{"data":[{"id":"jina-ai/jina-vlm","hugging_face_id":"jinaai/jina-vlm","name":"Jina AI: Jina VLM","created":1764806400,"input_modalities":["text","image"],"output_modalities":["text"],"quantization":"","context_length":32768,"max_output_length":0,"pricing":{"prompt":"0.00000005","completion":"0","image":"0","request":"0","input_cache_read":"0","input_cache_write":"0"},"supported_sampling_parameters":[],"supported_features":[],"description":"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.","datacenters":[{"country_code":"US"}]},{"id":"jina-ai/jina-reranker-v3","hugging_face_id":"jinaai/jina-reranker-v3","name":"Jina AI: Jina Reranker v3","created":1759276800,"input_modalities":["text"],"output_modalities":["text"],"quantization":"","context_length":134144,"max_output_length":256,"pricing":{"prompt":"0.00000005","completion":"0","image":"0","request":"0","input_cache_read":"0","input_cache_write":"0"},"supported_sampling_parameters":[],"supported_features":[],"description":"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.","datacenters":[{"country_code":"US"}]},{"id":"jina-ai/jina-code-embeddings-0.5b","hugging_face_id":"jinaai/jina-code-embeddings-0.5b","name":"Jina AI: Jina Code Embeddings 0.5b","created":1756684800,"input_modalities":["text"],"output_modalities":["embeddings"],"quantization":"","context_length":32768,"max_output_length":896,"pricing":{"prompt":"0.00000005","completion":"0","image":"0","request":"0","input_cache_read":"0","input_cache_write":"0"},"supported_sampling_parameters":[],"supported_features":[],"description":"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.","datacenters":[{"country_code":"US"}]},{"id":"jina-ai/jina-code-embeddings-1.5b","hugging_face_id":"jinaai/jina-code-embeddings-1.5b","name":"Jina AI: Jina Code Embeddings 1.5b","created":1756684800,"input_modalities":["text"],"output_modalities":["embeddings"],"quantization":"","context_length":32768,"max_output_length":1536,"pricing":{"prompt":"0.00000005","completion":"0","image":"0","request":"0","input_cache_read":"0","input_cache_write":"0"},"supported_sampling_parameters":[],"supported_features":[],"description":"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.","datacenters":[{"country_code":"US"}]},{"id":"jina-ai/jina-embeddings-v4","hugging_face_id":"jinaai/jina-embeddings-v4","name":"Jina AI: Jina Embeddings v4","created":1750723200,"input_modalities":["text","image"],"output_modalities":["embeddings"],"quantization":"","context_length":32768,"max_output_length":2048,"pricing":{"prompt":"0.00000005","completion":"0","image":"0","request":"0","input_cache_read":"0","input_cache_write":"0"},"supported_sampling_parameters":[],"supported_features":[],"description":"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.","datacenters":[{"country_code":"US"}]},{"id":"jina-ai/jina-reranker-m0","hugging_face_id":"jinaai/jina-reranker-m0","name":"Jina AI: Jina Reranker M0","created":1744070400,"input_modalities":["text","image"],"output_modalities":["text"],"quantization":"","context_length":10240,"max_output_length":0,"pricing":{"prompt":"0.00000005","completion":"0","image":"0","request":"0","input_cache_read":"0","input_cache_write":"0"},"supported_sampling_parameters":[],"supported_features":[],"description":"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.","datacenters":[{"country_code":"US"}]},{"id":"jina-ai/ReaderLM-v2","hugging_face_id":"jinaai/ReaderLM-v2","name":"Jina AI: ReaderLM v2","created":1736985600,"input_modalities":["text"],"output_modalities":["text"],"quantization":"","context_length":524288,"max_output_length":0,"pricing":{"prompt":"0.00000005","completion":"0","image":"0","request":"0","input_cache_read":"0","input_cache_write":"0"},"supported_sampling_parameters":[],"supported_features":[],"description":"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.","datacenters":[{"country_code":"US"}]},{"id":"jina-ai/jina-clip-v2","hugging_face_id":"jinaai/jina-clip-v2","name":"Jina AI: Jina Clip v2","created":1730764800,"input_modalities":["text","image"],"output_modalities":["embeddings"],"quantization":"","context_length":8192,"max_output_length":1024,"pricing":{"prompt":"0.00000005","completion":"0","image":"0","request":"0","input_cache_read":"0","input_cache_write":"0"},"supported_sampling_parameters":[],"supported_features":[],"description":"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.","datacenters":[{"country_code":"US"}]},{"id":"jina-ai/jina-embeddings-v3","hugging_face_id":"jinaai/jina-embeddings-v3","name":"Jina AI: Jina Embeddings v3","created":1726617600,"input_modalities":["text"],"output_modalities":["embeddings"],"quantization":"","context_length":8192,"max_output_length":1024,"pricing":{"prompt":"0.00000005","completion":"0","image":"0","request":"0","input_cache_read":"0","input_cache_write":"0"},"supported_sampling_parameters":[],"supported_features":[],"description":"Jina Embeddings v3 is a groundbreaking multilingual text embedding model that transforms how organizations handle text understanding and retrieval across languages. At its core, it solves the critical challenge of maintaining high performance across multiple languages and tasks while keeping computational requirements manageable. The model particularly shines in production environments where efficiency matters - it achieves state-of-the-art performance with just 570M parameters, making it accessible for teams that can't afford the computational overhead of larger models. Organizations needing to build scalable, multilingual search systems or analyze content across language barriers will find this model especially valuable.","datacenters":[{"country_code":"US"}]},{"id":"jina-ai/jina-colbert-v2","hugging_face_id":"jinaai/jina-colbert-v2","name":"Jina AI: Jina Colbert v2","created":1725062400,"input_modalities":["text"],"output_modalities":["embeddings"],"quantization":"","context_length":8192,"max_output_length":128,"pricing":{"prompt":"0.00000005","completion":"0","image":"0","request":"0","input_cache_read":"0","input_cache_write":"0"},"supported_sampling_parameters":[],"supported_features":[],"description":"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.","datacenters":[{"country_code":"US"}]},{"id":"jina-ai/reader-lm-0.5b","hugging_face_id":"jinaai/reader-lm-0.5b","name":"Jina AI: Reader LM 0.5b","created":1723334400,"input_modalities":["text"],"output_modalities":["text"],"quantization":"","context_length":262144,"max_output_length":0,"pricing":{"prompt":"0.00000005","completion":"0","image":"0","request":"0","input_cache_read":"0","input_cache_write":"0"},"supported_sampling_parameters":[],"supported_features":[],"description":"Reader LM 0.5B is a specialized language model designed to solve the complex challenge of converting HTML documents into clean, structured markdown text. This model addresses a critical need in modern data processing pipelines: efficiently transforming messy web content into a format that's ideal for LLMs and documentation systems. Unlike general-purpose language models that require massive computational resources, Reader LM 0.5B achieves professional-grade HTML processing with just 494M parameters, making it accessible to teams with limited computing resources. Organizations dealing with web content processing, documentation automation, or building LLM-powered applications will find this model particularly valuable for streamlining their content preparation workflows.","datacenters":[{"country_code":"US"}]},{"id":"jina-ai/reader-lm-1.5b","hugging_face_id":"jinaai/reader-lm-1.5b","name":"Jina AI: Reader LM 1.5b","created":1723334400,"input_modalities":["text"],"output_modalities":["text"],"quantization":"","context_length":262144,"max_output_length":0,"pricing":{"prompt":"0.00000005","completion":"0","image":"0","request":"0","input_cache_read":"0","input_cache_write":"0"},"supported_sampling_parameters":[],"supported_features":[],"description":"Reader LM 1.5B represents a breakthrough in efficient document processing, addressing the critical challenge of converting complex web content into clean, structured formats. This specialized language model tackles a fundamental problem in modern AI pipelines: the need to efficiently process and clean HTML content for downstream tasks without relying on brittle rule-based systems or resource-intensive large language models. What makes this model truly remarkable is its ability to outperform models 50 times its size while maintaining a surprisingly compact 1.54B parameter footprint. Organizations dealing with large-scale web content processing, documentation automation, or content management systems will find this model particularly valuable for its ability to handle extremely long documents while delivering superior accuracy in HTML-to-markdown conversion.","datacenters":[{"country_code":"US"}]},{"id":"jina-ai/jina-reranker-v2-base-multilingual","hugging_face_id":"jinaai/jina-reranker-v2-base-multilingual","name":"Jina AI: Jina Reranker v2 Base Multilingual","created":1719273600,"input_modalities":["text"],"output_modalities":["text"],"quantization":"","context_length":1024,"max_output_length":0,"pricing":{"prompt":"0.00000005","completion":"0","image":"0","request":"0","input_cache_read":"0","input_cache_write":"0"},"supported_sampling_parameters":[],"supported_features":[],"description":"Jina Reranker v2 Base Multilingual is a cross-encoder model designed to enhance search accuracy across language barriers and data types. This reranker addresses the critical challenge of precise information retrieval in multilingual environments, particularly valuable for global enterprises needing to refine search results across different languages and content types. With support for over 100 languages and unique capabilities in function calling and code search, it serves as a unified solution for teams requiring accurate search refinement across international content, API documentation, and multilingual codebases. The model's compact 278M parameter design makes it particularly appealing for organizations seeking to balance high performance with resource efficiency.","datacenters":[{"country_code":"US"}]},{"id":"jina-ai/jina-clip-v1","hugging_face_id":"jinaai/jina-clip-v1","name":"Jina AI: Jina Clip v1","created":1717545600,"input_modalities":["text","image"],"output_modalities":["embeddings"],"quantization":"","context_length":8192,"max_output_length":768,"pricing":{"prompt":"0.00000005","completion":"0","image":"0","request":"0","input_cache_read":"0","input_cache_write":"0"},"supported_sampling_parameters":[],"supported_features":[],"description":"Jina CLIP v1 revolutionizes multimodal AI by being the first model to excel equally in both text-to-text and text-to-image retrieval tasks. Unlike traditional CLIP models that struggle with text-only scenarios, this model achieves state-of-the-art performance across all retrieval combinations while maintaining a remarkably compact 223M parameter size. The model addresses a critical industry challenge by eliminating the need for separate models for text and image processing, reducing system complexity and computational overhead. For teams building search systems, recommendation engines, or content analysis tools, Jina CLIP v1 offers a single, efficient solution that handles both text and visual content with exceptional accuracy.","datacenters":[{"country_code":"US"}]},{"id":"jina-ai/jina-reranker-v1-tiny-en","hugging_face_id":"jinaai/jina-reranker-v1-tiny-en","name":"Jina AI: Jina Reranker v1 Tiny EN","created":1713398400,"input_modalities":["text"],"output_modalities":["text"],"quantization":"","context_length":8192,"max_output_length":0,"pricing":{"prompt":"0.00000005","completion":"0","image":"0","request":"0","input_cache_read":"0","input_cache_write":"0"},"supported_sampling_parameters":[],"supported_features":[],"description":"Jina Reranker v1 Tiny English represents a breakthrough in efficient search refinement, designed specifically for organizations requiring high-performance reranking in resource-constrained environments. This model addresses the critical challenge of maintaining search quality while significantly reducing computational overhead and deployment costs. With just 33M parameters - a fraction of typical reranker sizes - it delivers remarkably competitive performance through innovative knowledge distillation techniques. The model's most surprising feature is its ability to process documents nearly five times faster than base models while maintaining over 92% of their accuracy, making enterprise-grade search refinement accessible to applications where computational resources are at a premium.","datacenters":[{"country_code":"US"}]},{"id":"jina-ai/jina-reranker-v1-turbo-en","hugging_face_id":"jinaai/jina-reranker-v1-turbo-en","name":"Jina AI: Jina Reranker v1 Turbo EN","created":1713398400,"input_modalities":["text"],"output_modalities":["text"],"quantization":"","context_length":8192,"max_output_length":0,"pricing":{"prompt":"0.00000005","completion":"0","image":"0","request":"0","input_cache_read":"0","input_cache_write":"0"},"supported_sampling_parameters":[],"supported_features":[],"description":"Jina Reranker v1 Turbo English addresses a critical challenge in production search systems: the trade-off between result quality and computational efficiency. While traditional rerankers offer improved search accuracy, their computational demands often make them impractical for real-time applications. This model breaks that barrier by delivering 95% of the base model's accuracy while processing documents three times faster and using 75% less memory. For organizations struggling with search latency or computational costs, this model offers a compelling solution that maintains high-quality search refinement while significantly reducing infrastructure requirements and operational costs.","datacenters":[{"country_code":"US"}]},{"id":"jina-ai/jina-reranker-v1-base-en","hugging_face_id":"jina-ai/jina-reranker-v1-base-en","name":"Jina AI: Jina Reranker v1 Base EN","created":1709164800,"input_modalities":["text"],"output_modalities":["text"],"quantization":"","context_length":8192,"max_output_length":0,"pricing":{"prompt":"0.00000005","completion":"0","image":"0","request":"0","input_cache_read":"0","input_cache_write":"0"},"supported_sampling_parameters":[],"supported_features":[],"description":"Jina Reranker v1 Base English revolutionizes search result refinement by addressing a critical limitation in traditional vector search systems: the inability to capture nuanced relationships between queries and documents. While vector search with cosine similarity provides fast initial results, it often misses subtle relevance signals that human users intuitively understand. This reranker bridges that gap by performing sophisticated token-level analysis of both queries and documents, delivering a remarkable 20% improvement in search accuracy. For organizations struggling with search precision or implementing RAG systems, this model offers a powerful solution that significantly improves result quality without requiring a complete overhaul of existing search infrastructure.","datacenters":[{"country_code":"US"}]},{"id":"jina-ai/jina-colbert-v1-en","hugging_face_id":"jinaai/jina-colbert-v1-en","name":"Jina AI: Jina Colbert v1 EN","created":1708128000,"input_modalities":["text"],"output_modalities":["text"],"quantization":"","context_length":8192,"max_output_length":128,"pricing":{"prompt":"0.00000005","completion":"0","image":"0","request":"0","input_cache_read":"0","input_cache_write":"0"},"supported_sampling_parameters":[],"supported_features":[],"description":"Jina-ColBERT-v1-en revolutionizes text search by solving a critical challenge in information retrieval: achieving high accuracy without sacrificing computational efficiency. Unlike traditional models that compress entire documents into single vectors, this model maintains precise token-level understanding while requiring only 137M parameters. For teams building search applications, recommendation systems, or content discovery platforms, Jina-ColBERT-v1-en eliminates the traditional trade-off between search quality and system performance. The model particularly shines in scenarios where nuanced text understanding is crucial, such as technical documentation search, academic paper retrieval, or any application where capturing subtle semantic relationships can make the difference between finding the right information and missing critical content.","datacenters":[{"country_code":"US"}]},{"id":"jina-ai/jina-embeddings-v2-base-es","hugging_face_id":"jinaai/jina-embeddings-v2-base-es","name":"Jina AI: Jina Embeddings v2 Base ES","created":1707868800,"input_modalities":["text"],"output_modalities":["embeddings"],"quantization":"","context_length":8192,"max_output_length":768,"pricing":{"prompt":"0.00000005","completion":"0","image":"0","request":"0","input_cache_read":"0","input_cache_write":"0"},"supported_sampling_parameters":[],"supported_features":[],"description":"Jina Embeddings v2 Base Spanish is a groundbreaking bilingual text embedding model that addresses the critical challenge of cross-lingual information retrieval and analysis between Spanish and English content. Unlike traditional multilingual models that often show bias towards specific languages, this model delivers truly balanced performance across both Spanish and English, making it indispensable for organizations operating in Spanish-speaking markets or handling bilingual content. The model's most remarkable feature is its ability to generate geometrically aligned embeddings - when texts in Spanish and English express the same meaning, their vector representations naturally cluster together in the embedding space, enabling seamless cross-language search and analysis.","datacenters":[{"country_code":"US"}]},{"id":"jina-ai/jina-embeddings-v2-base-code","hugging_face_id":"jinaai/jina-embeddings-v2-base-code","name":"Jina AI: Jina Embeddings v2 Base Code","created":1707091200,"input_modalities":["text"],"output_modalities":["embeddings"],"quantization":"","context_length":8192,"max_output_length":768,"pricing":{"prompt":"0.00000005","completion":"0","image":"0","request":"0","input_cache_read":"0","input_cache_write":"0"},"supported_sampling_parameters":[],"supported_features":[],"description":"Jina Embeddings v2 Base Code tackles a critical challenge in modern software development: efficiently navigating and understanding large codebases. For development teams struggling with code discovery and documentation, this model transforms how developers interact with code by enabling natural language search across 30 programming languages. Unlike traditional code search tools that rely on exact pattern matching, this model understands the semantic meaning behind code, allowing developers to find relevant code snippets using plain English descriptions. This capability is particularly valuable for teams maintaining large legacy codebases, developers onboarding to new projects, or organizations looking to improve code reuse and documentation practices.","datacenters":[{"country_code":"US"}]},{"id":"jina-ai/jina-embeddings-v2-base-de","hugging_face_id":"jinaai/jina-embeddings-v2-base-de","name":"Jina AI: Jina Embeddings v2 Base DE","created":1705276800,"input_modalities":["text"],"output_modalities":["embeddings"],"quantization":"","context_length":8192,"max_output_length":768,"pricing":{"prompt":"0.00000005","completion":"0","image":"0","request":"0","input_cache_read":"0","input_cache_write":"0"},"supported_sampling_parameters":[],"supported_features":[],"description":"Jina Embeddings v2 Base German addresses a critical challenge in international business: bridging the language gap between German and English markets. For German companies expanding into English-speaking territories, where a third of businesses generate over 20% of their global sales, accurate bilingual understanding is essential. This model transforms how organizations handle cross-language content by enabling seamless text understanding and retrieval in both German and English, making it invaluable for companies implementing international documentation systems, customer support platforms, or content management solutions. Unlike traditional translation-based approaches, this model directly maps equivalent meanings in both languages to the same embedding space, enabling more accurate and efficient bilingual operations.","datacenters":[{"country_code":"US"}]},{"id":"jina-ai/jina-embeddings-v2-base-zh","hugging_face_id":"jinaai/jina-embeddings-v2-base-zh","name":"Jina AI: Jina Embeddings v2 Base ZH","created":1704758400,"input_modalities":["text"],"output_modalities":["embeddings"],"quantization":"","context_length":8192,"max_output_length":768,"pricing":{"prompt":"0.00000005","completion":"0","image":"0","request":"0","input_cache_read":"0","input_cache_write":"0"},"supported_sampling_parameters":[],"supported_features":[],"description":"Jina Embeddings v2 Base Chinese breaks new ground as the first open-source model to seamlessly handle both Chinese and English text with an unprecedented 8,192 token context length. This bilingual powerhouse addresses a critical challenge in global business: the need for accurate, long-form document processing across Chinese and English content. Unlike traditional models that struggle with cross-lingual understanding or require separate models for each language, this model maps equivalent meanings in both languages to the same embedding space, making it invaluable for organizations expanding globally or managing multilingual content.","datacenters":[{"country_code":"US"}]},{"id":"jina-ai/jina-embeddings-v2-base-en","hugging_face_id":"jinaai/jina-embeddings-v2-base-en","name":"Jina AI: Jina Embeddings v2 Base EN","created":1698451200,"input_modalities":["text"],"output_modalities":["embeddings"],"quantization":"","context_length":8192,"max_output_length":768,"pricing":{"prompt":"0.00000005","completion":"0","image":"0","request":"0","input_cache_read":"0","input_cache_write":"0"},"supported_sampling_parameters":[],"supported_features":[],"description":"Jina Embeddings v2 Base English is a groundbreaking open-source text embedding model that solves the critical challenge of processing long documents while maintaining high accuracy. Organizations struggling with analyzing extensive legal documents, research papers, or financial reports will find this model particularly valuable. It stands out by handling documents up to 8,192 tokens in length—16 times longer than traditional models—while matching the performance of OpenAI's proprietary solutions. With a compact size of 0.27GB and efficient resource usage, it offers an accessible solution for teams seeking to implement advanced document analysis without excessive computational overhead.","datacenters":[{"country_code":"US"}]},{"id":"jina-ai/jina-embedding-b-en-v1","hugging_face_id":"jinaai/jina-embedding-b-en-v1","name":"Jina AI: Jina Embedding B EN v1","created":1686960000,"input_modalities":["text"],"output_modalities":["embeddings"],"quantization":"","context_length":512,"max_output_length":768,"pricing":{"prompt":"0.00000005","completion":"0","image":"0","request":"0","input_cache_read":"0","input_cache_write":"0"},"supported_sampling_parameters":[],"supported_features":[],"description":"Jina Embedding B v1 is a specialized text embedding model designed to transform English text into high-dimensional numerical representations while maintaining semantic meaning. The model addresses the critical need for efficient and accurate text embeddings in production environments, particularly valuable for organizations requiring a balance between computational efficiency and embedding quality. With its 110M parameters generating 768-dimensional embeddings, it serves as a practical solution for teams implementing semantic search, document clustering, or content recommendation systems without requiring extensive computational resources.","datacenters":[{"country_code":"US"}]},{"id":"jina-ai/jina-embeddings-v5-text-small","hugging_face_id":"jinaai/jina-embeddings-v5-text-small","name":"Jina AI: Jina Embeddings v5 Text Small","created":1739923200,"input_modalities":["text"],"output_modalities":["embeddings"],"quantization":"","context_length":32768,"max_output_length":1024,"pricing":{"prompt":"0.00000005","completion":"0","image":"0","request":"0","input_cache_read":"0","input_cache_write":"0"},"supported_sampling_parameters":[],"supported_features":[],"description":"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.","datacenters":[{"country_code":"US"}]},{"id":"jina-ai/jina-embeddings-v5-omni-small","hugging_face_id":"jinaai/jina-embeddings-v5-omni-small","name":"Jina AI: Jina Embeddings v5 Omni Small","created":1739923200,"input_modalities":["text","image","video","audio"],"output_modalities":["embeddings"],"quantization":"","context_length":32768,"max_output_length":1024,"pricing":{"prompt":"0.00000005","completion":"0","image":"0","request":"0","input_cache_read":"0","input_cache_write":"0"},"supported_sampling_parameters":[],"supported_features":[],"description":"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.","datacenters":[{"country_code":"US"}]},{"id":"jina-ai/jina-embeddings-v5-omni-nano","hugging_face_id":"jinaai/jina-embeddings-v5-omni-nano","name":"Jina AI: Jina Embeddings v5 Omni Nano","created":1739923200,"input_modalities":["text","image","video","audio"],"output_modalities":["embeddings"],"quantization":"","context_length":8192,"max_output_length":768,"pricing":{"prompt":"0.00000002","completion":"0","image":"0","request":"0","input_cache_read":"0","input_cache_write":"0"},"supported_sampling_parameters":[],"supported_features":[],"description":"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.","datacenters":[{"country_code":"US"}]},{"id":"jina-ai/jina-embeddings-v5-text-nano","hugging_face_id":"jinaai/jina-embeddings-v5-text-nano","name":"Jina AI: Jina Embeddings v5 Text Nano","created":1739923200,"input_modalities":["text"],"output_modalities":["embeddings"],"quantization":"","context_length":8192,"max_output_length":768,"pricing":{"prompt":"0.00000002","completion":"0","image":"0","request":"0","input_cache_read":"0","input_cache_write":"0"},"supported_sampling_parameters":[],"supported_features":[],"description":"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.","datacenters":[{"country_code":"US"}]}]}