AI Model Library.

Claude Fable 5: Anthropic's model for creative generation. It brings strong tone, voice, and coherence to long-form writing across styles. It's ideal for storytelling, content creation, and rich creative work.

Claude Sonnet 5: The balance of intelligence and speed. Building on Claude Sonnet 4.5, it sharpens reasoning, coding, and analysis for everyday production work. It's ideal for scalable applications that need strong quality at a practical cost.

Claude Haiku 4.5: The next generation of speed and intelligence. Building on Claude Haiku 4, it improves instruction following and accuracy while staying fast and cost-efficient. It's ideal for user-facing products and high-volume, real-time experiences.

Claude Opus 4.8: Anthropic's most capable model. Building on Claude Opus 4, it delivers deeper reasoning, stronger coding, and reliable long-horizon agentic performance. It's ideal for the most complex, high-stakes tasks where quality matters most.

Claude Haiku 4.5 revolutionizes business efficiency by powering real-time customer service, coding sub-agents, and complex data analysis with unprecedented speed and cost-effectiveness for high-volume user experiences.

Claude 3.5 Sonnet v2 boasts enhanced coding and agentic task performance, plus a new computer interaction feature (public beta), all at the same price as its predecessor.

Claude 3.5 Haiku: The next generation of speed and intelligence. Building on the success of Claude 3 Haiku, this model boasts improved instruction following and accuracy. It's ideal for user-facing products and generating personalized experiences.

Unlock advanced reasoning capabilities with Claude 3.7 Sonnet. Its enhanced performance in coding, math, and instruction-following makes it a superior choice for complex tasks. Improve your workflow today!

Claude 3.5 Sonnet is an advanced AI model that excels in complex tasks such as customer support, coding, data analysis, and visual processing. It delivers high-quality results with the speed and cost efficiency of our mid-tier model, Claude 3 Sonnet, making it invaluable for advanced AI applications.

Claude 3 Opus is Anthropic's most powerful AI model, with state-of-the-art performance on complex tasks. It handles open-ended prompts and unseen scenarios with fluency and human-like understanding. With a 200K context window, it supports both text and image processing effectively.

Claude 3 Sonnet by Anthropic balances intelligence and speed, ideal for enterprise workloads. It provides maximum utility at a lower price, engineered for robust AI deployments. With a 200K context window, it supports both text and image processing effectively.

Claude 3 Haiku is Anthropic's fastest, most compact model for near-instant responsiveness, designed to handle simple queries and requests quickly. With a 200K context window, it excels in rapid interaction and supports both text and image inputs efficiently.

Powered by large-scale reinforcement learning, DeepSeek R1 Converse delivers intelligent dialogue experiences through state-of-the-art reasoning models that dynamically adapt to complex communication challenges across technical and linguistic domains.

DeepSeek R1 Text delivers advanced text generation capabilities, utilizing reinforcement learning to produce precise, coherent content across English and Chinese languages. Engineered for complex reasoning tasks, this model excels in generating high-quality text with remarkable accuracy and contextual understanding.

Gemini 3 Pro Image handles intricate image generation through built-in reasoning processes. When faced with complex or multi-step image tasks, it analyzes requirements thoroughly before responding, resulting in higher accuracy and visually superior output.

Google Veo 3.1 offers advanced spatio-temporal synthesis and cinematic motion generation for professional video workflows. With a 4-million-frame context window, it processes complex narrative prompts while maintaining temporal coherence and high-fidelity visual continuity. Integrated tool support enhances functionality for creators building dynamic video applications through Google AI Studio and Vertex AI platforms.

Nano Banana offers advanced visual synthesis and context-aware image generation for creative and design workflows. With a high-resolution multimodal architecture, it processes complex textual prompts while maintaining photorealistic detail and stylistic coherence. Integrated tool support enhances functionality for creators building specialized visual applications through Google AI Studio and Vertex AI platforms.

Gemini 2.0 Pro Experimental offers advanced coding capabilities and complex problem-solving features for technical workflows. With a 2-million-token context window, it processes extensive datasets while maintaining precision in code generation and logical reasoning. Integrated tool support enhances functionality for developers building specialized applications through Google AI Studio and Vertex AI platforms.

Gemini 2.0 Flash enables dynamic storytelling through integrated text and image generation. Developers can create illustrated narratives with consistent characters and settings, refining outputs through natural language feedback. This multimodal approach supports iterative creative processes while maintaining visual coherence across multiple scenes.

Gemini 1.5 Pro sets a new standard for AI models with its two-million-token context window. This groundbreaking feature enables Gemini 1.5 Pro to handle massive amounts of information with unparalleled accuracy and recall, paving the way for more efficient and powerful data analysis. Gemini 1.5 Pro's capabilities redefine the boundaries of AI. 

Gemini 1.5 Flash excels in high-volume, high-frequency tasks, offering a perfect balance of cost-effectiveness and low latency. This model delivers quality comparable to other Gemini Pro versions, but at a fraction of the cost. Ideal for businesses needing quick, efficient AI processing without compromising on performance, Gemini 1.5 Flash is the go-to solution for optimizing AI operations.

Azure PII Extraction is a powerful tool for identifying and managing sensitive information. It uses advanced algorithms to detect and extract personally identifiable information from various data sources. This process helps businesses comply with data protection regulations and safeguard customer privacy effectively.

Azure Document Intelligence transforms documents into actionable data. This AI-powered service accurately extracts text, key-value pairs, and tables from various document types without manual labeling or complex coding. Streamline your document processing with custom forms, prebuilt APIs, and layout analysis for efficient information retrieval.

Azure AI Speech Recognition is a sophisticated service that converts spoken language into written text with high precision. Leveraging advanced neural network models, it offers exceptional accuracy and supports a wide range of languages and dialects, making it an invaluable tool for various applications.

Azure AI Speech Synthesis is a powerful text-to-speech service designed to convert written text into lifelike spoken words. Utilizing advanced deep learning models, it delivers high-quality, natural-sounding speech synthesis that enhances user interactions and accessibility.

DALL·E 3 delivers superior image generation by understanding complex prompts with unprecedented precision. This advanced AI tool produces highly accurate visual outputs.

O1 Mini: A cost-effective large language model excelling in STEM reasoning. Achieves impressive results in mathematics, coding, and other STEM fields, making it a powerful tool for various applications.

GPT-4o Mini is a highly efficient and compact variant of OpenAI’s GPT-4o model, designed to deliver robust natural language generation with optimized performance and resource usage. It is ideal for applications requiring both high capability and efficient operation.

GPT-4o is a state-of-the-art language model by OpenAI, designed to generate human-like text with advanced capabilities in understanding and creating contextually relevant content. It excels in various applications, from complex reasoning to generating coherent text across diverse topics.

GPT-4 Turbo is a highly efficient and scalable variant of GPT-4, designed to provide rapid, high-quality text generation and advanced natural language understanding. It is optimized for performance, making it suitable for applications requiring both speed and precision.

Ada 002 embedding offers powerful text representation capabilities, transforming words into numerical vectors. This model excels in capturing semantic relationships, enabling efficient similarity searches and enhancing natural language understanding tasks. Its compact yet expressive embeddings make it ideal for various AI applications, from content recommendation to semantic analysis.

The META Llama 3.3 70B Instruct model delivers enterprise-grade performance matching higher-tier AI systems while reducing operational costs. Designed for complex analytical tasks and technical implementations, this version provides precise instruction processing ideal for developers building specialized applications. Organizations can maintain cutting-edge capabilities without infrastructure overhead through optimized resource efficiency.

Meta Llama 3.1 405B Instruct, the pinnacle of Llama 3.1 models, offers unparalleled capabilities in conversational AI. With 405 billion parameters, it excels in multilingual dialogue, reasoning, and data generation. This powerhouse model is ideal for businesses seeking cutting-edge language solutions, supporting diverse applications.

Meta LLaMA 3.1 70B Instruct boasts a 128K context window, elevating its ability to handle complex inputs. This model excels in multilingual tasks, advanced reasoning, and instruction-based generation. With enhanced contextual understanding and translation capabilities, it's ideal for diverse AI applications, from conversational systems to synthetic data creation.

Meta Llama 3.1 8B Instruct: A powerful language model with 128K context length, excelling in multilingual applications. It offers enhanced dialogue capabilities, complex reasoning, and precise instruction following. Ideal for advanced conversational AI, it delivers accurate, contextually relevant responses across diverse linguistic scenarios.

Amazon Titan V2 embedding delivers state-of-the-art text representation, transforming documents into highly accurate numerical vectors. This model excels in capturing deep semantic context, enabling superior similarity searches and powering high-performance RAG systems. Its robust and nuanced embeddings make it ideal for enterprise-grade AI applications, from precise document retrieval to advanced semantic analysis.

Amazon Nova Pro is a top-tier multimodal model, offering unmatched accuracy, speed, and cost-efficiency. It's perfect for tasks like video summarization, Q&A, mathematical reasoning, software development, and AI agents capable of executing multistep workflows.

Amazon Nova Micro is a text-only model that offers ultra-fast responses at a minimal cost. It excels in language understanding, translation, reasoning, code completion, brainstorming, and mathematical problem-solving. Its generation speed of over 200 tokens per second makes it perfect for applications needing quick responses.

Amazon Nova Lite is a low-cost, high-speed multimodal model processing images, video, and text. Its accuracy and speed make it ideal for interactive and high-volume applications where cost is crucial. Supports various languages and fine-tuning options.

Comprehend Targeted Sentiment Analysis precisely evaluates sentiment for specific entities within text. This powerful tool identifies positive, neutral, negative, or mixed feelings towards particular subjects, offering businesses deep insights into customer opinions and market trends.

Comprehend Syntax Analysis breaks down text into its grammatical components, identifying parts of speech for each word. This powerful feature enables businesses to extract valuable insights from unstructured data, improving content analysis and enhancing natural language processing capabilities.

Amazon Comprehend Key Phrases API identifies and extracts important phrases from text data. It processes documents to find key information, such as names, places, and events. This powerful tool enhances content analysis, enabling a better understanding of documents' main topics and themes.

Amazon Comprehend Entities Insights identifies key entities within text, offering a deeper understanding of  content. This powerful tool identifies people, places, and organizations, allowing the extraction of valuable information effortlessly. Enhance data analysis with precise entity recognition, enabling more informed decision-making and targeted content strategies.

Amazon's Comprehend Detect PII API pinpoints locations of selected Personally Identifiable Information (PII) entities within documents. This powerful tool enables businesses to create redacted versions, enhancing data privacy and compliance. Our API offers precise identification of PII, allowing for efficient document processing and protection of sensitive information.

Amazon Titan Text Premier is a highly advanced model within the Titan Text family, crafted to deliver exceptional performance and accuracy across a broad spectrum of enterprise applications. It excels in various text processing tasks, providing superior results for organizations seeking high-quality text generation, summarization, and more.

Cohere Command R+ is a highly performant generative language model optimized for large-scale production workloads, excelling in tasks like complex RAG, Q&A, multi-step tool use, chat, text generation, and text summarization with robust natural language processing capabilities.

Cohere Embed English translates text into numerical vectors that models can understand, playing a key role in high-performing AI applications. It enhances tasks such as semantic search, retrieval-augmented generation (RAG), classification, and clustering with 1024-dimensional embeddings.

Cohere Embed Multilingual translates text into numerical vectors that models can understand, playing a key role in high-performing AI applications. It enhances tasks such as semantic search, retrieval-augmented generation (RAG), classification, and clustering with 1024-dimensional embeddings.

Jamba-Instruct is AI21 Labs' latest foundation model, offering a 256K context window with excellent performance for text generation, summarization, and question answering, providing exceptional value for enterprise applications.

Mistral Large 2407 is an advanced Large Language Model (LLM) that supports dozens of languages and is trained on 80+ coding languages. It has best-in-class agentic capabilities with native function calling JSON outputting and more advanced reasoning capabilities.

Mistral Large is a powerful model designed for complex multilingual tasks, excelling in nuanced text processing and code generation. It features extensive capabilities with a large context window, ideal for detailed language and coding applications.

Mistral 7B is a compact yet powerful Transformer optimized for diverse applications. It offers robust performance in text and code generation with a 32k context window, making it suitable for efficient and advanced tasks.