Jina AI provides search foundation models and APIs for text, code and multimodal embeddings, reranking, document OCR, web reading, search and deep research. Hosted API pricing, Elastic access and self-hosted licenses are separate.
API models and prices · 17
Usage-based billing: text rates are usually per million tokens; other units and tiers are stated per entry. Compare only the same currency, unit and billing conditions. Unverified cache pricing does not mean free.
Jina OCR v1
Paid production API
Type / status: ocr / documented_api
Use cases: Document OCR, Document understanding
Supported languages: multilingual
Deployment options: api, huggingface, macos, license
Documented datacenters: US
Model release date: 2026-09-14
API endpoint: https://api.jina.ai/v1/chat/completions
Open-weights license (hosted API terms are separate): CC-BY-NC-4.0
Official catalog input-token price. Embeddings produce vectors and rerankers produce rankings, not billable generated output tokens. Zero catalog completion/image/request values do not make the service free. Reader API billing is separate from the model-catalog price.
The Reader page advertises 10 million free tokens for a new API key. Actual allocation and expiry are subject to the official account; this is a trial, not permanent free access.
Subject to hosted service terms; buying API tokens does not license model weights. Each model has its own weight license. CC-BY-NC-4.0 and Qwen Research License must not be described as unrestricted commercial self-hosting. Official FAQ states API requests, inputs and outputs are not used to train models. Jina legal page directs current data processing to Elastic's Data Processing Addendum. Model catalog lists US datacenters; Reader/Search also document EU endpoints. Do not infer identical regions across products.
Official documentation
Official model ID: jina-ai/jina-ocr-v1
Input / output: text, image, pdf → text
Model developer: Jina AI · Service provider: Jina AI
Model family: — · Currency: USD
Rates per million tokens| Price dimension | Current rate |
|---|
| Input | USD 0.5 |
|---|
| Output | USD 2 |
|---|
| Cached read | Unverified |
|---|
jina-ocr-v1 is a document OCR model served through the OpenAI chat completions schema: send a page image and it returns the transcription as text or markdown. The vision tower compresses a page into a small number of visual tokens before the language model reads them, so an A4 page costs roughly 903 input tokens regardless of how dense it is, and cost scales with what is transcribed rather than with page complexity. Structured extraction is supported through response_format with a JSON schema, and responses can be streamed. Endpoint and model identifier are declared in the current OpenAPI schema; authenticated inference was not executed. Endpoint support is documented; authenticated inference was not tested.
Documented API context: 32,768 tokens
Maximum output: 8,192 tokens
Official source · Last verified: 2026-10-15T09:33:13.684489+00:00
Jina VLM
Model catalog reference rate; endpoint billing unverified
The catalog rate does not establish the endpoint’s actual billing; excluded from lowest-cost comparisons.
Type / status: reader / beta_api_alias_pending
Use cases: Document understanding, Web content processing
Supported languages: multilingual
Deployment options: api, license, huggingface, airgapped
Documented datacenters: US
Model release date: 2025-12-04
API endpoint: https://api-beta-vlm.jina.ai/v1/chat/completions
Open-weights license (hosted API terms are separate): CC-BY-NC-4.0
Excluded from default production recommendations; check model availability, pricing and usage conditions.
Official catalog input-token price. Embeddings produce vectors and rerankers produce rankings, not billable generated output tokens. Zero catalog completion/image/request values do not make the service free. Reader API billing is separate from the model-catalog price.
The Reader page advertises 10 million free tokens for a new API key. Actual allocation and expiry are subject to the official account; this is a trial, not permanent free access.
Subject to hosted service terms; buying API tokens does not license model weights. Each model has its own weight license. CC-BY-NC-4.0 and Qwen Research License must not be described as unrestricted commercial self-hosting. Official FAQ states API requests, inputs and outputs are not used to train models. Jina legal page directs current data processing to Elastic's Data Processing Addendum. Model catalog lists US datacenters; Reader/Search also document EU endpoints. Do not infer identical regions across products.
Official documentation
Official model ID: jina-ai/jina-vlm
Input / output: text, image → text
Model developer: Jina AI · Service provider: Jina AI
Model family: — · Currency: USD
Rates per million tokens| Price dimension | Current rate |
|---|
| Input | USD 0.05 |
|---|
| Cached read | Unverified |
|---|
jina-vlm is a 2.4B parameter vision-language model that achieves state-of-the-art multilingual visual question answering among open 2B-scale VLMs. The model couples a SigLIP2-So400M vision encoder (449M parameters) with a Qwen3-1.7B language backbone through an attention-pooling connector that reduces visual tokens by 4× while preserving spatial information. Using overlapping image tiling with 12 tiles plus a global thumbnail, it processes images of arbitrary resolution up to 4K. Training data comprises approximately 5M multimodal samples and 12B text tokens across 29 languages, with roughly half in English and the remainder spanning high- and moderate-resource languages including Chinese, Arabic, German, Spanish, French, Italian, Japanese, Korean, and more. Official announcement uses jina-vlm on the beta chat endpoint, whose live model list identifies jina-vlm-v1. Reader also documents X-Respond-With: vlm. Alias and beta commercial availability require confirmation. Endpoint or model-list evidence is recorded; request compatibility and service-specific pricing require confirmation.
Documented API context: 32,768 tokens
Official source · Last verified: 2026-10-15T09:33:13.684489+00:00
Jina Reranker v3
Paid production API
Type / status: rerank / documented_api
Use cases: RAG, Document reranking
Supported languages: multilingual
Deployment options: elastic, api, huggingface, aws, azure, gcp, airgapped
Documented datacenters: US
Model release date: 2025-10-01
API endpoint: https://api.jina.ai/v1/rerank
Open-weights license (hosted API terms are separate): CC-BY-NC-4.0
Official catalog input-token price. Embeddings produce vectors and rerankers produce rankings, not billable generated output tokens. Zero catalog completion/image/request values do not make the service free. Reader API billing is separate from the model-catalog price.
The Reader page advertises 10 million free tokens for a new API key. Actual allocation and expiry are subject to the official account; this is a trial, not permanent free access.
Subject to hosted service terms; buying API tokens does not license model weights. Each model has its own weight license. CC-BY-NC-4.0 and Qwen Research License must not be described as unrestricted commercial self-hosting. Official FAQ states API requests, inputs and outputs are not used to train models. Jina legal page directs current data processing to Elastic's Data Processing Addendum. Model catalog lists US datacenters; Reader/Search also document EU endpoints. Do not infer identical regions across products.
Official documentation
Official model ID: jina-ai/jina-reranker-v3
Input / output: text → ranking
Model developer: Jina AI · Service provider: Jina AI
Model family: — · Currency: USD
Rates per million tokens| Price dimension | Current rate |
|---|
| Input | USD 0.05 |
|---|
| Cached read | Unverified |
|---|
jina-reranker-v3 is a 0.6B parameter multilingual document reranker introducing a novel last but not late interaction architecture. Unlike ColBERT's separate encoding with multi-vector matching, this model performs causal self-attention between query and documents within the same context window, enabling rich cross-document interactions before extracting contextual embeddings from the last token of each document. Built on Qwen3-0.6B with 28 transformer layers and a lightweight MLP projector (1024→512→256), it processes up to 64 documents simultaneously within 131K token context. The model achieves state-of-the-art BEIR performance with 61.94 nDCG-10 while being 10× smaller than generative listwise rerankers. Endpoint and model identifier are declared in the current OpenAPI schema; authenticated inference was not executed. Endpoint support is documented; authenticated inference was not tested. The output is ranking scores, not generated text tokens.
Documented API context: 134,144 tokens
Official source · Last verified: 2026-10-15T09:33:13.684489+00:00
Jina Reranker v3.5
Paid production API
Type / status: rerank / documented_api
Use cases: RAG, Document reranking
Supported languages: multilingual
Deployment options: elastic, api, huggingface, aws, azure, gcp, airgapped
Documented datacenters: US
Model release date: 2026-07-27
API endpoint: https://api.jina.ai/v1/rerank
Open-weights license (hosted API terms are separate): CC-BY-NC-4.0
Official catalog input-token price. Embeddings produce vectors and rerankers produce rankings, not billable generated output tokens. Zero catalog completion/image/request values do not make the service free. Reader API billing is separate from the model-catalog price.
The Reader page advertises 10 million free tokens for a new API key. Actual allocation and expiry are subject to the official account; this is a trial, not permanent free access.
Subject to hosted service terms; buying API tokens does not license model weights. Each model has its own weight license. CC-BY-NC-4.0 and Qwen Research License must not be described as unrestricted commercial self-hosting. Official FAQ states API requests, inputs and outputs are not used to train models. Jina legal page directs current data processing to Elastic's Data Processing Addendum. Model catalog lists US datacenters; Reader/Search also document EU endpoints. Do not infer identical regions across products.
Official documentation
Official model ID: jina-ai/jina-reranker-v3.5
Input / output: text → ranking
Model developer: Jina AI · Service provider: Jina AI
Model family: — · Currency: USD
Rates per million tokens| Price dimension | Current rate |
|---|
| Input | USD 0.05 |
|---|
| Cached read | Unverified |
|---|
jina-reranker-v3.5 is a 0.6B parameter multilingual listwise document reranker and a drop-in upgrade to jina-reranker-v3. It keeps the same last-but-not-late (LBNL) listwise interface — ranking a query against many candidates in a single forward pass — while improving domain robustness, structured-data ranking, multilingual retrieval, and inference efficiency. Built on Qwen3-0.6B with 28 layers using hybrid 3L2G attention (sliding-window layers, window 1024, interleaved with global-attention layers and a pinned terminal global layer required by LBNL) and a lightweight MLP projector (1024→512→512), it supports up to 131K tokens of context and ranks documents jointly via causal self-attention and cosine scoring. It reaches 63.20 nDCG@10 on BEIR — above the 4B Qwen3-Reranker at roughly 7× fewer parameters — while running 1.22×–1.56× faster than v3 across short-to-long contexts. Endpoint and model identifier are declared in the current OpenAPI schema; authenticated inference was not executed. Endpoint support is documented; authenticated inference was not tested. The output is ranking scores, not generated text tokens.
Documented API context: 131,072 tokens
Official source · Last verified: 2026-10-15T09:33:13.684489+00:00
Jina Code Embeddings 0.5b
Paid production API
Type / status: embedding / documented_api
Use cases: Code search, RAG
Embedding dimensions (not output tokens): 896
Supported languages: multilingual
Deployment options: api, huggingface, aws, azure, gcp, airgapped
Documented datacenters: US
Model release date: 2025-09-01
API endpoint: https://api.jina.ai/v1/embeddings
Open-weights license (hosted API terms are separate): CC-BY-NC-4.0
Official catalog input-token price. Embeddings produce vectors and rerankers produce rankings, not billable generated output tokens. Zero catalog completion/image/request values do not make the service free. Reader API billing is separate from the model-catalog price.
The Reader page advertises 10 million free tokens for a new API key. Actual allocation and expiry are subject to the official account; this is a trial, not permanent free access.
Subject to hosted service terms; buying API tokens does not license model weights. Each model has its own weight license. CC-BY-NC-4.0 and Qwen Research License must not be described as unrestricted commercial self-hosting. Official FAQ states API requests, inputs and outputs are not used to train models. Jina legal page directs current data processing to Elastic's Data Processing Addendum. Model catalog lists US datacenters; Reader/Search also document EU endpoints. Do not infer identical regions across products.
Official documentation
Official model ID: jina-ai/jina-code-embeddings-0.5b
Input / output: text → embedding
Model developer: Jina AI · Service provider: Jina AI
Model family: — · Currency: USD
- Input: USD 0.05 / 1,000,000 tokens
jina-code-embeddings-0.5b is a 494 million parameter code embedding model designed for retrieving code from natural language queries, technical Q&A, and identifying similar code across languages. Built on Qwen2.5-Coder-0.5B backbone, it generates embeddings via last-token pooling and addresses the fundamental limitation of traditional code embedding models that rely on scarce aligned data like comments and docstrings. The model leverages abundant unaligned code and documentation used in LLM training, achieving state-of-the-art performance despite its compact size. It supports five task categories with specific instruction prefixes: NL2Code, TechQA, Code2Code, Code2NL, and Code2Completion. The model implements Matryoshka representation learning for truncatable embeddings, allowing flexible precision-resource trade-offs. Endpoint and model identifier are declared in the current OpenAPI schema; authenticated inference was not executed. Endpoint support is documented; authenticated inference was not tested. Embedding dimensions are vector size, not generated tokens.
Documented API context: 32,768 tokens
Official source · Last verified: 2026-10-15T09:33:13.684489+00:00
Jina Code Embeddings 1.5b
Paid production API
Type / status: embedding / documented_api
Use cases: Code search, RAG
Embedding dimensions (not output tokens): 1536
Supported languages: multilingual
Deployment options: api, huggingface, aws, azure, gcp, airgapped
Documented datacenters: US
Model release date: 2025-09-01
API endpoint: https://api.jina.ai/v1/embeddings
Open-weights license (hosted API terms are separate): CC-BY-NC-4.0
Official catalog input-token price. Embeddings produce vectors and rerankers produce rankings, not billable generated output tokens. Zero catalog completion/image/request values do not make the service free. Reader API billing is separate from the model-catalog price.
The Reader page advertises 10 million free tokens for a new API key. Actual allocation and expiry are subject to the official account; this is a trial, not permanent free access.
Subject to hosted service terms; buying API tokens does not license model weights. Each model has its own weight license. CC-BY-NC-4.0 and Qwen Research License must not be described as unrestricted commercial self-hosting. Official FAQ states API requests, inputs and outputs are not used to train models. Jina legal page directs current data processing to Elastic's Data Processing Addendum. Model catalog lists US datacenters; Reader/Search also document EU endpoints. Do not infer identical regions across products.
Official documentation
Official model ID: jina-ai/jina-code-embeddings-1.5b
Input / output: text → embedding
Model developer: Jina AI · Service provider: Jina AI
Model family: — · Currency: USD
- Input: USD 0.05 / 1,000,000 tokens
jina-code-embeddings-1.5b is a 1.54 billion parameter model representing a significant advancement in code retrieval capabilities. Built on Qwen2.5-Coder-1.5B backbone with last-token pooling, it moves beyond traditional training on limited aligned data to leverage vast unaligned code and documentation corpora. The model implements comprehensive task-specific instructions across five categories: NL2Code, TechQA, Code2Code, Code2NL, and Code2Completion, each with distinct prefixes for queries and documents. Supports Matryoshka representation learning for flexible embedding truncation. Despite larger size, maintains practical deployment characteristics while achieving benchmark performance competitive with substantially larger alternatives. Endpoint and model identifier are declared in the current OpenAPI schema; authenticated inference was not executed. Endpoint support is documented; authenticated inference was not tested. Embedding dimensions are vector size, not generated tokens.
Documented API context: 32,768 tokens
Official source · Last verified: 2026-10-15T09:33:13.684489+00:00
Jina Embeddings v4
Paid production API
Type / status: embedding / documented_api
Use cases: RAG, Semantic search, Multimodal retrieval
Embedding dimensions (not output tokens): 2048
Supported languages: multilingual
Deployment options: api, huggingface, airgapped
Documented datacenters: US
Model release date: 2025-06-24
API endpoint: https://api.jina.ai/v1/embeddings
Open-weights license (hosted API terms are separate): Qwen Research License
Official catalog input-token price. Embeddings produce vectors and rerankers produce rankings, not billable generated output tokens. Zero catalog completion/image/request values do not make the service free. Reader API billing is separate from the model-catalog price.
The Reader page advertises 10 million free tokens for a new API key. Actual allocation and expiry are subject to the official account; this is a trial, not permanent free access.
Subject to hosted service terms; buying API tokens does not license model weights. Each model has its own weight license. CC-BY-NC-4.0 and Qwen Research License must not be described as unrestricted commercial self-hosting. Official FAQ states API requests, inputs and outputs are not used to train models. Jina legal page directs current data processing to Elastic's Data Processing Addendum. Model catalog lists US datacenters; Reader/Search also document EU endpoints. Do not infer identical regions across products.
Official documentation
Official model ID: jina-ai/jina-embeddings-v4
Input / output: text, image, pdf → embedding
Model developer: Jina AI · Service provider: Jina AI
Model family: — · Currency: USD
- Input: USD 0.05 / 1,000,000 tokens
Jina Embeddings V4 is a 3.8 billion parameter multimodal embedding model that provides unified text and image representation capabilities. Built on the Qwen2.5-VL-3B-Instruct backbone, the model features an architecture that supports both single-vector and multi-vector embeddings in the late interaction style, addressing limitations found in traditional CLIP-style dual-encoder models. The model incorporates three specialized task-specific LoRA adapters (60M parameters each) that optimize performance across different retrieval scenarios including asymmetric query-document retrieval, semantic text similarity, and code search without modifying the frozen backbone weights. The model demonstrates strong performance in processing visually rich content such as tables, charts, diagrams, screenshots, and mixed-media formats through a unified processing pathway that reduces the modality gap present in conventional architectures. Supporting multilingual capabilities, the model can handle input texts up to 32,768 tokens with images resized to 20 megapixels, making it suitable for various document retrieval and cross-modal search applications across different languages and domains. Endpoint and model identifier are declared in the current OpenAPI schema; authenticated inference was not executed. Endpoint support is documented; authenticated inference was not tested. Embedding dimensions are vector size, not generated tokens.
Documented API context: 32,768 tokens
Official source · Last verified: 2026-10-15T09:33:13.684489+00:00
Jina Reranker M0
Paid production API
Type / status: rerank / documented_api
Use cases: RAG, Document reranking
Supported languages: multilingual
Deployment options: api, license, huggingface, aws, azure, gcp, airgapped
Documented datacenters: US
Model release date: 2025-04-08
API endpoint: https://api.jina.ai/v1/rerank
Open-weights license (hosted API terms are separate): CC-BY-NC-4.0
Official catalog input-token price. Embeddings produce vectors and rerankers produce rankings, not billable generated output tokens. Zero catalog completion/image/request values do not make the service free. Reader API billing is separate from the model-catalog price.
The Reader page advertises 10 million free tokens for a new API key. Actual allocation and expiry are subject to the official account; this is a trial, not permanent free access.
Subject to hosted service terms; buying API tokens does not license model weights. Each model has its own weight license. CC-BY-NC-4.0 and Qwen Research License must not be described as unrestricted commercial self-hosting. Official FAQ states API requests, inputs and outputs are not used to train models. Jina legal page directs current data processing to Elastic's Data Processing Addendum. Model catalog lists US datacenters; Reader/Search also document EU endpoints. Do not infer identical regions across products.
Official documentation
Official model ID: jina-ai/jina-reranker-m0
Input / output: text, image → ranking
Model developer: Jina AI · Service provider: Jina AI
Model family: — · Currency: USD
Rates per million tokens| Price dimension | Current rate |
|---|
| Input | USD 0.05 |
|---|
| Cached read | Unverified |
|---|
jina-reranker-m0 is a groundbreaking multimodal multilingual reranker model designed to rank visual documents across multiple languages. What makes this model exceptional is its ability to process queries alongside visually rich document images—including pages with text, figures, tables, and various layouts—across 29 languages. The model outputs a ranked list of documents ordered by their relevance to the input query. Unlike previous rerankers that struggled with the "modality gap" problem (where images clustered near other images while text clustered near text), jina-reranker-m0 unifies textual and visual modalities in a single decoder-only model, creating a seamless multimodal search experience that can rank both images and text documents together effectively. Endpoint and model identifier are declared in the current OpenAPI schema; authenticated inference was not executed. Endpoint support is documented; authenticated inference was not tested. The output is ranking scores, not generated text tokens.
Documented API context: 10,240 tokens
Official source · Last verified: 2026-10-15T09:33:13.684489+00:00
ReaderLM v2
Model catalog reference rate; endpoint billing unverified
The catalog rate does not establish the endpoint’s actual billing; excluded from lowest-cost comparisons.
Type / status: reader / reader_api
Use cases: Document understanding, Web content processing
Supported languages: multilingual
Deployment options: reader-api, license, huggingface, aws, azure, gcp, airgapped
Documented datacenters: US
Model release date: 2025-01-16
API endpoint: https://r.jina.ai
Open-weights license (hosted API terms are separate): CC-BY-NC-4.0
Excluded from default production recommendations; check model availability, pricing and usage conditions.
Official catalog input-token price. Embeddings produce vectors and rerankers produce rankings, not billable generated output tokens. Zero catalog completion/image/request values do not make the service free. Reader API billing is separate from the model-catalog price.
The Reader page advertises 10 million free tokens for a new API key. Actual allocation and expiry are subject to the official account; this is a trial, not permanent free access.
Subject to hosted service terms; buying API tokens does not license model weights. Each model has its own weight license. CC-BY-NC-4.0 and Qwen Research License must not be described as unrestricted commercial self-hosting. Official FAQ states API requests, inputs and outputs are not used to train models. Jina legal page directs current data processing to Elastic's Data Processing Addendum. Model catalog lists US datacenters; Reader/Search also document EU endpoints. Do not infer identical regions across products.
Official documentation
Official model ID: jina-ai/ReaderLM-v2
Input / output: text → text
Model developer: Jina AI · Service provider: Jina AI
Model family: — · Currency: USD
Rates per million tokens| Price dimension | Current rate |
|---|
| Input | USD 0.05 |
|---|
| Cached read | Unverified |
|---|
ReaderLM-v2 is a 1.5B parameter language model that converts raw HTML into markdown or JSON, handling up to 512K tokens combined input/output length with support for 29 languages. Unlike its predecessor that treated HTML-to-markdown as a 'selective-copy' task, v2 approaches it as a translation process, enabling superior handling of complex elements like code fences, nested lists, tables, and LaTeX equations. The model maintains consistent performance across varying context lengths and introduces direct HTML-to-JSON generation capabilities with predefined schemas. Use Reader API with X-Respond-With: readerlm-v2. The main chat completions endpoint only accepts jina-ocr-v1. Endpoint or model-list evidence is recorded; request compatibility and service-specific pricing require confirmation.
Documented API context: 524,288 tokens
Official source · Last verified: 2026-10-15T09:33:13.684489+00:00
Jina Clip v2
Paid production API
Type / status: embedding / documented_api
Use cases: RAG, Semantic search, Multimodal retrieval
Embedding dimensions (not output tokens): 1024
Supported languages: multilingual
Deployment options: elastic, api, license, huggingface, aws, azure, gcp, airgapped
Documented datacenters: US
Model release date: 2024-11-05
API endpoint: https://api.jina.ai/v1/embeddings
Open-weights license (hosted API terms are separate): CC-BY-NC-4.0
Official catalog input-token price. Embeddings produce vectors and rerankers produce rankings, not billable generated output tokens. Zero catalog completion/image/request values do not make the service free. Reader API billing is separate from the model-catalog price.
The Reader page advertises 10 million free tokens for a new API key. Actual allocation and expiry are subject to the official account; this is a trial, not permanent free access.
Subject to hosted service terms; buying API tokens does not license model weights. Each model has its own weight license. CC-BY-NC-4.0 and Qwen Research License must not be described as unrestricted commercial self-hosting. Official FAQ states API requests, inputs and outputs are not used to train models. Jina legal page directs current data processing to Elastic's Data Processing Addendum. Model catalog lists US datacenters; Reader/Search also document EU endpoints. Do not infer identical regions across products.
Official documentation
Official model ID: jina-ai/jina-clip-v2
Input / output: text, image → embedding
Model developer: Jina AI · Service provider: Jina AI
Model family: — · Currency: USD
- Input: USD 0.05 / 1,000,000 tokens
Jina CLIP v2 revolutionizes multimodal AI by bridging the gap between visual and textual understanding across 89 languages. This model solves critical challenges in global e-commerce, content management, and cross-cultural communication by enabling accurate image-text matching regardless of language barriers. For businesses expanding internationally or managing multilingual content, it eliminates the need for separate models per language or complex translation pipelines. The model particularly shines in scenarios requiring precise visual search across language boundaries, such as global marketplace product discovery or multilingual digital asset management. Endpoint and model identifier are declared in the current OpenAPI schema; authenticated inference was not executed. Endpoint support is documented; authenticated inference was not tested. Embedding dimensions are vector size, not generated tokens.
Documented API context: 8,192 tokens
Official source · Last verified: 2026-10-15T09:33:13.684489+00:00
Jina Colbert v2
Paid production API
Type / status: embedding / documented_api
Use cases: RAG, Semantic search
Embedding dimensions (not output tokens): 128
Supported languages: multilingual
Deployment options: api, license, huggingface, aws, azure, gcp, airgapped
Documented datacenters: US
Model release date: 2024-08-31
API endpoint: https://api.jina.ai/v1/embeddings
Open-weights license (hosted API terms are separate): CC-BY-NC-4.0
Official catalog input-token price. Embeddings produce vectors and rerankers produce rankings, not billable generated output tokens. Zero catalog completion/image/request values do not make the service free. Reader API billing is separate from the model-catalog price.
The Reader page advertises 10 million free tokens for a new API key. Actual allocation and expiry are subject to the official account; this is a trial, not permanent free access.
Subject to hosted service terms; buying API tokens does not license model weights. Each model has its own weight license. CC-BY-NC-4.0 and Qwen Research License must not be described as unrestricted commercial self-hosting. Official FAQ states API requests, inputs and outputs are not used to train models. Jina legal page directs current data processing to Elastic's Data Processing Addendum. Model catalog lists US datacenters; Reader/Search also document EU endpoints. Do not infer identical regions across products.
Official documentation
Official model ID: jina-ai/jina-colbert-v2
Input / output: text → multi-vector
Model developer: Jina AI · Service provider: Jina AI
Model family: — · Currency: USD
- Input: USD 0.05 / 1,000,000 tokens
Jina-ColBERT-v2 is a groundbreaking multilingual information retrieval model that solves the critical challenge of efficient, high-quality search across multiple languages. As the first multilingual ColBERT-like model to generate compact embeddings, it addresses the growing need for scalable, cost-effective multilingual search solutions in global applications. Organizations dealing with multilingual content, from e-commerce platforms to content management systems, can leverage this model to provide accurate search results across 89 languages while significantly reducing storage and computational costs through its innovative dimension reduction capabilities. Endpoint and model identifier are declared in the current OpenAPI schema; authenticated inference was not executed. Endpoint support is documented; authenticated inference was not tested. Embedding dimensions are vector size, not generated tokens.
Documented API context: 8,192 tokens
Official source · Last verified: 2026-10-15T09:33:13.684489+00:00
Jina Embeddings v5 Text Small
Paid production API
Type / status: embedding / documented_api
Use cases: RAG, Semantic search
Embedding dimensions (not output tokens): 1024
Supported languages: multilingual
Deployment options: elastic, api, aws, huggingface, airgapped
Documented datacenters: US
Model release date: 2026-02-18
API endpoint: https://api.jina.ai/v1/embeddings
Open-weights license (hosted API terms are separate): CC-BY-NC-4.0
Official catalog input-token price. Embeddings produce vectors and rerankers produce rankings, not billable generated output tokens. Zero catalog completion/image/request values do not make the service free. Reader API billing is separate from the model-catalog price.
The Reader page advertises 10 million free tokens for a new API key. Actual allocation and expiry are subject to the official account; this is a trial, not permanent free access.
Subject to hosted service terms; buying API tokens does not license model weights. Each model has its own weight license. CC-BY-NC-4.0 and Qwen Research License must not be described as unrestricted commercial self-hosting. Official FAQ states API requests, inputs and outputs are not used to train models. Jina legal page directs current data processing to Elastic's Data Processing Addendum. Model catalog lists US datacenters; Reader/Search also document EU endpoints. Do not infer identical regions across products.
Official documentation
Official model ID: jina-ai/jina-embeddings-v5-text-small
Input / output: text → embedding
Model developer: Jina AI · Service provider: Jina AI
Model family: — · Currency: USD
- Input: USD 0.05 / 1,000,000 tokens
Jina Embeddings v5 Text Small is a multilingual text embedding model with 677M parameters built on the Qwen3-0.6B-Base backbone. It supports 32K context length and produces 1024-dimensional embeddings with Matryoshka representation learning (down to 32 dimensions). It uses last-token pooling and supports retrieval, text-matching, clustering, and classification tasks. Endpoint and model identifier are declared in the current OpenAPI schema; authenticated inference was not executed. Endpoint support is documented; authenticated inference was not tested. Embedding dimensions are vector size, not generated tokens.
Documented API context: 32,768 tokens
Official source · Last verified: 2026-10-15T09:33:13.684489+00:00
Jina Embeddings v5 Omni Small
Paid production API
Type / status: embedding / documented_api
Use cases: RAG, Semantic search, Multimodal retrieval
Embedding dimensions (not output tokens): 1024
Supported languages: multilingual
Deployment options: elastic, api, aws, huggingface, macos, airgapped
Documented datacenters: US
Model release date: 2026-05-07
API endpoint: https://api.jina.ai/v1/embeddings
Open-weights license (hosted API terms are separate): CC-BY-NC-4.0
Official catalog input-token price. Embeddings produce vectors and rerankers produce rankings, not billable generated output tokens. Zero catalog completion/image/request values do not make the service free. Reader API billing is separate from the model-catalog price.
The Reader page advertises 10 million free tokens for a new API key. Actual allocation and expiry are subject to the official account; this is a trial, not permanent free access.
Subject to hosted service terms; buying API tokens does not license model weights. Each model has its own weight license. CC-BY-NC-4.0 and Qwen Research License must not be described as unrestricted commercial self-hosting. Official FAQ states API requests, inputs and outputs are not used to train models. Jina legal page directs current data processing to Elastic's Data Processing Addendum. Model catalog lists US datacenters; Reader/Search also document EU endpoints. Do not infer identical regions across products.
Official documentation
Official model ID: jina-ai/jina-embeddings-v5-omni-small
Input / output: text, image, video, audio, pdf → embedding
Model developer: Jina AI · Service provider: Jina AI
Model family: — · Currency: USD
- Input: USD 0.05 / 1,000,000 tokens
Jina Embeddings v5 Omni Small is a multilingual multimodal embedding model with 1.66B parameters built on the jina-embeddings-v5-text-small text backbone, extended with a fine-tuned SigLIP2 So400m vision encoder (from Qwen3.5-2B) for image and video and a Whisper-large-v3 audio encoder (from Qwen2.5-Omni-7B), connected via trained cross-modal projectors. It supports 32K context length and produces 1024-dimensional embeddings with Matryoshka representation learning (down to 32 dimensions). It uses last-token pooling and supports retrieval, text-matching, clustering, and classification tasks across text, image, video, audio, and PDF inputs. Endpoint and model identifier are declared in the current OpenAPI schema; authenticated inference was not executed. Endpoint support is documented; authenticated inference was not tested. Embedding dimensions are vector size, not generated tokens.
Documented API context: 32,768 tokens
Official source · Last verified: 2026-10-15T09:33:13.684489+00:00
Jina Embeddings v5 Omni Nano
Paid production API
Type / status: embedding / documented_api
Use cases: RAG, Semantic search, Multimodal retrieval
Embedding dimensions (not output tokens): 768
Supported languages: multilingual
Deployment options: elastic, api, aws, huggingface, macos, airgapped
Documented datacenters: US
Model release date: 2026-05-07
API endpoint: https://api.jina.ai/v1/embeddings
Open-weights license (hosted API terms are separate): CC-BY-NC-4.0
Official catalog input-token price. Embeddings produce vectors and rerankers produce rankings, not billable generated output tokens. Zero catalog completion/image/request values do not make the service free. Reader API billing is separate from the model-catalog price.
The Reader page advertises 10 million free tokens for a new API key. Actual allocation and expiry are subject to the official account; this is a trial, not permanent free access.
Subject to hosted service terms; buying API tokens does not license model weights. Each model has its own weight license. CC-BY-NC-4.0 and Qwen Research License must not be described as unrestricted commercial self-hosting. Official FAQ states API requests, inputs and outputs are not used to train models. Jina legal page directs current data processing to Elastic's Data Processing Addendum. Model catalog lists US datacenters; Reader/Search also document EU endpoints. Do not infer identical regions across products.
Official documentation
Official model ID: jina-ai/jina-embeddings-v5-omni-nano
Input / output: text, image, video, audio, pdf → embedding
Model developer: Jina AI · Service provider: Jina AI
Model family: — · Currency: USD
- Input: USD 0.02 / 1,000,000 tokens
Jina Embeddings v5 Omni Nano is a lightweight multilingual multimodal embedding model with 1.004B parameters built on the jina-embeddings-v5-text-nano text backbone, extended with a fine-tuned SigLIP2 Base vision encoder (from Qwen3.5-0.8B) for image and video and a Whisper-large-v3 audio encoder (from Qwen2.5-Omni-7B), connected via trained cross-modal projectors. It supports 8K context length and produces 768-dimensional embeddings with Matryoshka representation learning (down to 32 dimensions). It uses last-token pooling and supports retrieval, text-matching, clustering, and classification tasks across text, image, video, audio, and PDF inputs. Endpoint and model identifier are declared in the current OpenAPI schema; authenticated inference was not executed. Endpoint support is documented; authenticated inference was not tested. Embedding dimensions are vector size, not generated tokens.
Documented API context: 8,192 tokens
Official source · Last verified: 2026-10-15T09:33:13.684489+00:00
Jina Embeddings v5 Text Nano
Paid production API
Type / status: embedding / documented_api
Use cases: RAG, Semantic search
Embedding dimensions (not output tokens): 768
Supported languages: multilingual
Deployment options: elastic, api, aws, huggingface, airgapped
Documented datacenters: US
Model release date: 2026-02-18
API endpoint: https://api.jina.ai/v1/embeddings
Open-weights license (hosted API terms are separate): CC-BY-NC-4.0
Official catalog input-token price. Embeddings produce vectors and rerankers produce rankings, not billable generated output tokens. Zero catalog completion/image/request values do not make the service free. Reader API billing is separate from the model-catalog price.
The Reader page advertises 10 million free tokens for a new API key. Actual allocation and expiry are subject to the official account; this is a trial, not permanent free access.
Subject to hosted service terms; buying API tokens does not license model weights. Each model has its own weight license. CC-BY-NC-4.0 and Qwen Research License must not be described as unrestricted commercial self-hosting. Official FAQ states API requests, inputs and outputs are not used to train models. Jina legal page directs current data processing to Elastic's Data Processing Addendum. Model catalog lists US datacenters; Reader/Search also document EU endpoints. Do not infer identical regions across products.
Official documentation
Official model ID: jina-ai/jina-embeddings-v5-text-nano
Input / output: text → embedding
Model developer: Jina AI · Service provider: Jina AI
Model family: — · Currency: USD
- Input: USD 0.02 / 1,000,000 tokens
Jina Embeddings v5 Text Nano is a lightweight multilingual text embedding model with 239M parameters built on the EuroBERT-210M backbone. It supports 8K context length and produces 768-dimensional embeddings with Matryoshka representation learning (down to 32 dimensions). It uses last-token pooling and supports retrieval, text-matching, clustering, and classification tasks. Endpoint and model identifier are declared in the current OpenAPI schema; authenticated inference was not executed. Endpoint support is documented; authenticated inference was not tested. Embedding dimensions are vector size, not generated tokens.
Documented API context: 8,192 tokens
Official source · Last verified: 2026-10-15T09:33:13.684489+00:00
Jina DeepSearch v1
Pricing Not Public
Endpoint billing is unverified; excluded from lowest-cost comparisons.
Type / status: search / listed_independent_api
Use cases: Deep Research, AI search
Deployment options: independent_hosted_api
API endpoint: https://deepsearch.jina.ai/v1/chat/completions
Excluded from default production recommendations; check model availability, pricing and usage conditions.
Search, reading and reasoning share a token budget; no verified conversion to USD or evidence that model-catalog embedding rates apply.
DeepSearch trial eligibility and sharing of the ordinary API trial balance are unverified; the Reader-advertised allocation does not establish a DeepSearch allowance.
Subject to hosted service terms; buying API tokens does not license model weights. Each model has its own weight license. CC-BY-NC-4.0 and Qwen Research License must not be described as unrestricted commercial self-hosting. Official FAQ states API requests, inputs and outputs are not used to train models. Jina legal page directs current data processing to Elastic's Data Processing Addendum. Model catalog lists US datacenters; Reader/Search also document EU endpoints. Do not infer identical regions across products.
Official documentation
Official model ID: jina-deepsearch-v1
Input / output: text, image, file, pdf → text
Model developer: Jina AI · Service provider: Jina AI
Model family: — · Model catalog only; see service-channel quotes
Iterative web search, page reading and reasoning with a shared token budget. The independent DeepSearch model endpoint lists this model; exact unit costs are not publicly verified. Listed by the independent /v1/models endpoint. The official integration example uses jina-deepsearch-v1. Authenticated inference and v2 capabilities were not tested. Endpoint or model-list evidence is recorded; request compatibility and service-specific pricing require confirmation.
Official source · Last verified: 2026-10-15T09:33:13.684489+00:00
Jina DeepSearch v2
Pricing Not Public
Endpoint billing is unverified; excluded from lowest-cost comparisons.
Type / status: search / listed_independent_api
Use cases: Deep Research, AI search
Deployment options: independent_hosted_api
API endpoint: https://deepsearch.jina.ai/v1/chat/completions
Excluded from default production recommendations; check model availability, pricing and usage conditions.
Search, reading and reasoning share a token budget; no verified conversion to USD or evidence that model-catalog embedding rates apply.
DeepSearch trial eligibility and sharing of the ordinary API trial balance are unverified; the Reader-advertised allocation does not establish a DeepSearch allowance.
Subject to hosted service terms; buying API tokens does not license model weights. Each model has its own weight license. CC-BY-NC-4.0 and Qwen Research License must not be described as unrestricted commercial self-hosting. Official FAQ states API requests, inputs and outputs are not used to train models. Jina legal page directs current data processing to Elastic's Data Processing Addendum. Model catalog lists US datacenters; Reader/Search also document EU endpoints. Do not infer identical regions across products.
Official documentation
Official model ID: jina-deepsearch-v2
Input / output: — → text
Model developer: Jina AI · Service provider: Jina AI
Model family: — · Model catalog only; see service-channel quotes
Iterative web search, page reading and reasoning with a shared token budget. The independent DeepSearch model endpoint lists this model; exact unit costs are not publicly verified. Listed by the independent /v1/models endpoint. The official integration example uses jina-deepsearch-v1. Authenticated inference and v2 capabilities were not tested. Endpoint or model-list evidence is recorded; request compatibility and service-specific pricing require confirmation.
Official source · Last verified: 2026-10-15T09:33:13.684489+00:00
