Business Software for Together AI

ONLYOFFICE Docs is a secure online office suite for teams and businesses of all sizes. Create and edit docs, sheets, slides, fillable forms and PDFs. Collaborate with your teammates in real time using two co-editing modes, version history and other tools. Enable the AI assistant of your choice — ChatGPT, DeepSeek, Mistral, Groq AI, etc. Generate new content, summarize, translate and do more with your favourite AI tool while working on office files. Integrate ONLYOFFICE Docs into your business platform, whether it be Odoo, Alfresco, Confluence, Pipedrive, Nextcloud, Redmine, SuiteCRM, etc., via an integration app (40+ available integrations). Use Docs within ONLYOFFICE DocSpace, a room-based document collaboration platform equipped with the online office suite. Create dedicated spaces for different purposes, invite your teammates, assign access permissions and collaborate the way you like. With DocSpace, you can store, share and co-edit office files, and even interact with third parties.

StackAI is an enterprise AI automation platform that allows organizations to build end-to-end internal tools and processes with AI agents. It ensures every workflow is secure, compliant, and governed, so teams can automate complex processes without heavy engineering. With a visual workflow builder and multi-agent orchestration, StackAI enables full automation from knowledge retrieval to approvals and reporting. Enterprise data sources like SharePoint, Confluence, Notion, Google Drive, and internal databases can be connected with versioning, citations, and access controls to protect sensitive information. AI agents can be deployed as chat assistants, advanced forms, or APIs integrated into Slack, Teams, Salesforce, HubSpot, ServiceNow, or custom apps. Security is built in with SSO (Okta, Azure AD, Google), RBAC, audit logs, PII masking, and data residency. Analytics and cost governance let teams track performance, while evaluations and guardrails ensure reliability before production. StackAI also offers model flexibility, routing tasks across OpenAI, Anthropic, Google, or local LLMs with fine-grained controls for accuracy. A template library accelerates adoption with ready-to-use workflows like Contract Analyzer, Support Desk AI Assistant, RFP Response Builder, and Investment Memo Generator. By consolidating fragmented processes into secure, AI-powered workflows, StackAI reduces manual work, speeds decision-making, and empowers teams to build trusted automation at scale.

Kimi K2.5 is a powerful multimodal AI model built to handle complex reasoning, coding, and visual understanding at scale. It supports both text and image or video inputs, enabling developers to build applications that go beyond traditional language-only models. As Kimi’s most advanced model to date, it delivers open-source state-of-the-art performance across agent tasks, software development, and general intelligence benchmarks. The model supports an ultra-long 256K context window, making it ideal for large codebases, long documents, and multi-turn conversations. Kimi K2.5 includes a long-thinking mode that excels at logical reasoning, mathematics, and structured problem solving. It integrates seamlessly with existing workflows through full compatibility with the OpenAI SDK and API format. Developers can use Kimi K2.5 for chat, tool calling, file-based Q&A, and multimodal analysis. Built-in support for streaming, partial mode, and web search expands its flexibility. With predictable pricing and enterprise-ready capabilities, Kimi K2.5 is designed for scalable AI development.

GLM-5.1 represents the latest advancement in Z.ai’s GLM series, crafted as a cutting-edge, agent-focused AI model tailored for coding, reasoning, and managing long-term workflows. This iteration builds upon the framework of GLM-5, which employs a Mixture-of-Experts (MoE) architecture to achieve high performance without incurring excessive inference expenses, aligning with a larger initiative towards open-weight models that are accessible to developers. A significant emphasis of GLM-5.1 is on fostering agentic behavior, allowing it to plan, execute, and refine multi-step tasks instead of merely reacting to isolated prompts. Its capabilities are specifically engineered to manage intricate workflows, such as debugging code, exploring repositories, and performing sequential operations while maintaining context over time. In comparison to its predecessors, GLM-5.1 enhances reliability during lengthy interactions, ensuring coherence throughout extended sessions and minimizing failures in multi-step reasoning processes. Overall, this model signifies a leap forward in AI development, particularly in its ability to support complex task management seamlessly.

Kimi K2.6 is an advanced agentic AI model created by Moonshot AI, aiming to enhance practical implementation, programming, and complex reasoning compared to its predecessors, K2 and K2.5. This model is based on a Mixture-of-Experts framework and the multimodal, agent-centric principles of the Kimi series, merging language comprehension, coding capabilities, and tool utilization into one cohesive system that can plan and execute intricate workflows. It features enhanced reasoning skills and significantly better agent planning, enabling it to deconstruct tasks, synchronize various tools, and tackle multi-file or multi-step challenges with increased precision and effectiveness. Additionally, it provides robust tool-calling capabilities with a high degree of reliability, facilitating seamless integration with external platforms like web searches or APIs, and incorporates built-in validation systems to guarantee the accuracy of execution formats. Notably, Kimi K2.6 represents a significant leap forward in the realm of AI, setting new standards for the complexity and reliability of automated tasks.

Langtail is a cloud-based development tool designed to streamline the debugging, testing, deployment, and monitoring of LLM-powered applications. The platform provides a no-code interface for debugging prompts, adjusting model parameters, and conducting thorough LLM tests to prevent unexpected behavior when prompts or models are updated. Langtail is tailored for LLM testing, including chatbot evaluations and ensuring reliable AI test prompts. Key features of Langtail allow teams to: • Perform in-depth testing of LLM models to identify and resolve issues before production deployment. • Easily deploy prompts as API endpoints for smooth integration into workflows. • Track model performance in real-time to maintain consistent results in production environments. • Implement advanced AI firewall functionality to control and protect AI interactions. Langtail is the go-to solution for teams aiming to maintain the quality, reliability, and security of their AI and LLM-based applications.

Unlock the potential of selecting the ideal LLM tailored to your specific requirements while enhancing quality, speed, and cost-effectiveness. With a single API key, you can seamlessly access every LLM from various providers through a standardized interface. You have the flexibility to set your own parameters for cost, latency, and output speed, along with the ability to establish a personalized quality metric. Customize your router to align with your individual needs, allowing for systematic query distribution to the quickest provider based on the latest benchmark data, which is refreshed every 10 minutes to ensure accuracy. Begin your journey with Unify by following our comprehensive walkthrough that introduces you to the functionalities currently at your disposal as well as our future plans. By simply creating a Unify account, you can effortlessly connect to all models from our supported providers using one API key. Our router intelligently balances output quality, speed, and cost according to your preferences, while employing a neural scoring function to anticipate the effectiveness of each model in addressing your specific prompts. This meticulous approach ensures that you receive the best possible outcomes tailored to your unique needs and expectations.

A free software solution designed to create compact applications through a single prompt, driven by Llama 3 405B and Together.ai technology. This innovative tool streamlines the app development process, making it more accessible for users.

Superinterface is a versatile open-source platform designed to facilitate the effortless incorporation of AI-powered user interfaces into your products. It presents flexible, headless UI options that enable the integration of interactive in-app AI assistants, complete with API function calls and voice chat features. This platform is compatible with a range of AI models, including those developed by OpenAI, Anthropic, and Mistral, allowing for diverse AI integration possibilities. Superinterface streamlines the embedding process of AI assistants within your website or application through various methods, such as script tags, React components, or dedicated web pages, ensuring a quick and efficient setup that aligns with your existing technology stack. Furthermore, it includes extensive customization options, permitting you to adjust the assistant's look to align with your brand identity by selecting avatars, accent colors, and themes. Moreover, the platform enhances the assistant's capabilities by supporting functionalities like file searching, vector stores, and knowledge bases, ensuring that it can deliver pertinent information effectively. Overall, Superinterface empowers developers to create innovative, AI-enhanced user experiences with ease and efficiency.

E2B is an open-source runtime that provides a secure environment for executing AI-generated code within isolated cloud sandboxes. This platform allows developers to enhance their AI applications and agents with code interpretation features, enabling the safe execution of dynamic code snippets in a regulated setting. Supporting a variety of programming languages like Python and JavaScript, E2B offers software development kits (SDKs) for easy integration into existing projects. It employs Firecracker microVMs to guarantee strong security and isolation during code execution. Developers have the flexibility to implement E2B on their own infrastructure or take advantage of the available cloud service. The platform is crafted to be agnostic to large language models, ensuring compatibility with numerous options, including OpenAI, Llama, Anthropic, and Mistral. Among its key features are quick sandbox initialization, customizable execution environments, and the capability to manage long-running sessions lasting up to 24 hours. With E2B, developers can confidently run AI-generated code while maintaining high standards of security and efficiency.

LiteLLM serves as a comprehensive platform that simplifies engagement with more than 100 Large Language Models (LLMs) via a single, cohesive interface. It includes both a Proxy Server (LLM Gateway) and a Python SDK, which allow developers to effectively incorporate a variety of LLMs into their applications without hassle. The Proxy Server provides a centralized approach to management, enabling load balancing, monitoring costs across different projects, and ensuring that input/output formats align with OpenAI standards. Supporting a wide range of providers, this system enhances operational oversight by creating distinct call IDs for each request, which is essential for accurate tracking and logging within various systems. Additionally, developers can utilize pre-configured callbacks to log information with different tools, further enhancing functionality. For enterprise clients, LiteLLM presents a suite of sophisticated features, including Single Sign-On (SSO), comprehensive user management, and dedicated support channels such as Discord and Slack, ensuring that businesses have the resources they need to thrive. This holistic approach not only improves efficiency but also fosters a collaborative environment where innovation can flourish.

LangDB provides a collaborative, open-access database dedicated to various natural language processing tasks and datasets across multiple languages. This platform acts as a primary hub for monitoring benchmarks, distributing tools, and fostering the advancement of multilingual AI models, prioritizing transparency and inclusivity in linguistic representation. Its community-oriented approach encourages contributions from users worldwide, enhancing the richness of the available resources.

LLM Gateway is a completely open-source, unified API gateway designed to efficiently route, manage, and analyze requests directed to various large language model providers such as OpenAI, Anthropic, and Gemini Enterprise Agent Platform, all through a single, OpenAI-compatible endpoint. It supports multiple providers, facilitating effortless migration and integration, while its dynamic model orchestration directs each request to the most suitable engine, providing a streamlined experience. Additionally, it includes robust usage analytics that allow users to monitor requests, token usage, response times, and costs in real-time, ensuring transparency and control. The platform features built-in performance monitoring tools that facilitate the comparison of models based on accuracy and cost-effectiveness, while secure key management consolidates API credentials under a role-based access framework. Users have the flexibility to deploy LLM Gateway on their own infrastructure under the MIT license or utilize the hosted service as a progressive web app, with easy integration that requires only a change to the API base URL, ensuring that existing code in any programming language or framework, such as cURL, Python, TypeScript, or Go, remains functional without any alterations. Overall, LLM Gateway empowers developers with a versatile and efficient tool for leveraging various AI models while maintaining control over their usage and expenses.

Qwen3-Coder is a versatile coding model that comes in various sizes, prominently featuring the 480B-parameter Mixture-of-Experts version with 35B active parameters, which naturally accommodates 256K-token contexts that can be extended to 1M tokens. This model achieves impressive performance that rivals Claude Sonnet 4, having undergone pre-training on 7.5 trillion tokens, with 70% of that being code, and utilizing synthetic data refined through Qwen2.5-Coder to enhance both coding skills and overall capabilities. Furthermore, the model benefits from post-training techniques that leverage extensive, execution-guided reinforcement learning, which facilitates the generation of diverse test cases across 20,000 parallel environments, thereby excelling in multi-turn software engineering tasks such as SWE-Bench Verified without needing test-time scaling. In addition to the model itself, the open-source Qwen Code CLI, derived from Gemini Code, empowers users to deploy Qwen3-Coder in dynamic workflows with tailored prompts and function calling protocols, while also offering smooth integration with Node.js, OpenAI SDKs, and environment variables. This comprehensive ecosystem supports developers in optimizing their coding projects effectively and efficiently.

Metorial serves as an open-source integration platform tailored for developers, simplifying the processes of creating, deploying, monitoring, and scaling agentic AI applications by linking models to various tools, data sources, and APIs through the Model Context Protocol. With a comprehensive library of over 600 validated MCP “servers,” developers can easily enhance their agents with functionalities such as communication with Slack, Google Calendar, Notion, APIs, databases, or other systems with minimal effort, requiring only a few clicks or a single API call. The serverless architecture of Metorial is designed for scalability, enabling the deployment of MCP servers with just three clicks or an API request, accommodating "zero to millions" of requests, and providing built-in observability features that include extensive logging, tracing, session replay, and error notifications. Developers can also access a complete suite of SDKs, including Python and TypeScript, ensuring that every interaction can be tracked, allowing teams to audit and refine agent performance efficiently. Whether utilized on-premises or through cloud solutions, Metorial guarantees enterprise-level security and supports multi-tenant architectures, making it a versatile choice for a range of applications. This flexibility empowers organizations to tailor the platform to their specific needs while ensuring robust security measures are upheld at all times.

Rebolt is a sophisticated AI platform tailored for enterprises, allowing businesses to develop bespoke applications and intelligent agents through simple verbal commands directed at the AI. It provides seamless integration with various corporate tools like OneDrive, SharePoint, Salesforce, and Slack, as well as custom APIs, and includes essential infrastructure such as databases, file storage, scheduling capabilities (like cron jobs), audit logs, and separate environments for staging and production deployment. Users can generate applications and agents without any need for API key coding, merely by articulating their requirements in natural language, while still ensuring robust enterprise security features, permissions mapping through systems like Azure groups, and role-based access controls. This platform is specifically engineered for constructing operational workflows, internal tools, and automation that link to the firm's existing data and services, thus empowering non-technical users or low-code teams to quickly create solutions that can replace spreadsheets, cumbersome manual processes, and disjointed SaaS solutions. Additionally, Rebolt's intuitive design fosters increased collaboration among teams, enhancing productivity and innovation within the organization.

DeepCoder, an entirely open-source model for code reasoning and generation, has been developed through a partnership between Agentica Project and Together AI. Leveraging the foundation of DeepSeek-R1-Distilled-Qwen-14B, it has undergone fine-tuning via distributed reinforcement learning, achieving a notable accuracy of 60.6% on LiveCodeBench, which marks an 8% enhancement over its predecessor. This level of performance rivals that of proprietary models like o3-mini (2025-01-031 Low) and o1, all while operating with only 14 billion parameters. The training process spanned 2.5 weeks on 32 H100 GPUs, utilizing a carefully curated dataset of approximately 24,000 coding challenges sourced from validated platforms, including TACO-Verified, PrimeIntellect SYNTHETIC-1, and submissions to LiveCodeBench. Each problem mandated a legitimate solution along with a minimum of five unit tests to guarantee reliability during reinforcement learning training. Furthermore, to effectively manage long-range context, DeepCoder incorporates strategies such as iterative context lengthening and overlong filtering, ensuring it remains adept at handling complex coding tasks. This innovative approach allows DeepCoder to maintain high standards of accuracy and reliability in its code generation capabilities.

DeepSWE is an innovative and fully open-source coding agent that utilizes the Qwen3-32B foundation model, trained solely through reinforcement learning (RL) without any supervised fine-tuning or reliance on proprietary model distillation. Created with rLLM, which is Agentica’s open-source RL framework for language-based agents, DeepSWE operates as a functional agent within a simulated development environment facilitated by the R2E-Gym framework. This allows it to leverage a variety of tools, including a file editor, search capabilities, shell execution, and submission features, enabling the agent to efficiently navigate codebases, modify multiple files, compile code, run tests, and iteratively create patches or complete complex engineering tasks. Beyond simple code generation, DeepSWE showcases advanced emergent behaviors; when faced with bugs or new feature requests, it thoughtfully reasons through edge cases, searches for existing tests within the codebase, suggests patches, develops additional tests to prevent regressions, and adapts its cognitive approach based on the task at hand. This flexibility and capability make DeepSWE a powerful tool in the realm of software development.

DeepSeek-V4 is an advanced open-source large language model engineered for efficient long-context processing and high-level reasoning tasks. Supporting a massive one million token context window, it enables developers to build applications that handle extensive data and complex workflows without fragmentation. The model is available in two versions: V4-Pro for maximum reasoning power and V4-Flash for faster, cost-efficient performance. DeepSeek-V4-Pro delivers top-tier results in coding, mathematics, and knowledge benchmarks, rivaling leading proprietary models. Its architecture incorporates innovative attention techniques that significantly improve efficiency while maintaining strong performance. The model is optimized for agent-based workflows, allowing seamless integration with tools and automation systems. It also supports dual reasoning modes, enabling users to switch between quick responses and deeper analytical outputs. DeepSeek-V4 is fully open-source, providing flexibility for customization and deployment across various environments. Overall, it offers a powerful and scalable solution for modern AI development.

Qwen3.5 represents a major advancement in open-weight multimodal AI models, engineered to function as a native vision-language agent system. Its flagship model, Qwen3.5-397B-A17B, leverages a hybrid architecture that fuses Gated DeltaNet linear attention with a high-sparsity mixture-of-experts framework, allowing only 17 billion parameters to activate during inference for improved speed and cost efficiency. Despite its sparse activation, the full 397-billion-parameter model achieves competitive performance across reasoning, coding, multilingual benchmarks, and complex agent evaluations. The hosted Qwen3.5-Plus version supports a one-million-token context window and includes built-in tool use for search, code interpretation, and adaptive reasoning. The model significantly expands multilingual coverage to 201 languages and dialects while improving encoding efficiency with a larger vocabulary. Native multimodal training enables strong performance in image understanding, video processing, document analysis, and spatial reasoning tasks. Its infrastructure includes FP8 precision pipelines and heterogeneous parallelism to boost throughput and reduce memory consumption. Reinforcement learning at scale enhances multi-step planning and general agent behavior across text and multimodal environments. Overall, Qwen3.5 positions itself as a high-efficiency foundation for autonomous digital agents capable of reasoning, searching, coding, and interacting with complex environments.

MiniMax M2.7 is a powerful AI model built to drive real-world productivity across coding, search, and office-based workflows. It is trained using reinforcement learning across a wide range of real-world environments, enabling it to execute complex, multi-step tasks with precision and efficiency. The model demonstrates strong problem-solving capabilities by breaking down challenges into structured steps before generating solutions across multiple programming languages. It delivers high-speed performance with rapid token output, ensuring faster completion of demanding tasks. With optimized reasoning, it reduces token usage and execution time, making it more efficient than previous models. M2.7 also achieves state-of-the-art results in software engineering benchmarks, significantly improving response times for technical issues. Its advanced agentic capabilities allow it to work seamlessly with tools and support complex workflows with high skill accuracy. The model is designed to handle professional tasks, including multi-turn interactions and high-quality document editing. It also provides strong support for office productivity, enabling efficient handling of structured data and business tasks. With competitive pricing, it delivers high performance while remaining cost-effective. Overall, it combines speed, intelligence, and versatility to meet the needs of modern professionals and teams.

DeepSeek-V4-Pro is an advanced Mixture-of-Experts language model built for high-performance reasoning, coding, and large-scale AI applications. With 1.6 trillion total parameters and 49 billion activated parameters, it delivers strong capabilities while maintaining computational efficiency. The model supports a massive context window of up to one million tokens, making it ideal for handling long documents and complex workflows. Its hybrid attention architecture improves efficiency by reducing computational overhead while maintaining accuracy. Trained on more than 32 trillion tokens, DeepSeek-V4-Pro demonstrates strong performance across knowledge, reasoning, and coding benchmarks. It includes advanced training techniques such as improved optimization and enhanced signal propagation for better stability. The model offers multiple reasoning modes, allowing users to choose between faster responses or deeper analytical thinking. It is designed to support agentic workflows and complex multi-step problem solving. As an open-source model, it provides flexibility for developers and organizations to customize and deploy at scale. Overall, DeepSeek-V4-Pro delivers a balance of performance, efficiency, and scalability for demanding AI applications.

DeepSeek-V4-Flash is an optimized Mixture-of-Experts language model built for efficient large-scale AI workloads and fast inference. With 284 billion total parameters and 13 billion activated parameters, it delivers strong performance while maintaining lower computational demands compared to larger models. The model supports a massive context length of up to one million tokens, making it suitable for handling long-form content and multi-step workflows. Its hybrid attention mechanism improves efficiency by minimizing resource consumption while preserving accuracy. Trained on a dataset exceeding 32 trillion tokens, DeepSeek-V4-Flash performs well across reasoning, coding, and knowledge benchmarks. It offers flexible reasoning modes, enabling users to switch between quick responses and more detailed analytical outputs. The architecture is designed to support agentic workflows and scalable deployment environments. As an open-source model, it provides flexibility for customization and integration. Overall, DeepSeek-V4-Flash is a cost-effective and high-performance solution for modern AI applications.

OllaCoder serves as a private AI coding assistant tailored for VS Code, catering specifically to developers who prefer not to upload their source code to external servers. Operating locally, it utilizes your personal Ollama models and integrates features such as agent mode, inline edits, codebase chat, intelligent autocomplete, MCP servers, and a local-first runtime all within a single editor interface. The core philosophy behind OllaCoder emphasizes the notion that software development is a personal endeavor, asserting that your code should remain under your control while providing an AI assistant that is robust, transparent, and unobtrusive. It primarily communicates with your local Ollama instance, ensuring that prompts, completions, and modifications remain on your device; cloud services are optional, with API keys securely stored in the OS keychain. OllaCoder's agent mode is capable of planning tasks, modifying files, executing terminal commands, and confirming the accuracy of its work, allowing users to approve, reject, or revert any action taken. Additionally, the inline edits feature enables users to select a function, specify the desired change, and examine a real diff change by change, enhancing the coding experience. Overall, OllaCoder represents a significant step forward in maintaining code privacy while providing powerful AI-assisted development tools.

Cut down on administrative expenses and enhance reimbursement rates, all while ensuring compliance is upheld. Transform your revenue cycle management (RCM) with the innovative capabilities of RapidClaims powered by AI technology. Significantly reduce administrative costs, elevate reimbursement levels, and maintain compliance with minimal effort. Simplify your coding workflow, and either automate tasks or empower your coding staff with tailored solutions that meet your specific needs. Process thousands of charts quickly and accurately while addressing the distinct demands of each client. Our advanced language model adeptly handles unstructured data, crafting a comprehensive patient record by turning notes into organized codes and identifying disease patterns. Avoid repeating past errors by establishing broad coding-related rules in straightforward language, which can be easily implemented across your charts, categorized by specialty, code type, and individual coders. Enhance your insight into code-level trends across various locations and take proactive steps to refine the revenue cycle. Additionally, our platform meticulously reviews charts to uncover claim denial trends, equipping you with the tools to address these challenges effectively and improve overall performance. With these capabilities, you can ensure a more streamlined and efficient coding process that supports your organization's financial health.