List of the Top Free LLM API Providers in 2026

Gemini platform is an enterprise artificial intelligence development and machine learning platform from Google Cloud that provides the tools and infrastructure required to build, customize, deploy, and govern AI models and autonomous agents. The platform represents the evolution of Vertex AI and combines generative AI development, predictive machine learning, agent orchestration, model training, and enterprise governance within a unified environment. Its Model Garden provides access to more than 200 foundation models, including Google's Gemini family, third-party language models, and open-source alternatives that can be evaluated, customized, and deployed for different applications. Agent Studio provides a low-code workspace for designing AI agents, experimenting with prompts, testing model behavior, and prototyping intelligent applications through visual development tools. The Agent Development Kit offers a model-agnostic framework for building sophisticated agents capable of reasoning, using external tools, coordinating specialized subagents, and executing multistep workflows. Google Antigravity extends the platform's agentic capabilities with a development environment for managing AI coding agents, generating application code, and coordinating automated software engineering tasks. Gemini platform also provides custom machine learning training with support for different frameworks, configurable training jobs, hyperparameter optimization, and deployment of trained models for online or batch predictions. Its MLOps capabilities include automated pipelines, model evaluation, Model Registry, Feature Store, and monitoring tools that help engineering teams manage the machine learning lifecycle and identify performance degradation.

OpenRouter provides a centralized API layer for accessing and managing AI models from a wide range of developers and infrastructure providers. Instead of building a separate integration for each model company, developers can use one interface to send requests to hundreds of available models. Its catalog includes offerings from OpenAI, Anthropic, Google, Meta, xAI, Mistral, DeepSeek, Qwen, Microsoft, NVIDIA, Amazon, and other AI providers. The platform can handle multimodal applications that work with text, images, audio, and video. Users fund a common credit balance that can be applied across supported models and providers without subscribing individually to each service. OpenRouter includes intelligent provider routing that can optimize requests according to pricing, response speed, and endpoint availability. Automatic fallback capabilities allow traffic to move between providers when an endpoint encounters reliability or uptime issues. Companies can also establish detailed data policies to control where prompts are processed and limit requests to providers that meet their privacy requirements. Model discovery tools, rankings, benchmarks, pricing information, and usage statistics help developers compare options before choosing models for particular workloads. OpenRouter supports an OpenAI-compatible API along with developer documentation, making it relatively straightforward to integrate into applications already built around common AI API conventions. The service is designed to simplify model experimentation and production deployment while giving teams greater flexibility over which models, providers, and routing strategies they use.

The Databricks Data Intelligence Platform empowers every individual within your organization to effectively utilize data and artificial intelligence. Built on a lakehouse architecture, it creates a unified and transparent foundation for comprehensive data management and governance, further enhanced by a Data Intelligence Engine that identifies the unique attributes of your data. Organizations that thrive across various industries will be those that effectively harness the potential of data and AI. Spanning a wide range of functions from ETL processes to data warehousing and generative AI, Databricks simplifies and accelerates the achievement of your data and AI aspirations. By integrating generative AI with the synergistic benefits of a lakehouse, Databricks energizes a Data Intelligence Engine that understands the specific semantics of your data. This capability allows the platform to automatically optimize performance and manage infrastructure in a way that is customized to the requirements of your organization. Moreover, the Data Intelligence Engine is designed to recognize the unique terminology of your business, making the search and exploration of new data as easy as asking a question to a peer, thereby enhancing collaboration and efficiency. This progressive approach not only reshapes how organizations engage with their data but also cultivates a culture of informed decision-making and deeper insights, ultimately leading to sustained competitive advantages.

Perplexity is an AI-powered search and answer platform that delivers accurate, real-time information through conversational queries. It combines large language models with live web search to generate precise and context-aware responses. Unlike traditional search engines, Perplexity provides direct answers along with citations from credible sources. This transparency helps users verify information and trust the results. The platform supports follow-up questions, allowing users to explore topics in depth without starting new searches. It offers multiple search modes, including general, academic, and focused research options. Perplexity is designed to simplify complex information and make knowledge more accessible. Its clean and intuitive interface ensures a seamless user experience. The platform is widely used for research, content creation, and decision-making. It is particularly valuable for users who need quick, reliable, and well-sourced answers. By combining AI reasoning with real-time data, Perplexity bridges the gap between search engines and intelligent assistants. Overall, it represents a new generation of search tools focused on accuracy, speed, and usability.

AnyAPI is a unified AI API platform built to simplify and accelerate AI adoption. It provides seamless access to hundreds of top-tier AI models through a single integration layer. Developers can use models from OpenAI, Anthropic, Google, xAI, and Mistral without changing their code structure. AnyAPI reduces complexity by standardizing requests across providers. The platform is designed for speed, offering low latency and high availability for production workloads. Developers can experiment, compare, and deploy models using an integrated AI playground. Long-context capabilities support up to hundreds of thousands of tokens for document-heavy use cases. Intelligent model switching improves response quality and performance automatically. Enterprise features include access control, usage monitoring, and overage alerts. AnyAPI works with modern development stacks and scales with growing applications. Built-in documentation and tutorials help teams onboard quickly. AnyAPI empowers startups and enterprises to build AI-powered products faster and with confidence.

Claude is a powerful AI assistant designed by Anthropic to support problem-solving, creativity, and productivity across a wide range of use cases. It helps users write, edit, analyze, and code by combining conversational AI with advanced reasoning capabilities. Claude allows users to work on documents, software, graphics, and structured data directly within the chat experience. Through features like Artifacts, users can collaborate with Claude to iteratively build and refine projects. The platform supports file uploads, image understanding, and data visualization to enhance how information is processed and presented. Claude also integrates web search results into conversations to provide timely and relevant context. Available on web, iOS, and Android, Claude fits seamlessly into modern workflows. Multiple subscription tiers offer flexibility, from free access to high-usage professional and enterprise plans. Advanced models give users greater depth, speed, and reasoning power for complex tasks. Claude is built with enterprise-grade security and privacy controls to protect sensitive information. Anthropic prioritizes transparency and responsible scaling in Claude’s development. As a result, Claude is positioned as a trusted AI assistant for both everyday tasks and mission-critical work.

Gemini is Google’s next-generation AI assistant designed to deliver intelligent help across research, creativity, communication, and task management. Built on Google’s most advanced AI models, including Gemini 3, it helps users understand complex topics, generate content, and solve problems through natural conversation. Gemini enables text, image, and video generation, allowing users to quickly turn ideas into visual and written outputs. Its grounding in Google Search ensures responses are informed, relevant, and easy to explore further through follow-up questions. Gemini supports hands-free and conversational brainstorming through Gemini Live, making it useful for presentations, interviews, and idea development. With Deep Research, Gemini can analyze hundreds of sources and compile detailed reports in a fraction of the time. The platform connects directly to Google apps like Gmail, Docs, Calendar, Maps, and YouTube to streamline everyday workflows. Users can build personalized AI helpers using Gems by saving detailed instructions and uploaded files. Gemini’s long context window allows it to process large documents, code repositories, and research materials in a single session. Multiple plans provide flexibility, from free access for students and casual users to premium tiers with higher limits and advanced features. Gemini is available across web and mobile devices for seamless access. Designed to adapt to different needs, Gemini supports consumers, professionals, educators, and enterprises alike.

DeepSeek emerges as a cutting-edge AI assistant, utilizing the advanced DeepSeek-V3 model, which features a remarkable 600 billion parameters for enhanced performance. Designed to compete with the top AI systems worldwide, it provides quick responses and a wide range of functionalities that streamline everyday tasks. Available across multiple platforms such as iOS, Android, and the web, DeepSeek ensures that users can access its services from nearly any location. The application supports various languages and is regularly updated to improve its features, add new language options, and resolve any issues. Celebrated for its seamless performance and versatility, DeepSeek has garnered positive feedback from a varied global audience. Moreover, its dedication to user satisfaction and ongoing enhancements positions it as a leader in the AI technology landscape, making it a trusted tool for many. With a focus on innovation, DeepSeek continually strives to refine its offerings to meet evolving user needs.

Mistral AI is recognized as a pioneering startup in the field of artificial intelligence, with a particular emphasis on open-source generative technologies. The company offers a wide range of customizable, enterprise-grade AI solutions that can be deployed across multiple environments, including on-premises, cloud, edge, and individual devices. Notable among their offerings are "Le Chat," a multilingual AI assistant designed to enhance productivity in both personal and business contexts, and "La Plateforme," a resource for developers that streamlines the creation and implementation of AI-powered applications. Mistral AI's unwavering dedication to transparency and innovative practices has enabled it to carve out a significant niche as an independent AI laboratory, where it plays an active role in the evolution of open-source AI while also influencing relevant policy conversations. By championing the development of an open AI ecosystem, Mistral AI not only contributes to technological advancements but also positions itself as a leading voice within the industry, shaping the future of artificial intelligence. This commitment to fostering collaboration and openness within the AI community further solidifies its reputation as a forward-thinking organization.

Cohere is a powerful enterprise AI platform that enables developers and organizations to build sophisticated applications using language technologies. By prioritizing large language models (LLMs), Cohere delivers cutting-edge solutions for a variety of tasks, including text generation, summarization, and advanced semantic search functions. The platform includes the highly efficient Command family, designed to excel in language-related tasks, as well as Aya Expanse, which provides multilingual support for 23 different languages. With a strong emphasis on security and flexibility, Cohere allows for deployment across major cloud providers, private cloud systems, or on-premises setups to meet diverse enterprise needs. The company collaborates with significant industry leaders such as Oracle and Salesforce, aiming to integrate generative AI into business applications, thereby improving automation and enhancing customer interactions. Additionally, Cohere For AI, the company’s dedicated research lab, focuses on advancing machine learning through open-source projects and nurturing a collaborative global research environment. This ongoing commitment to innovation not only enhances their technological capabilities but also plays a vital role in shaping the future of the AI landscape, ultimately benefiting various sectors and industries.

Grok is an AI-powered assistant developed by xAI, designed to provide real-time, context-aware, and engaging conversational experiences. It is tightly integrated with the X platform, allowing it to access live data, trending topics, and user-generated content for up-to-date insights. Grok is built to handle a variety of tasks, including research, content generation, problem-solving, and general inquiries. Its advanced language model enables it to understand complex questions and deliver accurate, thoughtful responses. Unlike traditional AI tools, Grok incorporates humor and personality, making interactions more engaging and human-like. The platform is particularly effective for tracking current events and social trends in real time. It supports both casual and professional use cases, offering flexibility for different user needs. Grok continuously improves through updates, enhancing its reasoning and conversational abilities. It is designed to be intuitive and easy to use within the X ecosystem. The integration with live data makes it highly relevant for fast-changing information environments. Security and performance are key priorities, ensuring reliable interactions. Overall, Grok represents a next-generation AI assistant focused on real-time intelligence and engaging user experiences.

Qwen is an advanced AI assistant and development platform powered by Alibaba Cloud’s cutting-edge Qwen model family, offering powerful multimodal reasoning and creativity tools for users at all skill levels. It provides a free and accessible interface through Qwen Chat, where anyone can generate images, analyze content, perform deep multi-step research, and build fully coded web pages simply by describing what they want. Using its VLo model, Qwen transforms ideas into detailed visuals and supports editing, style transfer, and complex multi-element image creation. Deep Research acts like an automated research partner, gathering information online, synthesizing insights, and generating structured reports in minutes. The Web Dev feature empowers users to create modern, ready-to-deploy websites with clean code using only natural language instructions. Qwen’s enhanced “Thinking” capabilities provide stronger logic, structured problem-solving, and real-time internet-aware analysis. Its Search tool retrieves precise results with contextual understanding, while multimodal intelligence enables Qwen to process images, audio, video, and text together for deeper comprehension. For developers, the Qwen API offers OpenAI-compatible endpoints, allowing seamless integration of Qwen’s reasoning, generation, and multimodal abilities into any application or product. This makes Qwen not only an AI assistant but also a versatile platform for builders and engineers. Across web, desktop, and mobile environments, Qwen delivers a unified, high-performance AI experience.

Hugging Face is an AI-driven platform designed for developers, researchers, and businesses to collaborate on machine learning projects. The platform hosts an extensive collection of pre-trained models, datasets, and tools that can be used to solve complex problems in natural language processing, computer vision, and more. With open-source projects like Transformers and Diffusers, Hugging Face provides resources that help accelerate AI development and make machine learning accessible to a broader audience. The platform’s community-driven approach fosters innovation and continuous improvement in AI applications.

Replicate is a robust machine learning platform that empowers developers and organizations to run, fine-tune, and deploy AI models at scale with ease and flexibility. Featuring an extensive library of thousands of community-contributed models, Replicate supports a wide range of AI applications, including image and video generation, speech and music synthesis, and natural language processing. Users can fine-tune models using their own data to create bespoke AI solutions tailored to unique business needs. For deploying custom models, Replicate offers Cog, an open-source packaging tool that simplifies model containerization, API server generation, and cloud deployment while ensuring automatic scaling to handle fluctuating workloads. The platform's usage-based pricing allows teams to efficiently manage costs, paying only for the compute time they actually use across various hardware configurations, from CPUs to multiple high-end GPUs. Replicate also delivers advanced monitoring and logging tools, enabling detailed insight into model predictions and system performance to facilitate debugging and optimization. Trusted by major companies such as Buzzfeed, Unsplash, and Character.ai, Replicate is recognized for making the complex challenges of machine learning infrastructure accessible and manageable. The platform removes barriers for ML practitioners by abstracting away infrastructure complexities like GPU management, dependency conflicts, and model scaling. With easy integration through API calls in popular programming languages like Python, Node.js, and HTTP, teams can rapidly prototype, test, and deploy AI features. Ultimately, Replicate accelerates AI innovation by providing a scalable, reliable, and user-friendly environment for production-ready machine learning.

AI21 Studio offers API access to its Jurassic-1 large language models, which are utilized for text generation and comprehension in countless applications. With our advanced models, you can address any language-related task. The Jurassic-1 models excel at following natural language instructions and require only a handful of examples to adapt to new challenges. Our APIs are ideally suited for standard tasks, including paraphrasing and summarization, providing exceptional results at competitive prices without the need for extensive reworking. If you're looking to fine-tune a personalized model, achieving that is just a few clicks away. The training process is swift and cost-effective, allowing for immediate deployment of the models. By integrating an AI co-writer into your application, you can empower your users with enhanced features. Capabilities such as paraphrasing, long-form draft creation, content repurposing, and tailored auto-complete options can significantly boost user engagement, paving the way for your success and growth in the industry. Ultimately, our tools are designed to streamline your workflows and elevate the overall user experience.

Fireworks partners with leading generative AI researchers to deliver exceptionally efficient models at unmatched speeds. It has been evaluated independently and is celebrated as the fastest provider of inference services. Users can access a selection of powerful models curated by Fireworks, in addition to our unique in-house developed multi-modal and function-calling models. As the second most popular open-source model provider, Fireworks astonishingly produces over a million images daily. Our API, designed to work with OpenAI, streamlines the initiation of your projects with Fireworks. We ensure dedicated deployments for your models, prioritizing both uptime and rapid performance. Fireworks is committed to adhering to HIPAA and SOC2 standards while offering secure VPC and VPN connectivity. You can be confident in meeting your data privacy needs, as you maintain ownership of your data and models. With Fireworks, serverless models are effortlessly hosted, removing the burden of hardware setup or model deployment. Besides our swift performance, Fireworks.ai is dedicated to improving your overall experience in deploying generative AI models efficiently. This commitment to excellence makes Fireworks a standout and dependable partner for those seeking innovative AI solutions. In this rapidly evolving landscape, Fireworks continues to push the boundaries of what generative AI can achieve.

Parasail is an innovative network designed for the deployment of artificial intelligence, providing scalable and cost-efficient access to high-performance GPUs that cater to various AI applications. The platform includes three core services: serverless endpoints for real-time inference, dedicated instances for the deployment of private models, and batch processing options for managing extensive tasks. Users have the flexibility to either implement open-source models such as DeepSeek R1, LLaMA, and Qwen or deploy their own models, supported by a permutation engine that effectively matches workloads to hardware, including NVIDIA’s H100, H200, A100, and 4090 GPUs. The platform's focus on rapid deployment enables users to scale from a single GPU to large clusters within minutes, resulting in significant cost reductions, often cited as being up to 30 times cheaper than conventional cloud services. In addition, Parasail provides day-zero availability for new models and features a user-friendly self-service interface that eliminates the need for long-term contracts and prevents vendor lock-in, thereby enhancing user autonomy and flexibility. This unique combination of offerings positions Parasail as an appealing option for those seeking to utilize advanced AI capabilities without facing the typical limitations associated with traditional cloud computing solutions, ensuring that users can stay ahead in the rapidly evolving tech landscape.

FriendliAI is an innovative platform that acts as an advanced generative AI infrastructure, designed to offer quick, efficient, and reliable inference solutions specifically for production environments. This platform is loaded with a variety of tools and services that enhance the deployment and management of large language models (LLMs) and diverse generative AI applications on a significant scale. One of its standout features, Friendli Endpoints, allows users to develop and deploy custom generative AI models, which not only lowers GPU costs but also accelerates the AI inference process. Moreover, it ensures seamless integration with popular open-source models found on the Hugging Face Hub, providing users with exceptionally rapid and high-performance inference capabilities. FriendliAI employs cutting-edge technologies such as Iteration Batching, the Friendli DNN Library, Friendli TCache, and Native Quantization, resulting in remarkable cost savings (between 50% and 90%), a drastic reduction in GPU requirements (up to six times fewer), enhanced throughput (up to 10.7 times), and a substantial drop in latency (up to 6.2 times). As a result of its forward-thinking strategies, FriendliAI is establishing itself as a pivotal force in the dynamic field of generative AI solutions, fostering innovation and efficiency across various applications. This positions the platform to support a growing number of users seeking to harness the power of generative AI for their specific needs.

Kluster.ai serves as an AI cloud platform specifically designed for developers, facilitating the rapid deployment, scalability, and fine-tuning of large language models (LLMs) with exceptional effectiveness. Developed by a team of developers who understand the intricacies of their needs, it incorporates Adaptive Inference, a flexible service that adjusts in real-time to fluctuating workload demands, ensuring optimal performance and dependable response times. This Adaptive Inference feature offers three distinct processing modes: real-time inference for scenarios that demand minimal latency, asynchronous inference for economical task management with flexible timing, and batch inference for efficiently handling extensive data sets. The platform supports a diverse range of innovative multimodal models suitable for various applications, including chat, vision, and coding, highlighting models such as Meta's Llama 4 Maverick and Scout, Qwen3-235B-A22B, DeepSeek-R1, and Gemma 3. Furthermore, Kluster.ai includes an OpenAI-compatible API, which streamlines the integration of these sophisticated models into developers' applications, thereby augmenting their overall functionality. By doing so, Kluster.ai ultimately equips developers to fully leverage the capabilities of AI technologies in their projects, fostering innovation and efficiency in a rapidly evolving tech landscape.

Gemini Enterprise app is a powerful enterprise-grade AI platform that enables organizations to deploy, manage, and scale AI agents across their entire workforce. It integrates seamlessly with popular productivity tools and data sources, allowing users to access and analyze business data through a single interface. The platform supports advanced automation by enabling agents to execute complex, multi-step workflows across multiple applications. It includes prebuilt agents like NotebookLM Enterprise, as well as tools for building custom and third-party agents using a no-code approach. Gemini Enterprise app provides robust security, governance, and compliance features, including data access controls, encryption, and regulatory support. It offers centralized visibility into all agents, workflows, and permissions, ensuring efficient management at scale. The platform is designed to enhance productivity across departments by automating repetitive tasks and accelerating content creation. It also helps break down data silos by connecting multiple data sources into one system. With scalable pricing options and enterprise-grade infrastructure, it supports both small teams and large organizations. Overall, Gemini Enterprise app delivers a unified, secure, and scalable solution for AI-driven business transformation.

Grokified operates as a cloud-based API gateway that is fully compatible with OpenAI, providing users with a single API endpoint to access various Grok models. Tailored for developers and AI engineers, this platform simplifies chat interactions and coding tasks while also managing requests for images, videos, audio, and other tools. Key features include API key management, model selection, streaming options, function calling, and tools aimed at tracking usage and expenses, as well as managing prepaid balances. OpenAI SDK clients and compatible editors can seamlessly connect by configuring the Grokified base URL and their credentials, and there is also a command-line interface available for setting up supported agents. Each request deducts credits from prepaid accounts, with competitive rates that make it a cost-effective solution for developers. Furthermore, Grokified is committed to continuous improvement, with regular updates that enhance its capabilities and integration possibilities, ensuring users stay at the forefront of technology. This ongoing evolution positions Grokified as a leading choice for those looking to harness the power of AI effectively.

UncensoredLLM acts as a versatile API gateway that aligns with OpenAI's standards, focusing on the deployment of uncensored, modified, and roleplay-tailored language models. Developers are empowered to select specific models using their unique identifiers, easily integrating them into various applications via coding or supporting chat, writing, and programming clients, all while utilizing a simple base URL and API key for streamlined access. The rich catalog encompasses a range of builds from model families such as DeepSeek, GLM, Qwen, Gemma, Kimi, and Llama, each presenting its own unique pricing structures for input and output tokens. In addition to text generation, the same API key enables users to access endpoints for creating images and videos, with fees applied for each image rendered or per second of video produced. Billing operates on a prepaid balance system, supplemented by a browser-based playground that offers a limited number of complimentary interactions with selected models on a daily basis. Users can explore publicly accessible model pages for detailed insights into catalog offerings and pricing schemes, while each model is subjected to a daily fixed-prompt verification process aimed at ensuring accuracy in reported input-token usage, which significantly bolsters the reliability of the service. This meticulous methodology not only fosters transparency but also cultivates user confidence in the platform's overall capabilities, ultimately enhancing the user experience and encouraging deeper engagement with the tools available.

Synap offers a hosted inference API that provides developers with access to an OpenAI-compatible endpoint for open-weight language models. By merely modifying the API base URL, key, and model name, applications can effortlessly connect using the well-known OpenAI SDKs and chat-completion requests. The platform boasts an extensive lineup of models, including Qwen3, Qwen3-VL, Qwen3 Coder, Gemma 4, and gpt-oss-20b, with each model having distinct input and output token pricing structures. Furthermore, Synap supports streaming and tool invocation while maintaining a strict policy of zero data retention for all requests. Developers have the flexibility to select from multiple payment methods, such as prepaid credits that do not expire, monthly subscriptions, or pay-per-call charges in USDC through x402. This service is specifically designed for software developers, creators of AI applications, and teams that aim to effectively incorporate model inference into their applications and workflows. With its intuitive interface and comprehensive features, Synap seeks to streamline the integration of AI-driven solutions across a variety of projects, ultimately enhancing productivity and innovation in the field. As such, it becomes an invaluable resource for anyone looking to leverage advanced AI capabilities in their work.

Contextwaise is a cutting-edge API and agent SDK tailored for teams focused on building retrieval-augmented generation (RAG) applications, AI agents, and various large language model (LLM) products. It assesses retrieved materials, including passages, web pages, chat logs, and tool outputs, in line with the specific requirements of the task at hand, delivering pertinent context while respecting a designated token limit prior to the model's engagement. Equipped with a flexible REST API, it supports requests in any programming language, while its TypeScript and Python SDKs enhance agent workflows and integrate effortlessly with Vercel AI SDK, Anthropic SDK, and OpenAI SDK. The output systematically preserves the sequence of submissions, generating reports that outline token modifications, potential cost savings, and rationales for excluded content. Contextwaise also includes features such as request logging, adjustable budgets, and quality assurance; its agent SDKs can disclose segments of excluded tool outputs for additional clarification. By employing this solution, engineering teams can significantly reduce unnecessary model inputs while maintaining their retrieval resources, prompts, and interactions with model providers, thus simplifying the development workflow. This optimization not only improves efficiency but also empowers teams to advance their AI-driven applications more effectively and creatively. Ultimately, Contextwaise serves as an essential tool for fostering innovation in the AI landscape.

A company based in the EU provides an inference API that is compatible with models from OpenAI and Anthropic. Their leading model operates on dedicated GPUs housed in EIA data centers, ensuring that all data is processed exclusively in memory—thus no prompts or completions are stored or logged, and they are not employed for training purposes. Users can also access routed open models from various third-party providers using the same key, with these models clearly labeled for transparency. The service is complemented by a Data Processing Agreement (DPA) and an invoice issued by the EU entity. Key features include streaming capabilities, tool calling, structured output, and a publicly available DPA along with a list of sub-processors, as well as a pricing structure based on token usage. In a performance measurement conducted on the live system in August 2026, it was found that the service could process 176 tokens per second for each stream, generating the first token in merely 0.3 seconds, which underscores its remarkable efficiency and speed. This level of performance is essential for developers in search of dependable and swift AI solutions for their applications, showcasing the importance of reliable metrics in the fast-paced tech landscape.