--- source_url: "https://jina.ai/contact-sales/" title: Contact sales mirrored_at: 2026-08-13T01:35:36.071Z host: jina.ai cited_in_42a: true mirror_canonical: "https://index.42a.ai/jina.ai/contact-sales/index" --- > **Original source:** https://jina.ai/contact-sales/ Grow your business with Jina AI. * * * Name Work email Job role Organization Organization size Country Organization website Which products are you interested in? Tell us about your problem, idea or drop some screenshots. By submitting, you confirm that you agree to the processing of your personal data by Jina AI as described in the [Privacy Statement](https://jina.ai/legal#privacy-policy) Sales team away, back in 6h ## [Two Ways to Purchase](#pricing) Subscribe to our API or purchase through cloud providers. With **3** cloud service providers Using AWS or Azure? You can deploy our models directly on your company's cloud platform and handle billing through the CSP account. With Jina Search Foundation API The easiest way to access all of our products. Top-up tokens as you go. Enter the API key you wish to recharge Top up this API key with more tokens Depending on your location, you may be charged in USD, EUR, or other currencies. Taxes may apply. Please input the right API key to top up Understand the rate limit Rate limits are the maximum number of requests that can be made to an API within a minute per IP address/API key (RPM). Find out more about the rate limits for each product and tier below. Auto top-up on low token balance Recommended for uninterrupted service in production. When your token balance drops below the set threshold, we will automatically recharge your saved payment method for the last purchased package, until the threshold is met. We introduced a new pricing model on May 6th, 2025. If you enabled auto-recharge before this date, you'll continue to pay the old price (the one when you purchased). The new pricing only applies if you modify your auto-recharge settings or purchase a new API key. < 1M Tokens Top up when ## FAQ ### [Jina AI × Elastic](#post-acquisition) Will the Jina brand be preserved? What will Jina AI focus on going forward? Will the API and cloud marketplace offerings continue? Will you still release open-weights models on Hugging Face? Under which license will these open models be released? Will you continue publishing research papers? I'm not yet a Jina or Elastic customer, but I want to use the Reader API, model APIs, or cloud marketplace images. What should I do? I'm already a paid Elastic customer and want to use the Reader API, model APIs, or cloud marketplace images. What should I do? I'm a paid Elastic customer and want to use Jina embedding and reranker models on-premises for commercial purposes—not via API or cloud marketplace. What should I do? I'm not an Elastic customer, and I want to use Jina embedding and reranker models on-premises for commercial purposes—not via API or cloud marketplace. What should I do? I'm purchasing your services as a Chinese entity. Can I get a Chinese invoice (发票)? I want to sign a contract with Jina AI. What should I do? I'm a paid Elastic customer and want to learn best practices for using embeddings and reranker models, or I'm generally interested in Jina AI's development. What should I do? ### [How to get my API key?](#get-api-key) video\_not\_supported ### [What's the rate limit?](#rate-limit) Rate Limit Rate limits are tracked in three ways: **RPM** (requests per minute), and **TPM** (tokens per minute). Limits are enforced per IP/API key and will be triggered when either the RPM or TPM threshold is reached first. When you provide an API key in the request header, we track rate limits by key rather than IP address. Columns Product API Endpoint Description w/o API Key w/ Free API Key w/ Paid API Key w/ Premium API Key Average Latency Token Usage Counting Allowed Request Reader API `https://r.jina.ai` Convert URL to LLM-friendly text 20 RPM 500 RPM 500 RPM 5000 RPM 7.9s Count the number of tokens in the output response. GET/POST Reader API `https://s.jina.ai` Search the web and convert results to LLM-friendly text 100 RPM 100 RPM 1000 RPM 2.5s Every request costs a fixed number of tokens, starting from 10000 tokens GET/POST Embedding API `https://api.jina.ai/v1/embeddings` Convert text/images to fixed-length vectors 100 RPM & 100,000 TPM 500 RPM & 2,000,000 TPM 5,000 RPM & 50,000,000 TPM depends on the input size Count the number of tokens in the input request. POST Reranker API `https://api.jina.ai/v1/rerank` Rank documents by query 100 RPM & 100,000 TPM 500 RPM & 2,000,000 TPM 5,000 RPM & 50,000,000 TPM depends on the input size Count the number of tokens in the input request. POST Classifier API `https://api.jina.ai/v1/train` Train a classifier using labeled examples 25 RPM & 25,000 TPM 125 RPM & 500,000 TPM 1,250 RPM & 12,000,000 TPM depends on the input size Tokens counted as: input\_tokens × num\_iters POST Classifier API (Few-shot) `https://api.jina.ai/v1/classify` Classify inputs using a trained few-shot classifier 25 RPM & 25,000 TPM 125 RPM & 500,000 TPM 1,250 RPM & 12,000,000 TPM depends on the input size Tokens counted as: input\_tokens POST Classifier API (Zero-shot) `https://api.jina.ai/v1/classify` Classify inputs using zero-shot classification 25 RPM & 25,000 TPM 125 RPM & 500,000 TPM 1,250 RPM & 12,000,000 TPM depends on the input size Tokens counted as: input\_tokens + label\_tokens POST Segmenter API `https://api.jina.ai/v1/segment` Tokenize and segment long text 20 RPM 200 RPM 200 RPM 1,000 RPM 0.3s Token is not counted as usage. GET/POST DeepSearch `https://deepsearch.jina.ai/v1/chat/completions` Reason, search and iterate to find the best answer 50 RPM 50 RPM 500 RPM 56.7s Count the total number of tokens in the whole process. POST ### [Do I need a commercial license?](#cc-self-check) CC BY-NC License Self-Check * * * ### [Other questions](#faq) What are the costs associated with using the Reader API? How does the Reader API function? Is the Reader API open source? What is the typical latency for the Reader API? Why should I use the Reader API instead of scraping the page myself? Does the Reader API support multiple languages? Does the Reader API respect website access controls? Can the Reader API extract content from PDF files? Can the Reader API process media content from web pages? Is it possible to use the Reader API on local HTML files? Does Reader API cache the content? Can I use the Reader API to access content behind a login? Can I use the Reader API to access PDF on arXiv? How does image caption work in Reader? What is the scalability of the Reader? Can I use it in production? What is the rate limit of the Reader API? What is Reader-LM? How can I use it? How do I extract structured data from webpages? Does Reader actively bypass website anti-bot protection? Will upgrading from a free to a paid API key give me access to more websites? How were the Jina embedding models trained? What are your multimodal embedding models? Which languages do your models support? What is the maximum length for a single sentence input? What is the maximum number of sentences I can include in a single request? How do I send images to multimodal embedding models? How do Jina Embeddings models compare to OpenAI's and Cohere's latest embeddings? How seamless is the transition from OpenAI's text-embedding-3-large to your solution? How tokens are calculated when using jina-clip and jina-embeddings models? Do you provide models for embedding images or audio? Can Jina Embedding models be fine-tuned with private or company data? Can your endpoints be hosted privately on AWS, Azure, or GCP? What is the 'task' parameter and when should I use it? What is late-interaction retrieval and which models support it? What is late chunking and when should I use it? Why does the API support a different context length than the model's maximum capacity? Why is jina-embeddings-v4 free, and why is it slow? What are the rate limits for the Embeddings API? What are the context length limits for each embedding model? What are the file size limits for images and PDFs? How much does the Reranker API cost? What are the differences between Jina rerankers? How are Jina Rerankers licensed? Do the rerankers support multiple languages? What is the maximum context length for each reranker model? Is there a limit on the number of documents I can rerank per query? What latency can I expect when reranking 100 documents? Can your endpoints be hosted privately on AWS, Azure, or GCP? Do you offer a fine-tuned reranker on domain-specific data? What's the minimum image size for the documents? What is listwise reranking and how does it differ from pointwise? Why does the API support a different context length than the model's maximum capacity? What are the rate limits for the Reranker API? Can I use the same API key for reader, embedding, reranking, classifying and fine-tuning APIs? Can I monitor the token usage of my API key? What should I do if I forget my API key? Do API keys expire? Can I transfer tokens between API keys? Can I revoke my API key? Why is the first request for some models slow? Is my API data used to train your models? What are the rate limits for Jina APIs? Are there batch size limits for the APIs? Is billing based on the number of sentences or requests? Is there a free trial available for new users? Are tokens charged for failed requests? What payment methods are accepted? Is invoicing available for token purchases? What is DeepSearch? How is DeepSearch different from OpenAI and Gemini's deep research capabilities? What API key do I need to use DeepSearch? What happens when DeepSearch reaches its token budget? Does it return an incomplete answer? Does DeepSearch guarantee accurate answers? How long does a typical DeepSearch query take? Can DeepSearch work with any OpenAI-compatible client like Chatwise, CherryStudio or ChatBox? What are the rate limits for the API? What is the content inside the tag? Does DeepSearch use Jina Reader for web search and reading? Why does DeepSearch use so many tokens for my queries? Is there a way to control or limit the number of steps? How reliable are the references in the answers? Can DeepSearch handle questions about future events? What's different about labels in zero-shot vs few-shot? What's num\_iters for and how should I use it? How does public classifier sharing work? How much data do I need for few-shot to work well? Can it handle multiple languages and both text/images? What are the hard limits I should know about? How do I handle data changes over time? What happens to my training data after I send it? Zero-shot vs few-shot - when to use which? Can I use different models for different languages/tasks? How much does the Segmenter API cost? If I don't provide an API key, what is the rate limit? If I provide an API key, what is the rate limit? Will you charge the tokens from my API key? Does the Segmenter API support multiple languages? What is the difference between GET and POST requests? What is the maximum length I can tokenize per request? How does the chunking feature work? Is it semantic chunking? How do you handle special tokens such as 'endoftext' in the Segmenter API? Does chunking support other languages than English? How much does the Fine-tuning API cost? What do I need to input? Do I need to provide training data? How long does it take to fine-tune a model? Where are the fine-tuned models stored? If I provide a reference URL, how does the system use it? Can I fine-tune a model for a specific language? Can I fine-tune non-Jina embeddings, e.g., bge-M3? How do you ensure the quality of the fine-tuned models? How do you generate synthetic data? Can I keep my fine-tuned models and synthetic data private? How can I use the fine-tuned model? I never received the email with the evaluation results. What should I do? Elastic © 2020-2026. This website and all associated content, software, products, and services are intended for professional use only. No consumer use is intended or directed.