenAI CLIP model that falls short on text-text search, Jina CLIP is trained to be your text retriever. You can read more about it from our tech report.

Our models support English, German, Spanish, Chinese, various programming languages and images. For more details, please refer to our publication on bilingual models.

Our models allow for an input length of up to 8192 tokens, which is significantly higher than most other models. A token can range from a single character, like 'a', to an entire word, such as 'apple'. The total number of characters that can be input depends on the length and complexity of the words used. This extended input capability enables our jina-embeddings-v2 models to perform more comprehensive text analysis and achieve higher accuracy in context understanding, especially for extensive textual data.

A single API call can process up to 2048 sentences or texts, facilitating extensive text analysis in one request.

You can use either url or bytes in the input field of the API request. For url, provide the URL of the image you want to process. For bytes, encode the image in base64 format and include it in the request. The model will return the embeddings of the image in the response.

According to the MTEB Leaderboard, our Base model competes closely with OpenAI’s text-embedding-ada-002, exhibiting comparable performance on average. Furthermore, our Base model excels in several tasks, including classification, pair-classification, re-ranking, and summarization, outperforming OpenAI’s model.

The transition is streamlined, as our API endpoint, https://api.jina.ai/v1/embeddings, matches the input and output JSON schemas of OpenAI’s text-embeddings-ada-002 model. This compatibility ensures users can easily replace the OpenAI model with ours when using OpenAI’s endpoint.

The tokens are calculated based on the text length and image size. For text in the request, tokens are counted in the standard way. For image in the request, the following steps are conducted: 1. Tile Size: Each image is divided into tiles of size 224x224 pixels. 2. Coverage: The number of tiles required to completely cover the input image is calculated. Even if the image dimensions are not perfectly divisible by 224, we will count partial tiles as full tiles. 3. Total Tiles: The total number of tiles covering the image determines the cost. For instance, if an image is 500x500 pixels, it would be covered by 3x3 tiles, resulting in 9 tiles. 4. Cost Calculation: Each tile contributes to the final cost of processing the image. The cost per tile is 1000 tokens. Example: For an image with dimensions 500x500 pixels: • The image is divided into 224x224 pixel tiles. • The total number of tiles required is 3 (horizontal) x 3 (vertical) = 9 tiles. • The cost will be 9*1000 = 9000 tokens

Yes, jina-clip-v1 can embed both images and texts. Embedding models on more modalities will be announced soon!

For inquiries about fine-tuning our models with specific data, please contact us to discuss your requirements. We are open to exploring how our models can be adapted to meet your needs.

Yes, our services are available on the AWS marketplace, and we are in the process of expanding to Azure and GCP marketplaces. If you have particular requirements, please contact us at sales AT jina.ai.

Yes, the same API key is valid for all search foundation products from Jina AI. This includes the embedding, reranking, reader and fine-tuning APIs, with tokens shared between the all services.

Yes, token usage can be monitored in the 'Buy tokens' tab by entering your API key, allowing you to view the usage history and remaining tokens.

If you have misplaced a topped-up key and wish to retrieve it, please contact support AT jina.ai with your registered email for assistance.

No, our API keys do not have an expiration date. However, if you suspect your key has been compromised and wish to retire it or transfer its tokens to a new key, please contact our support team for assistance.

This is because our serverless architecture offloads certain models during periods of low usage. The initial request activates or 'warms up' the model, which may take a few seconds. After this initial activation, subsequent requests process much more quickly.

We adhere to a strict privacy policy and do not use user input data for training our models.

Our pricing model is based on the total number of tokens processed, allowing users the flexibility to allocate these tokens across any number of sentences, offering a cost-effective solution for diverse text analysis requirements.

We offer a welcoming free trial to new users, which includes one million tokens for use with any of our models, facilitated by an auto-generated API key. Once the free token limit is reached, users can easily purchase additional tokens for their API keys via the 'Buy tokens' tab.

No, tokens are not deducted for failed requests.

Payments are processed through Stripe, supporting a variety of payment methods including credit cards, Google Pay, and PayPal for your convenience.

Yes, an invoice will be issued to the email address associated with your Stripe account upon the purchase of tokens.