Elastic
Jina AI
Models
API
keyboard_arrow_down
Reader
Convert any URL to Markdown for better grounding LLMs.
Embeddings
Multimodal multilingual embeddings.
Reranker
Reranker for maximizing search relevancy.
Elastic Inference Service
Run Jina models natively inside Elasticsearch.
MCP
terminal
CLI
article
llms.txt
smart_toy
Agents
data_object
Schema
menu_book
Docs
Log in
login

Embeddings

Top-performing multimodal multilingual long-context embeddings for search, RAG, agents applications.

Embedding API

Try our embedding models to improve your search and RAG systems. Start with a free trial!
keyAPI Key & Billing
codeUsage
more_horizMore
chevron_leftchevron_right
home
speedRate Limit
bug_reportRaise issue
help_outlineFAQ
Status
chevron_leftchevron_right
upload
Request
POST
curl "https://api.jina.ai/v1/embeddings" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $JINA_API_KEY" \
  -d @- <<EOFEOF
{
  "model": null,
  "normalized": true,
  "embedding_type": "float",
  "input": [
    text_fieldsclose"Organic skincare for sensitive skin with aloe vera and chamomile: Imagine the soothing embrace of na…ing, healthy complexion.",
    text_fieldsclose"Bio-Hautpflege für empfindliche Haut mit Aloe Vera und Kamille: Erleben Sie die wohltuende Wirkung u…einen strahlenden Teint.",
    text_fieldsclose"Cuidado de la piel orgánico para piel sensible con aloe vera y manzanilla: Descubre el poder de la n…el radiante y saludable.",
    text_fieldsclose"针对敏感肌专门设计的天然有机护肤产品：体验由芦荟和洋甘菊提取物带来的自然呵护。我们的护肤产品特别为敏感肌设计，温和滋润，保护您的肌肤不受刺激。让您的肌肤告别不适，迎来健康光彩。",
    text_fieldsclose"新しいメイクのトレンドは鮮やかな色と革新的な技術に焦点を当てています: 今シーズンのメイクアップトレンドは、大胆な色彩と革新的な技術に注目しています。ネオンアイライナーからホログラフィックハイライターまで、クリエイティビティを解き放ち、毎回ユニークなルックを演出しましょう。"
    + add input
  ]
}
EOFEOF

v5-omni: One Embedding for All

Text, image, audio, video — one shared embedding space, two sizes. v5-omni-small (1.6B) is the best-performing open-weight omni model under 2B parameters. v5-omni-nano (0.9B) delivers competitive retrieval at under 1B. Both are byte-for-byte compatible with v5-text — no reindexing needed.

v5-text: New SOTA Small Multilingual Embeddings

jina-embeddings-v5-text delivers fifth-generation embedding quality in two efficient sizes — a 677M small and 239M nano model — with task-specific LoRA adapters, Matryoshka dimensions, 32K context, and GGUF/MLX quantization for edge deployment, setting new benchmarks across MMTEB, MTEB English, and retrieval tasks.

Two Ways to Purchase

Subscribe to our API or purchase through cloud providers.
radio_button_unchecked
cloud
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.
AWS SageMaker
Embeddings
Reranker
Microsoft Azure
Embeddings
Reranker
Google Cloud
Embeddings
radio_button_checked
With Jina Search Foundation API
The easiest way to access all of our products. Top-up tokens as you go.
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.
keyboard_arrow_down
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.
ProductAPI EndpointDescriptionarrow_upwardw/o API Keykey_offw/ Free API Keykeyw/ Paid API Keykeyw/ Premium API KeykeyAverage LatencyToken Usage CountingAllowed Request
Reader APIhttps://r.jina.aiConvert URL to LLM-friendly text20 RPM500 RPM500 RPMtrending_up5000 RPM7.9sCount the number of tokens in the output response.GET/POST
Reader APIhttps://s.jina.aiSearch the web and convert results to LLM-friendly textblock100 RPM100 RPMtrending_up1000 RPM2.5sEvery request costs a fixed number of tokens, starting from 10000 tokensGET/POST
Embedding APIhttps://api.jina.ai/v1/embeddingsConvert text/images to fixed-length vectorsblock100 RPM & 100,000 TPM500 RPM & 2,000,000 TPMtrending_up5,000 RPM & 50,000,000 TPM
ssid_chart
depends on the input size
help
Count the number of tokens in the input request.POST
Reranker APIhttps://api.jina.ai/v1/rerankRank documents by queryblock100 RPM & 100,000 TPM500 RPM & 2,000,000 TPMtrending_up5,000 RPM & 50,000,000 TPM
ssid_chart
depends on the input size
help
Count the number of tokens in the input request.POST
Classifier APIhttps://api.jina.ai/v1/trainTrain a classifier using labeled examplesblock25 RPM & 25,000 TPM125 RPM & 500,000 TPM1,250 RPM & 12,000,000 TPM
ssid_chart
depends on the input size
Tokens counted as: input_tokens × num_itersPOST
Classifier API (Few-shot)https://api.jina.ai/v1/classifyClassify inputs using a trained few-shot classifierblock25 RPM & 25,000 TPM125 RPM & 500,000 TPM1,250 RPM & 12,000,000 TPM
ssid_chart
depends on the input size
Tokens counted as: input_tokensPOST
Classifier API (Zero-shot)https://api.jina.ai/v1/classifyClassify inputs using zero-shot classificationblock25 RPM & 25,000 TPM125 RPM & 500,000 TPM1,250 RPM & 12,000,000 TPM
ssid_chart
depends on the input size
Tokens counted as: input_tokens + label_tokensPOST
Segmenter APIhttps://api.jina.ai/v1/segmentTokenize and segment long text20 RPM200 RPM200 RPM1,000 RPM0.3sToken is not counted as usage.GET/POST
DeepSearchhttps://deepsearch.jina.ai/v1/chat/completionsReason, search and iterate to find the best answerblock50 RPM50 RPM500 RPM56.7sCount the total number of tokens in the whole process.POST

On-premises deployment

Deploy Jina Embeddings models in AWS Sagemaker and Microsoft Azure, and soon in Google Cloud Services, or contact our sales team to get customized Kubernetes deployments for your Virtual Private Cloud and on-premises servers.
AWS SageMaker
Embeddings
Reranker
Microsoft Azure
Embeddings
Reranker
Google Cloud
Embeddings
API Integrations
Our Embedding API is natively integrated with various renowned databases, vector stores, RAG, and LLMOps frameworks. To begin, just copy and paste your API key into any of the listed integrations for a quick and seamless start.
Vector Store
LLMOps
RAG
Observability
open_in_new
MongoDB
open_in_new
DataStax
open_in_new
Qdrant
open_in_new
Pinecone
open_in_new
Chroma
open_in_new
Weaviate
open_in_new
Milvus
open_in_new
Epsilla
open_in_new
MyScale
open_in_new
LlamaIndex
open_in_new
Haystack
open_in_new
Langchain
open_in_new
Dify
open_in_new
SuperDuperDB
open_in_new
DashVector
open_in_new
Portkey
open_in_new
Baseten
open_in_new
TiDB
open_in_new
LanceDB
open_in_new
Carbon

Our Publications

Understand how our frontier search models were trained from scratch, check out our latest publications. Meet our team at EMNLP, SIGIR, ICLR, NeurIPS, and ICML!
arXiv
July 20, 2026
jina-reranker-v3.5: An Efficient Listwise Reranker with Hybrid Attention and Self-Distillation
SIGIR 2026
May 11, 2026
jina-embeddings-v5-omni: Geometry-preserving Embeddings via Locked Aligned Towers
SIGIR 2026
February 17, 2026
jina-embeddings-v5-text: Task-Targeted Embedding Distillation
ICLR 2026
January 22, 2026
Embedding Compression via Spherical Coordinates
arXiv
December 29, 2025
Vision Encoders in Vision-Language Models: A Survey
ICLR 2026
December 04, 2025
Jina-VLM: Small Multilingual Vision Language Model
AAAI 2026
October 01, 2025
jina-reranker-v3: Last but Not Late Interaction for Document Reranking
NeurIPS 2025
August 31, 2025
Efficient Code Embeddings from Code Generation Models
EMNLP 2025
June 24, 2025
jina-embeddings-v4: Universal Embeddings for Multimodal Multilingual Retrieval
ICLR 2025
March 04, 2025
ReaderLM-v2: Small Language Model for HTML to Markdown and JSON
ACL 2025
December 17, 2024
AIR-Bench: Automated Heterogeneous Information Retrieval Benchmark
ICLR 2025
December 12, 2024
jina-clip-v2: Multilingual Multimodal Embeddings for Text and Images
ECIR 2025
September 18, 2024
jina-embeddings-v3: Multilingual Embeddings With Task LoRA
SIGIR 2025
September 07, 2024
Late Chunking: Contextual Chunk Embeddings Using Long-Context Embedding Models
EMNLP 2024
August 30, 2024
Jina-ColBERT-v2: A General-Purpose Multilingual Late Interaction Retriever
WWW 2025
June 21, 2024
Leveraging Passage Embeddings for Efficient Listwise Reranking with Large Language Models
ICML 2024
May 30, 2024
Jina CLIP: Your CLIP Model Is Also Your Text Retriever
arXiv
February 26, 2024
Multi-Task Contrastive Learning for 8192-Token Bilingual Text Embeddings
arXiv
October 30, 2023
Jina Embeddings 2: 8192-Token General-Purpose Text Embeddings for Long Documents
EMNLP 2023
July 20, 2023
Jina Embeddings: A Novel Set of High-Performance Sentence Embedding Models
20 publications in total.

Learning about Embeddings

Where to start with embeddings? We've got you covered. Learn about embeddings from the ground up with our comprehensive guide.
May 12, 2026 • 7 minutes read
jina-embeddings-v5-omni: Embeddings for Text, Image, Audio and Video
One model, four modalities: text, image, audio, video. Best-in-class omni embeddings in 1.6B and 0.9B.
Han Xiao
jina-embeddings-v5-omni: Geometry-preserving Embeddings via Locked Aligned Towers
May 11, 2026
jina-embeddings-v5-omni: Geometry-preserving Embeddings via Locked Aligned Towers
We introduce GELATO (Geometry-preserving Embeddings via Locked Aligned TOwers), a novel approach to multimodal embedding models. We build on the VLM-style architecture, in which non-text encoders are adapted to produce input for a language model, which in turn generates embeddings for all varieties of input. GELATO extends the two Jina Embeddings v5 Text models to support additional modality by adding encoders for images and audio. The backbone text embedding models and the added non-text modality encoders remain frozen. We only trained the connecting components, representing 0.35% of the total weights of the joint model. Additionally, the language model remains effectively unaltered, producing exactly the same embeddings for text inputs as the Jina Embeddings v5 Text models. The resulting jina-embeddings-v5-omni suite encodes text, image, audio, and video into a single semantic embedding space, yielding nearly equal performance to larger multimodal embedding models.
Abstract illustration of a sound wave or heartbeat, formed by blue, orange, and gray dots on a white background.
March 11, 2026 • 7 minutes read
Bootstrapping Audio Embeddings from Multimodal LLMs
Turn any multimodal LLM into a small audio embedding model that beats CLAP with 25x less data.
Han Xiao
Fingerprint illustration made from numbers, showcasing digital and high-tech design on a light background.
March 06, 2026 • 6 minutes read
Identifying Embedding Models from Raw Numerical Values
A tiny transformer that fingerprints embedding models by reading raw numerical digits. No feature engineering.
Han Xiao

Comparison of Reranker, Vector Search, and BM25

The table below provides a comprehensive comparison of the Reranker, Vector/Embeddings Search, and BM25, highlighting their strengths and weaknesses across various categories.
RerankerVector SearchBM25
Best ForEnhanced search precision and relevanceInitial, rapid filteringGeneral text retrieval across wide-ranging queries
GranularityDetailed: Sub-document and query segmentBroad: Entire documentsIntermediate: Various text segments
Query Time ComplexityHighMediumLow
Indexing Time ComplexityNot requiredHighLow, utilizes pre-built index
Training Time ComplexityHighHighNot required
Search QualitySuperior for nuanced queriesBalanced between efficiency and accuracyConsistent and reliable for a broad set of queries
StrengthsHighly accurate with deep contextual understandingQuick and efficient, with moderate accuracyHighly scalable, with established efficacy
Try reranker API for freeTry embedding API for free

The Evolution of Embeddings Poster

Discover the ideal poster for your space, featuring captivating infographics or breathtaking visuals tracing the evolution of text embedding models since 1950.
Learn how we made it
shopping_cartBuy a hard copy

FAQ

How were the Jina embedding models trained?
keyboard_arrow_down
For detailed information on our training processes, data sources, and evaluations, refer to the technical reports on arXiv. The jina-embeddings-v5 text models are trained in two stages: embedding distillation from a larger teacher model, followed by task-specific LoRA adapter training on frozen backbone weights. The v5-omni multimodal variants add a third stage that trains only cross-modal projectors, leaving the text backbone and adapters frozen.
launcharXiv
What are your multimodal embedding models?
keyboard_arrow_down
jina-embeddings-v5-omni-small (~1.74B parameters, 1024 dimensions, 32K context) and jina-embeddings-v5-omni-nano (~1.04B parameters, 768 dimensions, 8K context) are our current multimodal models. They accept text, images, audio, video, and PDFs in one shared vector space, so you can index in one modality and query in another without reindexing. Their text-only output is identical to jina-embeddings-v5-text-small and jina-embeddings-v5-text-nano respectively, which means you can add multimodal input to an existing text index without re-embedding it. jina-clip-v2 (865M parameters) remains available as a lighter text-and-image option.
launcharXiv
Which languages do your models support?
keyboard_arrow_down
All models released since 2024 are multilingual. jina-embeddings-v5-text-small and the v5-omni models are built on a Qwen3 backbone with broad multilingual coverage; jina-embeddings-v5-text-nano is built on EuroBERT-210M, covering 15 major European and global languages including English, French, German, Spanish, Chinese, Japanese, Arabic, and Hindi. jina-embeddings-v3 and jina-clip-v2 support 89 languages. For per-language benchmark numbers, see the MMTEB results in each model's technical report.
launcharXiv
What is the maximum context length for a single input?
keyboard_arrow_down
Context length varies by model: jina-embeddings-v5-text-small and jina-embeddings-v5-omni-small support up to 32,768 tokens, while jina-embeddings-v5-text-nano and jina-embeddings-v5-omni-nano support 8,192 tokens. jina-embeddings-v4 and the jina-code-embeddings models support 32,768 tokens; jina-embeddings-v3, jina-clip-v2, and jina-colbert-v2 support 8,192 tokens. Inputs above the limit return an error unless you set truncate: true.
What is the maximum number of inputs I can include in a single request?
keyboard_arrow_down
There is no hard limit on the number of items per request. The API batches inputs internally by token count for optimal GPU utilization, so you can send as many texts or images as needed in a single request. PDFs are the exception: send one PDF per request.
How do I send images, audio, video, or PDFs to the multimodal models?
keyboard_arrow_down
Pass a typed object in the input array using an image, audio, video, or pdf key, whose value is either a public URL or base64-encoded bytes. The model routes each modality to the appropriate encoder, and you can mix modalities freely within a single batch. Supported audio formats include WAV, MP3, FLAC, OGG, M4A, and Opus; video is processed as 32 uniformly sampled frames. PDFs must be sent one per request.
How do Jina embeddings compare to the latest OpenAI, Cohere, and Voyage models?
keyboard_arrow_down
jina-embeddings-v5-text-small (677M parameters) is the strongest model under 1B parameters on MMTEB, scoring 67.0 average at task level, and reaches 71.7 average on English MTEB. jina-embeddings-v5-text-nano (239M parameters) scores 65.5 on MMTEB, ahead of every model we evaluated under 500M parameters. Our design target is capability per parameter rather than raw size, so these models are cheaper to serve than most alternatives at comparable or better retrieval quality. All v5 models support Matryoshka Representation Learning, so you can truncate dimensions down to 32 without retraining.
How seamless is the transition from OpenAI's text-embedding-3-large to your solution?
keyboard_arrow_down
The transition is straightforward: our API endpoint matches the input and output JSON schemas of OpenAI's text-embedding-3-large, so in most codebases you change the base URL, the API key, and the model name. The same holds for the Jina On-Prem containers, which additionally expose Elastic Inference Service (EIS), Cohere, Voyage AI, and Gemini schemas, so Jina models are a drop-in replacement in existing code paths. Note that embeddings from different model families are not comparable, so you have to re-embed your corpus rather than mix vectors from two providers in one index. For the On-Prem containers themselves, contact Elastic Sales.
How are tokens calculated for images and other non-text inputs?
keyboard_arrow_down
Text is counted in the standard way. Non-text inputs are converted to tokens by the relevant encoder, and the cost depends heavily on which model you use, so measure with your own inputs rather than assuming. As a reference point, a 600x600 pixel image costs approximately: • jina-embeddings-v5-omni-small: ~363 tokens • jina-embeddings-v5-omni-nano: ~362 tokens • jina-embeddings-v4: ~4,840 tokens • jina-clip-v2: ~16,000 tokens The v5-omni models are one to two orders of magnitude cheaper per image than the older models. Every response includes a usage object with the exact token count for that request, including an image_tokens breakdown for multimodal inputs, so you can verify cost per call.
Do you provide models for embedding images, audio, or video?
keyboard_arrow_down
Yes. jina-embeddings-v5-omni-small and jina-embeddings-v5-omni-nano embed text, images, audio, video, and PDFs into a single shared vector space. jina-embeddings-v4 and jina-clip-v2 handle text and images.
Can Jina embedding models be fine-tuned on private or company data?
keyboard_arrow_down
There are two paths. The self-serve one is the Fine-tuning API, which generates synthetic training data from a description of your domain and returns a fine-tuned model, without your having to assemble a labelled dataset. For fine-tuning on proprietary data under a commercial agreement, on dedicated infrastructure, or on a model that is not in the base model selector, Contact Elastic Sales; that work is scoped and contracted through Elastic.
Contact
Can the models be hosted privately, on my own infrastructure or in my own cloud account?
keyboard_arrow_down
Yes, in two ways. Jina models are available on the AWS, Azure, and GCP marketplaces, so you can deploy them inside your own cloud account. For self-managed, on-premises, or air-gapped infrastructure, Elastic sells a commercial license called Jina On-Prem, available since August 10, 2026, which ships the models as fully offline Docker containers with no external calls and no license server. To get a quote for either path, contact Elastic Sales.
launchAWS SageMakerlaunchGoogle CloudlaunchMicrosoft Azure
What is the 'task' parameter and when should I use it?
keyboard_arrow_down
The task parameter selects a task-specific LoRA adapter for optimal performance. Use retrieval.query for search queries, retrieval.passage for documents being searched, text-matching for symmetric similarity such as duplicate or paraphrase detection, classification for categorization, and separation for clustering. Retrieval is asymmetric, so using the wrong side of the query/passage pair measurably degrades results. The parameter is supported by jina-embeddings-v5, jina-embeddings-v4, and jina-embeddings-v3.
What is late-interaction retrieval and which models support it?
keyboard_arrow_down
Late interaction keeps token-level vectors instead of collapsing a document into one vector, which preserves fine-grained detail at the cost of a larger index. jina-embeddings-v4 supports both dense (single-vector) and late-interaction (multi-vector) output via the output_type parameter, and jina-colbert-v2 is a dedicated late-interaction model. For most retrieval pipelines, a dense v5 model followed by a reranker is the better accuracy-per-cost tradeoff.
What is late chunking and when should I use it?
keyboard_arrow_down
Late chunking embeds the whole document first with a long-context model, then derives chunk embeddings from the token-level representations. Unlike naive chunking, which embeds each chunk in isolation, late chunking preserves cross-chunk context, which improves retrieval quality in RAG pipelines where a chunk refers to something defined earlier in the document. Enable it with the late_chunking parameter.
Why does the API enforce a different context length than the model supports?
keyboard_arrow_down
Some models are architecturally capable of longer context than the hosted API accepts. Very long sequences consume substantial GPU memory, and we tune the serving configuration to balance throughput, latency, and cost for the majority of use cases. If you need the full architectural context length, run the model yourself: contact Elastic Sales about a self-managed deployment.
Why is jina-embeddings-v4 free, and why is it slow?
keyboard_arrow_down
jina-embeddings-v4 is built on the Qwen2-VL base model, released under the Qwen Research License, which permits research and non-commercial use only. We therefore cannot license it commercially and provide it free of charge via the API instead. It is also a 3.8B parameter model, so it is inherently slower per request, and we throttle its throughput to manage infrastructure costs. It is not suitable for production workloads, and for the same reason it is not offered through the Elastic Inference Service or as part of Jina On-Prem. For production use, take the jina-embeddings-v5 family: it is faster, stronger on retrieval benchmarks, and can be licensed for commercial use through Elastic Sales.
What are the rate limits for the Embeddings API?
keyboard_arrow_down
Rate limits depend on your API key type:

Free: 100 RPM, 100K TPM
Paid: 500 RPM, 2M TPM
Premium: 5,000 RPM, 50M TPM

There is an additional IP-based limit of 10,000 requests per 60 seconds to prevent abuse. Limits are applied per key and counted over a 60-second window, so bursts are smoothed rather than queued; a request over the limit returns HTTP 429 and should be retried with exponential backoff. If you need limits beyond the Premium tier, or dedicated capacity with no shared-tenant limit at all, contact Elastic Sales.
Which embedding model should I choose?
keyboard_arrow_down
Start with jina-embeddings-v5-text-small for text retrieval: it is the strongest sub-1B model we ship and handles 32K context. Drop to jina-embeddings-v5-text-nano when latency, cost, or edge hardware matters more than the last point of accuracy. Use jina-embeddings-v5-omni-small or v5-omni-nano when images, audio, video, or PDFs are involved; their text output is identical to the corresponding text model, so you can add modalities to an existing index without re-embedding. Use jina-code-embeddings-0.5b or 1.5b for source code. Within a family, newer is better.
What are the file size limits for images and PDFs?
keyboard_arrow_down
Maximum file sizes are 5 MB for images and 8 MB for PDFs. Larger files are rejected with an error.

How to get my API key?

video_not_supported

What's the 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.
ProductAPI EndpointDescriptionarrow_upwardw/o API Keykey_offw/ Free API Keykeyw/ Paid API Keykeyw/ Premium API KeykeyAverage LatencyToken Usage CountingAllowed Request
Reader APIhttps://r.jina.aiConvert URL to LLM-friendly text20 RPM500 RPM500 RPMtrending_up5000 RPM7.9sCount the number of tokens in the output response.GET/POST
Reader APIhttps://s.jina.aiSearch the web and convert results to LLM-friendly textblock100 RPM100 RPMtrending_up1000 RPM2.5sEvery request costs a fixed number of tokens, starting from 10000 tokensGET/POST
Embedding APIhttps://api.jina.ai/v1/embeddingsConvert text/images to fixed-length vectorsblock100 RPM & 100,000 TPM500 RPM & 2,000,000 TPMtrending_up5,000 RPM & 50,000,000 TPM
ssid_chart
depends on the input size
help
Count the number of tokens in the input request.POST
Reranker APIhttps://api.jina.ai/v1/rerankRank documents by queryblock100 RPM & 100,000 TPM500 RPM & 2,000,000 TPMtrending_up5,000 RPM & 50,000,000 TPM
ssid_chart
depends on the input size
help
Count the number of tokens in the input request.POST
Classifier APIhttps://api.jina.ai/v1/trainTrain a classifier using labeled examplesblock25 RPM & 25,000 TPM125 RPM & 500,000 TPM1,250 RPM & 12,000,000 TPM
ssid_chart
depends on the input size
Tokens counted as: input_tokens × num_itersPOST
Classifier API (Few-shot)https://api.jina.ai/v1/classifyClassify inputs using a trained few-shot classifierblock25 RPM & 25,000 TPM125 RPM & 500,000 TPM1,250 RPM & 12,000,000 TPM
ssid_chart
depends on the input size
Tokens counted as: input_tokensPOST
Classifier API (Zero-shot)https://api.jina.ai/v1/classifyClassify inputs using zero-shot classificationblock25 RPM & 25,000 TPM125 RPM & 500,000 TPM1,250 RPM & 12,000,000 TPM
ssid_chart
depends on the input size
Tokens counted as: input_tokens + label_tokensPOST
Segmenter APIhttps://api.jina.ai/v1/segmentTokenize and segment long text20 RPM200 RPM200 RPM1,000 RPM0.3sToken is not counted as usage.GET/POST
DeepSearchhttps://deepsearch.jina.ai/v1/chat/completionsReason, search and iterate to find the best answerblock50 RPM50 RPM500 RPM56.7sCount the total number of tokens in the whole process.POST

Do I need a commercial license?

CC BY-NC License Self-Check
play_arrow
Are you using our official API or official images on Azure, AWS, or GCP?
play_arrow
Yes
No restrictions. Simply sign up and pay through our website or cloud marketplace.
play_arrow
No
play_arrow
Are you a paid Elastic customer?
play_arrow
Yes
Commercial use is likely already included in your Elastic license. Contact your Elastic Sales representative if unsure.
Contact sales
play_arrow
No
We're currently unable to issue standalone commercial licensing agreements. Please contact Elastic Sales for more information.
Contact sales
API-related common questions
code
Can I use the same API key across all Jina APIs?
keyboard_arrow_down
Yes. One API key is valid for all Jina AI search foundation products, including the Reader, Embeddings, Reranker, Classifier, and Segmenter APIs, with tokens shared across all of them.
code
Can I monitor the token usage of my API key?
keyboard_arrow_down
Yes, token usage can be monitored in the 'API Key & Billing' tab by entering your API key, allowing you to view the recent usage history and remaining tokens. If you have logged in to the API dashboard, these details can also be viewed in the 'Manage API Key' tab.
code
What should I do if I forget my API key?
keyboard_arrow_down
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. It's recommended to log in to keep your API key securely stored and easily accessible.
Contact
code
Do API keys expire?
keyboard_arrow_down
No, our API keys do not have an expiration date. If a key is compromised, revoke it yourself in the API Key Management dashboard, which takes effect immediately; issue a replacement key first if you want to avoid downtime. Any remaining token balance stays on your account rather than on the revoked key. If you cannot access the dashboard, or believe the account itself is compromised, raise it with Elastic Support.
Contact
code
Can I transfer tokens between API keys?
keyboard_arrow_down
Yes, you can transfer tokens from a premium key to another. After logging into your account on the API Key Management dashboard, use the settings of the key you want to transfer out to move all remaining paid tokens.
code
Can I revoke my API key?
keyboard_arrow_down
Yes, you can revoke your API key if you believe it has been compromised. Revoking a key will immediately disable it for all users who have stored it, and all remaining balance and associated properties will be permanently unusable. If the key is a premium key, you have the option to transfer the remaining paid balance to another key before revocation. Notice that this action cannot be undone. To revoke a key, go to the key settings in the API Key Management dashboard.
code
Why is the first request for some models slow?
keyboard_arrow_down
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.
code
Is my API data used to train your models?
keyboard_arrow_down
No. We never use your API requests, inputs, or outputs to train our embedding, reranker, or any other models. Your data remains yours.
code
What are the rate limits for Jina APIs?
keyboard_arrow_down
Rate limits apply per API key:

Free: 100 RPM, 100K TPM
Paid: 500 RPM, 2M TPM
Premium: 5,000 RPM, 50M TPM

There is also an IP-based limit of 10,000 requests per 60 seconds. Limits vary by endpoint; see the rate limit table above for per-endpoint figures.
code
Are there batch size limits for the APIs?
keyboard_arrow_down
There is no batch size limit for either the Embeddings or Reranker APIs. You can send as many items or documents as needed per request. Both APIs batch inputs internally by token count for optimal GPU utilization.
code
Are the Jina APIs the same thing as Jina models inside Elastic?
keyboard_arrow_down
No, they are three separate paths. The Jina APIs on this site are self-serve and pay-as-you-go with a Jina API key. The Elastic Inference Service (EIS) runs Jina models inside Elastic Cloud, billed through your Elastic subscription, with no infrastructure for you to manage. Jina On-Prem is a commercial license, sold by Elastic as its own SKU since August 10, 2026, for running the models in your own self-managed, on-premises, or air-gapped infrastructure. For the EIS and On-Prem paths, contact Elastic Sales.
Billing-related common questions
attach_money
Is billing based on the number of sentences or requests?
keyboard_arrow_down
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.
attach_money
Is there a free trial available for new users?
keyboard_arrow_down
Yes. New users get an auto-generated API key with free tokens usable across any of our models. Once the free tokens are consumed, you can purchase additional tokens for the key in the 'Buy tokens' tab.
attach_money
Are tokens charged for failed requests?
keyboard_arrow_down
No, tokens are not deducted for failed requests.
attach_money
What payment methods are accepted?
keyboard_arrow_down
Payments are processed through Stripe, supporting a variety of payment methods including credit cards, Google Pay, and PayPal for your convenience.
attach_money
Is invoicing available for token purchases?
keyboard_arrow_down
For self-serve token purchases, Stripe issues an invoice to the email address associated with your Stripe account at the time of purchase. If you need a formal purchase order, a negotiated contract, procurement paperwork, or consolidated billing, that runs through Elastic rather than Stripe: contact Elastic Sales.
attach_money
How do I buy a commercial license rather than API tokens?
keyboard_arrow_down
Token purchases on this site cover use of the hosted Jina APIs. They do not license you to run the model weights in your own infrastructure. For that, Elastic has sold a commercial license as its own SKU since August 10, 2026, priced annually rather than per token. Contact Elastic Sales for a quote.
attach_money
Can I pay by invoice or purchase order instead of card?
keyboard_arrow_down
Self-serve token purchases are processed through Stripe and invoiced automatically to your Stripe account email. For purchase orders, procurement processes, or volumes above what self-serve top-up supports, contact Elastic Sales.
Current language / theme
Search Foundation
Reader
Embeddings
Reranker
Get Jina API key
Rate Limit
About us
News
Download Jina logo
open_in_new
Download Elastic logo
open_in_new
API Status
Elastic © 2026.SecurityTerms & ConditionsPrivacyManage CookiesDo Not Sell or Share My Personal Information
This website and all associated content, software, products, and services are intended for professional use only. No consumer use is intended or directed.