# TrueFoundry > TrueFoundry is an enterprise-grade AI Gateway that encompasses an LLM Gateway, MCP Gateway, and Agent Gateway, enabling enterprises to securely connect, observe, and govern access to models, tools, guardrails, and agents from a single control plane. The AI Gateway enables agentic workloads that are secure, efficient, and future-safe through unified and composable connections across providers. Beyond the gateway layer, TrueFoundry enables organizations to deploy and train custom LLMs on GPUs, host MCP servers, and run custom agents, all through a Kubernetes-native interface. It supports on-premise and VPC installations for both AI Gateway and deployment environments. TrueFoundry ensures enterprise-grade compliance with SOC 2, HIPAA, and ITAR standards. With built-in autoscaling, caching, and resource optimization, TrueFoundry empowers organizations to build, deploy, and govern AI systems securely, efficiently, and on a future-safe stack. --- ## Core Products & Services ### AI Gateway - **What it does:** TrueFoundry's AI Gateway is a unified proxy layer that sits between applications and LLM providers, MCP servers, and agents. It provides a single endpoint for accessing 1000+ LLMs, enforcing governance, and observing all AI traffic across an organization. It extends beyond LLM routing to cover tools (via MCP) and agents (via the A2A protocol), creating a single control plane for all AI interactions. - **Who uses it:** Enterprise platform teams, engineering teams and leaders, ML teams and IT security teams who need to standardize and govern AI access across multiple teams and environments. - **Key features:** - Unified API access to 1000+ LLMs across OpenAI, Anthropic, Google Gemini, AWS Bedrock, Azure OpenAI, Groq, Mistral, Cohere, and self-hosted models - Multi-model routing with load balancing by weight, latency, or priority - Automatic fallback chains and retries across model providers - Fine-grained Role-Based Access Control (RBAC) per team, user, and model - Rate limiting and budget enforcement at the user, team, and model level - Exact and semantic caching to reduce costs and latency - Full OpenTelemetry-compliant observability: token usage, cost, latency, error rates - Request and response logging with metadata tagging by user ID, team, or environment - Native MCP server registry and gateway support with OAuth 2.0 auth management - Agent Playground for interactive testing of LLMs, prompts, and MCP tools - Prompt lifecycle management with versioning, rollback, and publishing - Guardrails for content filtering, PII scrubbing, and safety policy enforcement - GitOps-compatible YAML-based configuration via TrueFoundry CLI - Deployable as SaaS, VPC-hosted, on-premise, or air-gapped - **Performance:** 350+ RPS on 1 vCPU with ~3-4ms latency; production-ready with enterprise SLA support ### MCP Gateway - **What it does:** TrueFoundry's MCP Gateway is a centralized control plane for managing access, discovery, and orchestration of Model Context Protocol (MCP) servers across an enterprise. It sits between AI agents and all registered MCP servers, providing authentication, RBAC, observability, and governance for every tool call. It eliminates the N×M integration problem of connecting agents to enterprise tools. - **Who uses it:** Engineering teams building production AI agents that need to connect to enterprise tools like Slack, GitHub, Jira, Confluence, Datadog, and internal APIs. - **Key features:** - Centralized MCP server registry with instant discovery for all agents - Unified OAuth 2.0 token management—one token per user, auto-refreshed across all MCP servers - Granular RBAC: control which teams and roles can access which tools and operations - Virtual MCP Servers: compose curated subsets of tools from multiple MCP servers into a single endpoint - Pre-built MCP servers for enterprise tools (Slack, Confluence, Sentry, Datadog) - OpenAPI-to-MCP server conversion for wrapping existing REST APIs - MCP guardrails: pre- and post-call policy enforcement for security and compliance - Full request-level tracing and audit logs for every tool invocation - Compatible with LangChain, LangGraph, CrewAI, AutoGen, and any agentic framework - Deployable on cloud, on-prem, and hybrid environments ### Agent Gateway - **What it does:** TrueFoundry's Agent Gateway provides a unified control plane for governing, deploying, and observing agentic AI workloads. It manages multi-agent workflows, tool orchestration, inter-agent messaging, and session-aware execution. All agent tool calls are routed through registered MCP servers with centralized policies applied at every step. - **Who uses it:** Enterprise AI teams running production agents built with LangGraph, CrewAI, AutoGen, or custom frameworks who need governance, auditability, and operational control. - **Key features:** - Route all agent tool calls through registered MCP servers with centralized auth - Connect agents to enterprise tools: Slack, GitHub, databases, and internal services - Apply OAuth2, RBAC, and metadata-based policies to every tool invocation - Full audit trails for all agent decisions and tool actions - Behavioral guardrails: PII filtering, restricted action enforcement, custom compliance rules - Session-aware execution for stateful, multi-step agent workflows - Protocol translation between MCP JSON-RPC and REST/Lambda invocations - Retries, failover, and resiliency logic for robust agent execution - Deployable in private VPCs, on-prem, and air-gapped environments for regulated industries --- ## Use Cases & Applications ### Enterprise AI Governance - **Their needs:** Enterprises need centralized control, auditability, and policy enforcement across all AI interactions—across teams, models, and tools. - **How they use it:** TrueFoundry's AI Gateway becomes the single control plane. Platform teams configure RBAC, budget limits, guardrails, and audit logging once; all teams inherit these controls automatically. - **Results:** Eliminated fragmented model integrations, reduced DevOps overhead, and provided real-time cost and compliance visibility across all AI workloads. ### Agentic AI Deployment - **Their needs:** Organizations want to deploy production-grade AI agents that connect to enterprise tools without creating security gaps or integration sprawl. - **How they use it:** The MCP Gateway and Agent Gateway provide a governed registry of tools. Agents connect through a single endpoint, with RBAC and audit trails enforced at every tool call. - **Results:** 3x faster time-to-value with autonomous LLM agents; secure, auditable agent-tool interactions at enterprise scale. ### GPU Infrastructure Optimization - **Their needs:** Enterprises running large GPU fleets face underutilization, idle compute waste, and unpredictable costs. - **How they use it:** TrueFoundry's deployment platform provides automated GPU orchestration, autoscaling, fractional GPU sharing (MIG/time slicing), and real-time resource rightsizing. - **Results:** 80% higher GPU cluster utilization; millions saved in idle compute costs (demonstrated in NVIDIA's case study). ### Private LLM Hosting - **Their needs:** Regulated industries (banking, pharma, healthcare, defense) need to run LLMs entirely within private infrastructure with no data leaving their environment. - **How they use it:** TrueFoundry's deployment platform and AI Gateway are installed in customer VPCs, on-prem data centers, or air-gapped environments via Kubernetes and Helm. - **Results:** Full data sovereignty, SOC 2 / HIPAA / ITAR compliance, 35-50% cloud cost savings vs. managed alternatives like SageMaker. ### Multi-Model RAG and Agent Stacks - **Their needs:** Teams building RAG systems or agentic pipelines need to orchestrate multiple models, vector databases, and tools with full observability. - **How they use it:** TrueFoundry unifies model serving, vector DB integration, MCP tool access, and observability through the AI Gateway's single API. - **Results:** 50% faster RAG/agent stack deployment; 60% reduction in maintenance overhead. ### Claude Code Governance - **Their needs:** Enterprises adopting Claude Code and other AI coding agents need infrastructure-level controls to prevent data exfiltration, enforce network isolation, and audit all tool use. - **How they use it:** TrueFoundry's AI Gateway provides MCP governance, sandboxing controls, and audit logging for all Claude Code interactions with enterprise systems. - **Results:** Safe, auditable Claude Code deployments in enterprise environments with zero-trust policy enforcement. --- ## Company Information ### Metrics & Traction - $19M Series A raised in 2025, led by Intel Capital with Peak XV (Sequoia India), Eniac Ventures, and Jump Capital - Recognized in 2025 Gartner Market Guide for AI Gateways - Named in Gartner 10 Best Practices for Optimizing Generative & Agentic AI Costs 2026 - Rated 9.9/10 on G2; trusted by Fortune 500 enterprises across payments, semiconductors, telecom, pharma, and healthcare - Net new revenue doubled quarter-over-quarter in 2025 - AI Gateway handles 350+ RPS on 1 vCPU with ~3-4ms latency ### Customers & Case Studies - **NVIDIA:** Used LLM agents on TrueFoundry to optimize GPU cluster utilization—achieving 80% higher utilization and saving millions in idle compute - **Whatfix:** 80% reduction in time-to-production for models; 35% cloud cost savings vs. previous SageMaker setup - **Innovaccer:** 5x faster internal AI platform productionization; 50% lower cloud spend post-migration - **Customers across:** Cargill, Mavenir, Aviva, Games24x7, Aviso, Wadhwani AI, JanitorAI, and others in banking, semiconductors, pharma, healthcare, telecom, security, and data infrastructure --- ## Get started with Truefoundry’s AI Gateway - [Book a Demo | TrueFoundry](https://www.truefoundry.com/book-demo): Schedule a demo with TrueFoundry to explore our platform's capabilities in automating ML pipelines and accelerating model deployment. Get started today! - [Create Your Free Account | TrueFoundry](https://www.truefoundry.com/register): Sign up for TrueFoundry and get started with a 7-day free trial. Experience our platform for automating ML pipelines and deploying models hassle-free. - [TrueFoundry Login | Access Your Account](https://www.truefoundry.com/login): Log in to your TrueFoundry account to access and manage your machine learning projects efficiently. Secure and easy access to all your ML tools. - [TrueFoundry | Pricing](https://www.truefoundry.com/pricing): View TrueFoundry pricing plans and choose the right option for deploying and managing machine learning workloads. - [Terms And Conditions | TrueFoundry](https://www.truefoundry.com/terms): Review the terms and conditions for using TrueFoundry's services. Understand your rights and responsibilities when accessing our platform. - [Product Tour | TrueFoundry](https://www.truefoundry.com/product-tour): Take a guided tour of TrueFoundry's platform to see how we automate ML pipelines and empower developers to deploy models quickly and effectively. --- ## Core Products - [AI Gateway For Enterprises: Built-in Governance & Monitoring](https://www.truefoundry.com/ai-gateway): Deploy and manage AI models at scale with TrueFoundry’s AI Gateway. Get centralized governance, monitoring, and secure control across AI workloads. - [MCP Gateway : Secure, Reliable, and Easy Integration](https://www.truefoundry.com/mcp-gateway): MCP Gateway for enterprises - get centralized access to multiple MCP servers. Enable agentic workflows with RBAC, OAuth 2.0, tool discovery, and observability. - [Agent Gateway: A Unified Control Plane For AI Workflows](https://www.truefoundry.com/agent-gateway): Deploy and govern AI agents using an enterprise-grade agent gateway with full observability, cost control, and secure tool access with TrueFoundry. - [AI Model Tracing & Observability](https://www.truefoundry.com/tracing): Enable tracing to monitor model performance, debug issues, and gain visibility across machine learning workflows. --- ## Resources - [AI & Machine Learning Resources](https://www.truefoundry.com/resources): Browse resources including blogs, case studies, reports, and guides on machine learning and AI platforms. - [Blog | TrueFoundry](https://www.truefoundry.com/blog): Explore the TrueFoundry blog for the latest insights, tutorials, and expert articles on Machine Learning, LLM infrastructure, and AI operations. - [Case Studies | TrueFoundry](https://www.truefoundry.com/case-studies): Discover how TrueFoundry is transforming industries with machine learning. Explore our case studies to see real-world ML applications and success stories. - [Glossary](https://www.truefoundry.com/glossary): Explore our glossary which covers the key concepts behind AI and LLM infrastructure, and more so your team speaks the same language. - [Events & Conferences](https://www.truefoundry.com/events-conferences): Explore upcoming events and conferences where TrueFoundry shares insights on machine learning, AI platforms, and MLOps. - [On-Demand AI Webinars & Expert Sessions](https://www.truefoundry.com/webinars): Browse upcoming and past TrueFoundry webinars. - [AI Models | Truefoundry AI Gateway](https://www.truefoundry.com/models): Browse and compare AI models supported by Truefoundry AI Gateway. Search by provider, features, and pricing. ### Resources | Blog - [TrueFoundry's Vision | Enterprise AI Gateway for Agentic AI](https://www.truefoundry.com/blog/truefoundry): Learn how TrueFoundry is shaping the future of enterprise AI with a unified gateway to connect, monitor, and govern agentic AI applications at scale. - [On-Prem AI Platform Guide for Enterprise Security](https://www.truefoundry.com/blog/on-premise-ai-platform): Discover everything you need to know about on premise AI platform. Understand key benefits, deployment strategies, and how Truefoundry enables scalability. - [LLMOps Architecture : A Detailed Explanation](https://www.truefoundry.com/blog/llmops-architecture): Understand LLMOps architecture through TrueFoundry’s layered gateway, orchestration, monitoring, and cost-tracking components for scalable LLM deployments. - [What Is An MCP Server? Key Features & Benefits](https://www.truefoundry.com/blog/mcp-server): Learn what an MCP server is, how it powers AI applications, and why it’s essential for secure, scalable, and efficient tool integration in modern AI systems. - [What Is an LLM Gateway and How Does It Work?](https://www.truefoundry.com/blog/llm-gateway): An LLM gateway helps manage, route, secure, and monitor large language model requests across providers. Learn how it works and why enterprises use it. - [How to Think About Gateway Architecture in the Generative AI Stack](https://www.truefoundry.com/blog/how-to-think-about-ai-gateway-architecture-in-the-generative-ai-stack): How to Think About Gateway Architecture in the Generative AI Stack - [What is LLM Inference: The Definitive Guide](https://www.truefoundry.com/blog/llm-inferencing): Learn what LLM inference is and how it works, including routing, load balancing, cost tracking, and fallback mechanisms for efficient AI deployments. - [What Is MCP Authorization? Key Concepts & Best Practices](https://www.truefoundry.com/blog/what-is-mcp-authorization): Clear explanation of what is MCP authorization, including core concepts, architecture, real-world use cases, and adoption patterns. - [LiteLLM vs LangChain: A Hands-On Comparison](https://www.truefoundry.com/blog/litellm-vs-langchain): Comparing LiteLLM vs LangChain for production AI? This guide breaks down routing, orchestration, cost control, and where each tool quietly fails at scale. - [Agentic AI in Banking: Distributed Compliance at Scale](https://www.truefoundry.com/blog/distributed-agentic-ai-in-banking): Learn how leaders use distributed Agentic AI in banking in 2026 to automate AML while meeting data residency and latency requirements with TrueFoundry. - [Multi Agent Architecture: Patterns, Use Cases & Production Reality](https://www.truefoundry.com/blog/multi-agent-architecture): Explore multi agent architecture patterns and use cases. Learn why traditional serverless platforms fail long-running agents and how to deploy them. - [Azure AI Gateway Pricing in 2026: Costs and Components](https://www.truefoundry.com/blog/understanding-azure-ai-gateway-pricing-for-2026---a-complete-breakdown): A detailed breakdown of Azure AI Gateway pricing, Azure OpenAI costs, and hidden enterprise expenses. Learn when teams consider alternatives like TrueFoundry. - [Top 5 LiteLLM Alternatives in 2026](https://www.truefoundry.com/blog/litellm-alternatives): Explore enterprise-grade LiteLLM alternatives, offering end-to-end observability, governance, security, and scalable LLM operations beyond basic orchestration. - [How to Build Persistent Memory for AI Applications](https://www.truefoundry.com/blog/truemem-building-a-model-agnostic-memory-layer-for-ai): Meta Description: Learn how TrueMem solves the AI amnesia problem with a dual-memory architecture that works across multiple models and chat sessions. - [Benchmarking LLM Guardrail Providers: A Data-Driven Comparison](https://www.truefoundry.com/blog/benchmarking-llm-guardrail-providers): A data-driven comparison of leading LLM guardrail providers across PII detection, content moderation, and prompt injection using balanced evaluation datasets and latency analysis. - [Agentic AI Security: Top 5 Risks Enterprises Should Know](https://www.truefoundry.com/blog/agentic-ai-security): Agentic AI security is underprepared. Here are 5 things every security and engineering leader must understand before agents go into production. - [Amazon Bedrock Agents vs. TrueFoundry: Architectural Review of LLM Agent Control Planes](https://www.truefoundry.com/blog/amazon-bedrock-agents-vs-the-control-plane-an-architectural-review): Compare Amazon Bedrock Agents vs. TrueFoundry. Analyze trade-offs in observability, universal tool integration, and semantic routing for multi-cloud agents. - [Amazon Bedrock Review (2026): Is It Production Ready?](https://www.truefoundry.com/blog/our-honest-review-of-amazon-bedrock-2026-edition): We tested AWS Bedrock so you don’t have to. Read our honest review on latency, throttling, knowledge bases, and why enterprises add TrueFoundry for control. - [Core Differences Between MCP Authentication and Authorization](https://www.truefoundry.com/blog/mcp-authentication-and-authorization): MCP authentication and authorization are not the same. Confusing them leaves your agents over-exposed. Here is how each works and why both matter. - [Cognita: Open Source Modular RAG Apps for Production](https://www.truefoundry.com/blog/cognita-building-an-open-source-modular-rag-applications-for-production): Explore how Cognita achieves customizability and scalability, adapting to AI advancements while maintaining user-friendliness and long-term value. - [What Is AI Security: Definition and How Enterprises Respond](https://www.truefoundry.com/blog/what-is-ai-security): Learn what is AI security, the core threats facing enterprise AI systems, and the practical steps enterprises take to protect models and agents in production. - [Intelligent Document Processing Accelerator by TF](https://www.truefoundry.com/blog/truefoundry-intelligent-document-processing-accelerator): In-depth breakdown of truefoundry intelligent document processing accelerator, focusing on architecture, benefits, challenges, and enterprise… - [Secure OpenCode In-House: TrueFoundry Private Code Interpreter](https://www.truefoundry.com/blog/bringing-opencode-in-house-secure-tool-usage-on-truefoundry): Build a secure, in-house 'OpenCode' Private Code Interpreter with TrueFoundry. Learn the architecture and security benefits of running code execution next to your sensitive data inside your VPC. - [What is AI Agent Registry - A Complete Guide](https://www.truefoundry.com/blog/ai-agent-registry): Learn what an AI agent registry is, how it works, its architecture, benefits, challenges, and why enterprises use it. - [Secure AI Gateway with MCP: Enterprise-Ready Protection](https://www.truefoundry.com/blog/enterprise-ready-mcp-gateway): Discover how a secure AI gateway for MCP protects data, enforces access control, and enables safe AI tool integration for scalable, compliant enterprise automation. - [Amazon SageMaker Review 2026: Features, Pricing, Pros & Cons](https://www.truefoundry.com/blog/amazon-sagemaker-review-features-pricing-pros-and-cons-better-alternative): SageMaker review covering real user feedback, pricing breakdown, key features, and pros/cons. Discover why teams are switching to alternatives in 2026. - [Building a Resilient Web Scraper: LangGraph, TrueFoundry & Semantic AI](https://www.truefoundry.com/blog/accelerator-series-building-a-resilient-web-scraper-with-langgraph-and-truefoundry): Learn how to build a resilient, autonomous web scraping agent that uses LangGraph and LLMs for semantic extraction instead of brittle DOM selectors. Deploy on TrueFoundry with an AI Gateway for observability, caching, and failover. - [Cloudflare AI Gateway Pricing Explained For 2026](https://www.truefoundry.com/blog/cloudflare-ai-gateway-pricing): Learn how Cloudflare AI Gateway pricing works, what impacts cost, and when teams consider alternatives for predictable AI spend. Compare Cloudflare plans now. - [LiteLLM Review 2026: Features, Pricing, Pros and Cons](https://www.truefoundry.com/blog/a-detailed-litellm-review-features-pricing-pros-and-cons-2026): Is LiteLLM the best open‑source AI gateway? We review its features, enterprise limitations, and when teams switch to managed platforms like TrueFoundry. - [AWS & TrueFoundry: Control Plane Architecture for GenAI](https://www.truefoundry.com/blog/how-truefoundry-integrates-with-aws-the-architecture-of-a-control-plane): Deep dive into the TrueFoundry AWS integration architecture. Learn how a control plane approach enhances security, optimizes EKS compute costs, and streamlines GenAI deployment on your existing infrastructure. - [MCP Tool Discovery for Enterprise AI Agents](https://www.truefoundry.com/blog/mcp-tool-discovery-for-enterprise-ai-agents): Learn how MCP tool discovery works, why static tool configs fail at scale, and how enterprise AI platforms enable secure, runtime discovery. - [Enterprise Security for Claude: A Practical Governance Guide for Engineering Teams](https://www.truefoundry.com/blog/enterprise-security-for-claude): A practical guide to securing Claude for enterprise teams across web, desktop, and CLI — covering SSO, sandboxing, MCP governance, and managed settings. - [Secure AI Hackathons: Control Keys, Budgets, and Agent Risk with TrueFoundry](https://www.truefoundry.com/blog/how-to-host-an-ai-hackathon-without-losing-control-of-your-keys-or-budget-the-truefoundry-architecture): Host enterprise AI hackathons with safer key handling, per-team spend controls, metadata-scoped rate limits, governed agent workflows, and a playground that tests through the same gateway path used in production. - [Multi-Cloud GPU Orchestration for LLMs | TrueFoundry](https://www.truefoundry.com/blog/multi-cloud-gpu-orchestration-integrating-specialized-clouds-with-truefoundry): Solve the GPU compute crunch. Use TrueFoundry to orchestrate LLM training and inference across AWS, CoreWeave, and Lambda Labs with a unified Kubernetes control plane. - [AWS Bedrock Pricing Explained: Model Costs, Usage Patterns, and Key Considerations](https://www.truefoundry.com/blog/aws-bedrock-pricing-explained-everything-you-need-to-know): A clear breakdown of AWS Bedrock pricing, model costs, and usage patterns. Learn how pricing scales and what teams should plan for. - [Multi-Model Routing: Optimize AI Tasks Efficiently](https://www.truefoundry.com/blog/multi-model-routing): Learn how multi-model routing directs queries to the best AI models, improving speed, accuracy, and cost-efficiency for complex and simple tasks alike. - [Bifrost Alternatives: Top Tools You Can Consider in 2026](https://www.truefoundry.com/blog/bifrost-alternative-mcp-gateway): The 6 best Bifrost MCP gateway alternatives in 2026 — compared on native MCP support, enterprise governance, observability, and deployment flexibility to help you choose the right platform. - [A Definitive Guide to AI Gateways in 2026: Competitive Landscape Comparison](https://www.truefoundry.com/blog/a-definitive-guide-to-ai-gateways-in-2026-competitive-landscape-comparison): A practical comparison of AI gateways and platforms, examining Kong, Portkey, LiteLLM, and TrueFoundry as AI moves into production. - [MCP Security Explained: Guide to Zero Trust for Agentic AI](https://www.truefoundry.com/blog/mcp-security): MCP security is no longer optional. As AI agents gain access to real tools and live data, here is how Zero Trust principles stop threats teams don't anticipate. - [Query Structured & Unstructured Data Using MCP Tools](https://www.truefoundry.com/blog/truefoundry-accelerator-series-querying-structured-and-unstructured-data-seamlessly-with-mcp-tools): In-depth breakdown of truefoundry accelerator series querying structured and unstructured data seamlessly with mcp tools, focusing on… - [Obot AI Alternatives: Top 6 Tools You Can Consider in 2026](https://www.truefoundry.com/blog/obot-ai-alternatives): Let's discuss the top Obot AI alternatives in 2026. Compare MCP gateways, AI agent platforms, and tools for production infrastructure, observability, and control. - [Building Resilient Web Automation: From Web Scraping to Semantic Web Operating](https://www.truefoundry.com/blog/building-resilient-web-automation-when-apis-dont-exist): Discover the next generation of web automation. Learn how the TrueFoundry Accelerator uses the Accessibility Object Model (AOM) and a Controller-Worker pattern to build resilient agents that succeed where brittle web scraping fails. - [Best MCP Servers for Cursor AI: Tools Every Developer Should Use](https://www.truefoundry.com/blog/best-mcp-servers-for-cursor-ai): Discover the best MCP servers for Cursor AI. Learn how to integrate GitHub, databases, APIs, and more to build powerful AI-driven development workflows. - [AutoGen vs LangGraph: Comparing Multi-Agent AI Frameworks](https://www.truefoundry.com/blog/autogen-vs-langgraph): Compare AutoGen vs LangGraph covering features, architecture differences, trade-offs, and best use cases. - [10 Best AI Observability Platforms for LLMs in 2026](https://www.truefoundry.com/blog/best-ai-observability-platforms-for-llms-in-2026): Discover the top AI observability platforms for 2026 to track cost, latency, hallucinations, and compliance. Compare TrueFoundry, Arize, LangSmith, and more. - [Top 8 Amazon Bedrock Alternative and Competitors for 2026](https://www.truefoundry.com/blog/top-8-amazon-bedrock-alternative-and-competitors-for-2026-detailed-review): Break free from AWS lock-in. Discover top Amazon Bedrock alternatives with multi-cloud flexibility, transparent pricing, and unlimited model support. - [Cursor vs GitHub Copilot: Which AI Coding Tool Should You Use in 2026?](https://www.truefoundry.com/blog/cursor-vs-github-copilot): Cursor vs GitHub Copilot? Compare features, pricing, agent mode, and context awareness to pick the right AI coding tool for your team. - [What is LLMOps ? The Ultimate Guide](https://www.truefoundry.com/blog/what-is-llmops): LLMOps is the operational layer around LLMs—TrueFoundry defines it as gateway‑driven orchestration, observability, fallback, and cost control wrapped around model deployments for enterprise readiness. - [Kong vs LiteLLM: Architecture, Pricing, and Trade‑Offs](https://www.truefoundry.com/blog/kong-vs-litellm): Compare Kong vs LiteLLM across architecture, pricing, security, and ops overhead. Know why enterprises consider managed platforms like TrueFoundry. - [From Browser to Prompt: Building Infra for the Agentic Internet](https://www.truefoundry.com/blog/building-infra-for-the-agentic-internet): Explore the shift from browser-driven workflows to prompt-driven execution—and the gateway, MCP, and control plane infrastructure powering production agentic AI. - [The Hidden Costs of GenerativeAI and How to Control Them](https://www.truefoundry.com/blog/cost-of-generative-ai): The cost of generative AI goes well beyond API fees. Here is what enterprises consistently underestimate and how to build GenAI that scales without runaway spend. - [Claude Code --dangerously-skip-permissions: What It Does and When Not to Use It](https://www.truefoundry.com/blog/claude-code-dangerously-skip-permissions): Learn what --dangerously-skip-permissions does in Claude Code, what security controls it bypasses, and how enterprises should use it safely in automated pipelines. - [6 Best LLM Gateways in 2026](https://www.truefoundry.com/blog/best-llm-gateways): Explore and compare the best LLM gateways, their key features, use cases, and how they help deploy, secure, and scale generative AI systems. - [Victorialogs vs Loki - Benchmarking Results](https://www.truefoundry.com/blog/victorialogs-vs-loki): Side-by-side comparison of victorialogs vs loki, covering features, architecture differences, trade-offs, and best use cases. - [Kong Gateway Latest Pricing Explained for 2026](https://www.truefoundry.com/blog/kong-gateway-pricing-architecture-an-analysis-for-ai-teams-2026-edition): A complete breakdown of Kong Gateway pricing, including Konnect vs Enterprise costs, AI plugin limitations, and why teams choose AI‑native alternatives. - [Databricks vs. AWS SageMaker: Key Differences You Should Know](https://www.truefoundry.com/blog/databricks-vs-aws-sagemaker-what-is-the-difference-and-which-one-should-you-pick): A clear comparison of Databricks vs AWS SageMaker, covering architecture, pricing models, and why teams choose compute‑neutral platforms likeTrueFoundry. - [Understanding Databricks Mosaic AI Gateway Pricing in 2026 Meta](https://www.truefoundry.com/blog/databricks-mosaic-ai-gateway-pricing-explained-2026): A complete breakdown of Databricks Mosaic AI Gateway pricing, DBUs, and hidden costs. Learn when teams consider alternatives like TrueFoundry. - [Enterprise MCP access control: managing tools, servers, and agents](https://www.truefoundry.com/blog/enterprise-mcp-access-control): Learn how Virtual MCP Servers, protocol-level guardrails, and gateways prevent “root access” AI agents—enabling secure, scoped enterprise agent execution - [5 Best MCP Gateways in 2026](https://www.truefoundry.com/blog/best-mcp-gateways): Explore the best MCP gateways, including Truefoundry. Compare top scalable platforms for model routing, observability, authentication, and cost control. - [Understanding What is MCP Authentication and How It Works](https://www.truefoundry.com/blog/mcp-authentication): MCP authentication is the security layer every AI agent deployment needs. Learn how it works, what OAuth 2.1 changes, and how enterprises enforce it without complexity. - [A Systematic Prompt Enhancement Workflow for Production AI](https://www.truefoundry.com/blog/stop-guessing-start-measuring-a-systematic-prompt-enhancement-workflow-for-production-ai-systems): Learn a practical prompt enhancement workflow for production AI: score prompts, fix structural gaps, test on eval sets, and compare across models. - [Claude Code Workflow: How It Works and How to Use It in Production](https://www.truefoundry.com/blog/claude-code-workflow-guide): Learn how Claude Code workflows really work — from context ingestion to iteration. Discover failure modes, scaling challenges, and best practices for production use. - [Best AI Code Security Tools for Enterprise in 2026: Reviewed & Compared](https://www.truefoundry.com/blog/best-ai-code-security): Compare 8 AI code security tools for enterprise in 2026 — from governance platforms like TrueFoundry to scanners like Snyk and Checkmarx. Find the right fit for your team's risk profile. - [LLMOps CoE: The Next Frontier in MLOps | TrueFoundry](https://www.truefoundry.com/blog/the-future-is-here-llmops): Dive into LLMOps CoE: Uncover its modern ML operational significance. See how it streamlines workflows and boosts efficiency for impactful results. - [How to Add an MCP Server to Claude Code (Step-by-Step Guide)](https://www.truefoundry.com/blog/how-to-add-an-mcp-server-to-claude-code): - [Prompt Injection and AI Agent Security Risks: A Claude Code Guide for Enterprise Teams](https://www.truefoundry.com/blog/claude-code-prompt-injection): Understand how prompt injection and other AI agent security risks affect Claude Code in enterprise environments, and the infrastructure controls that actually prevent them. - [10 Gartner-Backed Recommendations for Enterprises to Reduce GenAI Costs](https://www.truefoundry.com/blog/the-real-cost-of-generative-ai): Gartner “10 Best Practices for Optimizing Generative and Agentic AI Costs” focuses on how enterprises must rethink cost, governance, and operational control as AI systems move into production. TrueFoundry is mentioned in this report in the context of AI gateways - [Akto Partners with TrueFoundry to Bring Security Guardrails to AI Agents](https://www.truefoundry.com/blog/akto-partners-with-truefoundry-to-bring-security-guardrails-to-ai-agents): - [AWS Bedrock vs Azure AI: Which Platform Fits Best?](https://www.truefoundry.com/blog/aws-bedrock-vs-azure-ai-which-ai-platform-to-choose): A clear comparison of AWS Bedrock vs Azure AI, covering pricing, lock‑in risks, and why multi‑cloud teams choose TrueFoundry. - [MCP vs RAG: Key Differences and Use Cases](https://www.truefoundry.com/blog/mcp-vs-rag): Compare MCP vs RAG on the basis of architecture, key features, trade-offs, use cases, and when to use each for building AI applications. - [8 Best Databricks Mosaic Alternatives for AI Developers](https://www.truefoundry.com/blog/8-best-databricks-mosaic-ai-alternatives): Escape Databricks lock-in and cost complexity. Discover top Mosaic AI alternatives for 2026 with cloud-agnostic flexibility, GenAI-native tools, and transparent pricing. - [AI Gateways: From Outage Panic to Enterprise Backbone](https://www.truefoundry.com/blog/ai-gateways-from-outage-panic-to-enterprise-backbone): As AI becomes mission-critical, enterprises need a trusted control layer. This post explores how AI Gateways—a technology recognized by Gartner —solve challenges with reliability and spiraling costs - [Claude Code Governance: Building an Enterprise Usage Policy from Scratch](https://www.truefoundry.com/blog/claude-code-governance-building-an-enterprise-usage-policy-from-scratch): Build a Claude Code enterprise usage policy from scratch. Covers managed settings, permissions, MCP governance, audit logging, spend controls, and phased rollout. - [Cursor AI Setup Guide: Getting Started with AI-Assisted Development](https://www.truefoundry.com/blog/cursor-ai-setup-guide): - [LLM Load Balancing](https://www.truefoundry.com/blog/llm-load-balancing): Learn about LLM load balancing, including its architecture, routing strategies, failover, cost optimization, and enterprise best practices. - [Autonomous Agents: Solve SEO Bottlenecks with TrueFoundry](https://www.truefoundry.com/blog/solving-seo-data-bottlenecks-with-autonomous-agents-and-truefoundry): TrueFoundry's Keyword Automation Agent and AI Gateway solve SEO data bottlenecks. Transform manual analysis into a resilient, scalable, event-driven pipeline, cutting time-to-insight from days to minutes. - [Best MCP Security Tools in 2026](https://www.truefoundry.com/blog/best-mcp-security-tools): Discover the best MCP security tools in 2026. Compare top options by threat coverage, access control, and enterprise readiness to secure your AI agent stack. - [8 Best Mint MCP Alternatives for AI Agent Infrastructure in 2026](https://www.truefoundry.com/blog/best-mint-mcp-alternatives-for-ai-agent-infrastructure): Let's discuss the best Mint MCP alternatives in 2026. Compare MCP gateways, AI infrastructure tools, and platforms for performance, security, and scalability. - [TrueFoundry on OCI: Bare-Metal AI Architecture](https://www.truefoundry.com/blog/orchestrating-bare-metal-ai-truefoundry-integration-with-oracle-cloud-infrastructure): Learn how to orchestrate bare-metal AI workloads on OCI with TrueFoundry. Read the technical integration covering OKE, RDMA networking, and Block Volume. - [Requesty vs OpenRouter: A Detailed Comparison](https://www.truefoundry.com/blog/requesty-vs-openrouter): Choose between Requesty vs OpenRouter for your LLM stack. Explore routing, cost, and governance, plus how TrueFoundry adds self-hosted VPC support. - [Understanding Portkey AI Gateway Pricing For 2026](https://www.truefoundry.com/blog/portkey-pricing-guide): A complete breakdown of Portkey AI Gateway pricing, including usage costs, guardrails, MCP features, and hidden limitations. Learn when teams choose TrueFoundry. - [Smart Movie Co-pilot: Resilient Web Automation with TrueFoundry & Google ADK](https://www.truefoundry.com/blog/collaborative-web-actions-building-a-smart-movie-co-pilot-with-truefoundry-and-google-adk): Deploy a highly resilient AI Movie Co-pilot using our new TrueFoundry Accelerator and Google ADK. Built on a unique collaborative handoff model, this production-ready blueprint uses a server-side browser agent to navigate complex sites like Fandango while ensuring security for payment steps. - [The Infrastructure for an Agent-to-Agent Economy](https://www.truefoundry.com/blog/the-infrastructure-for-an-agent-to-agent-economy): Agent systems fail in production due to missing infrastructure, not intelligence. Discover how control planes, gateways, and Agent APIs enable governable autonomy. - [Cloudflare AI Gateway Pricing Explained For 2026](https://www.truefoundry.com/blog/cloudflare-ai-gateway-pricing-a-complete-breakdown): Learn how Cloudflare AI Gateway pricing works, what impacts cost, and when teams consider alternatives for predictable AI spend. Compare Cloudflare plans now. - [Amazon SageMaker AI Pricing: A Detailed Breakdown](https://www.truefoundry.com/blog/amazon-sagemaker-ai-pricing-a-detailed-breakdown-and-better-alternative): A detailed breakdown of Amazon SageMaker pricing, including training, inference, and hidden costs. Learn when teams consider alternatives like TrueFoundry. - [truefailover™: Ensure Business-Critical AI Workflows Are Uninterrupted](https://www.truefoundry.com/blog/introducing-truefailover-tm-ensure-business-critical-ai-workflows-are-uninterrupted): Introducing truefailover™ by TrueFoundry, a new resilience layer that keeps business-critical AI workflows running through model outages, regional failures, and API degradation. - [Cursor vs Claude Code: Which AI Coding Agent Is Better for Production Development?](https://www.truefoundry.com/blog/cursor-vs-claude-code): - [MCP Registry: The Infrastructure Layer for Production LLM Agents](https://www.truefoundry.com/blog/what-is-mcp-registry-and-why-you-cant-run-agents-without-one): Learn how the MCP Registry and TrueFoundry's Virtual MCP Servers solve the agent connection problem ("N x M" matrix) by providing dynamic tool discovery, centralized authentication, and critical governance for running large-scale LLM agents in production. - [OpenRouter Vs AI Gateway: Differences, Use Cases & Best Choice](https://www.truefoundry.com/blog/openrouter-vs-ai-gateway): Compare OpenRouter vs AI Gateway in detail. Learn key differences, architecture, use cases, and which solution is best for prototyping vs production AI systems. - [Best MCP Automation Platforms for Enterprise](https://www.truefoundry.com/blog/mcp-automation-platforms-for-enterprise): In-depth breakdown of mcp automation platforms for enterprise, focusing on architecture, benefits, challenges, and enterprise relevance. - [Best MCP Servers for Claude Code](https://www.truefoundry.com/blog/best-mcp-servers-for-claude-code): - [Running LLMs on OpenShift: SCCs, IAM, and Watsonx Integration](https://www.truefoundry.com/blog/architecting-llms-on-openshift-solving-sccs-and-hybrid-identity): Technical guide for deploying LLMs on Red Hat OpenShift. Covers solving Security Context Constraints (SCCs), IBM Cloud IAM federation, and GPU scheduling - [Understanding LiteLLM Pricing: Cost of Open Source Gateways](https://www.truefoundry.com/blog/litellm-pricing-guide): A complete breakdown of LiteLLM AI Gateway pricing, including open‑source usage, enterprise add‑ons, and hidden operational costs. Learn when teams choose TrueFoundry. - [Enterprise Intent Classification with SetFit | TF Series](https://www.truefoundry.com/blog/truefoundry-accelerator-series-building-enterprise-grade-intent-classification-with-setfit): In-depth breakdown of truefoundry accelerator series building enterprise grade intent classification with setfit, focusing on architecture,… - [Portkey vs LiteLLM: Which is Best?](https://www.truefoundry.com/blog/portkey-vs-litellm): Compare Portkey vs LiteLLM: Portkey offers enterprise-grade observability, RBAC, and routing, while LiteLLM provides lightweight LLM orchestration. - [Cursor for AIOps: Where AI Coding Agents Help in Incident Response (and Where They Don't)](https://www.truefoundry.com/blog/cursor-for-aiops): Learn where AI coding agents such as Cursor help SREs with incident response—debugging, runbooks, IaC fixes—and where they fall short in production. - [Claude Code MCP Integrations: How Tools Connect to AI Coding Agents](https://www.truefoundry.com/blog/claude-code-mcp-integrations-guide): Learn how Claude Code uses the Model Context Protocol to connect with external tools—covering MCP architecture, integration types, limitations, and production best practices. - [Top 9 Cloudflare AI Alternatives and Competitors For 2026 (Ranked)](https://www.truefoundry.com/blog/top-9-cloudflare-ai-alternatives-and-competitors-for-2026-ranked): Scale your AI without limits. Discover top Cloudflare AI alternatives for 2026 that deliver private cloud control and cheaper inference costs. - [MCP Servers in Claude Code](https://www.truefoundry.com/blog/mcp-servers-in-claude-code): Learn what MCP (Model Context Protocol) is, how it simplifies AI–tool integrations, its architecture, and how to set up MCP servers in Claude Code. - [MCP Authentication in Claude Code 2026 Guide](https://www.truefoundry.com/blog/mcp-authentication-in-claude-code): Learn how to securely configure MCP authentication in Claude Code. This 2026 guide covers API keys, Bearer tokens, AWS credentials, IAM role assumption, OAuth flows, CLI setup, and security best practices for production environments. - [Supply Chain Attacks in AI: What the LiteLLM Incident Reveals](https://www.truefoundry.com/blog/supply-chain-attack-ai-infrastructure-litellm): A sophisticated supply chain attack targeted AI infrastructure in March 2026. Here's what happened, why it matters, and how to protect your ML stack. - [Langflow vs LangGraph: Which LLM Framework Fits Best?](https://www.truefoundry.com/blog/langflow-vs-langgraph): Compare Langflow and LangGraph for LLM apps. Learn how Langflow enables visual prototyping while LangGraph powers stateful, production-ready AI workflows. - [MCP Authentication in Cursor: OAuth, API Keys, and Secure Configuration (2026 Guide)](https://www.truefoundry.com/blog/mcp-authentication-in-cursor-oauth-api-keys-and-secure-configuration): Learn how MCP authentication works in Cursor, including OAuth 2.1 with PKCE, API keys, static headers, and secure mcp.json configuration. Understand spec updates (2025), real-world vulnerabilities, and enterprise best practices for protecting MCP servers in 2026. - [Enterprise MCP Server: Secure AI System Integration](https://www.truefoundry.com/blog/mcp-server-in-enterprise): Enterprise MCP Servers enable secure, scalable AI integration, offering control, speed, governance, and seamless access to AI tools and data. - [Building the Enterprise AI Control Plane: Gartner® Insights and TrueFoundry’s Approach](https://www.truefoundry.com/blog/building-the-enterprise-ai-control-plane-gartner-r-insights-and-truefoundrys-approach): Gartner recognizes TrueFoundry as a representative vendor for our product, the TrueFoundry AI Gateway. Read the full report to learn more about key emerging trends in the AI Gateway landscape - [From GenAI to Agentic AI: Episode 3 of Tesseract Talks](https://www.truefoundry.com/blog/from-genai-to-agentic-ai-episode-3-of-tesseract-talks): how do you move from isolated AI features to intelligent systems that can operate safely, reliably, and at scale? That question was at the heart of a recent episode of Tesseract Talks, with Anuraag Gutgutia. - [Vercel AI Pricing Plans 2026: How Much Does It Cost?](https://www.truefoundry.com/blog/understanding-vercel-ai-gateway-pricing): A deep dive into Vercel AI pricing, including the AI Gateway credits, streaming costs, and execution limits. See where Vercel falls short in this detailed guide. - [Vercel AI Review 2026: Detailed Analysis](https://www.truefoundry.com/blog/vercel-ai-review-2026-we-tested-it-so-you-dont-have-to): Is Vercel AI Gateway production‑ready? We tested the Edge Runtime and pricing limits. See where it shines, where it breaks, and why teams move to TrueFoundry. - [Bifrost vs LiteLLM: Choosing the Right AI Gateway](https://www.truefoundry.com/blog/bifrost-vs-litellm): Compare Bifrost vs LiteLLM across performance, observability, and scalability. Discover which LLM router is best for enterprise AI and production workloads. - [Architecting TrueFoundry on Azure: AKS & Control Plane Integration](https://www.truefoundry.com/blog/architecting-truefoundry-on-azure-control-plane-and-compute-integration): Technical guide to integrating TrueFoundry with Microsoft Azure. Learn how we utilize AKS, Entra Workload ID, and Azure OpenAI within a split-plane architecture. - [What is Data Residency?](https://www.truefoundry.com/blog/data-residency): Discover why data residency is becoming mission-critical in the era of Agentic AI. Learn how TrueFoundry’s AI Gateway enables enterprises to maintain sovereignty, compliance, and scale with region-aware routing, logging, and governance. - [Build a Calendar Scheduling AI Agent | TF Accelerator](https://www.truefoundry.com/blog/truefoundry-accelerator-series-calender-scheduling-agent): In-depth breakdown of truefoundry accelerator series calender scheduling agent, focusing on architecture, benefits, challenges, and enterprise… - [Data Residency in TrueFoundry AI Gateway: From Configuration to Runtime Enforcement](https://www.truefoundry.com/blog/data-residency-in-truefoundry-ai-gateway): Learn how TrueFoundry’s AI Gateway enforces data residency at runtime across inference, agents, tools, and observability for enterprise AI systems. - [What Is an MCP Gateway: Architecture and Use Cases](https://www.truefoundry.com/blog/what-is-mcp-gateway): Learn what is an MCP Gateway, how it works, and how it differs from API gateways and servers. Understand how enterprises deploy MCP Gateways securely. - [Cursor AI MCP Server Configuration: A Complete Setup Guide](https://www.truefoundry.com/blog/cursor-ai-mcp-server-configuration): A complete guide to Cursor AI MCP server configuration. Learn setup, authentication, and best practices for building agent-driven workflows. - [On-Prem AI Stack: From Chips to Control Planes | TrueFoundry](https://www.truefoundry.com/blog/mapping-the-on-prem-ai-market-from-chips-to-control-planes): A practical map of the on-prem AI stack—from GPUs and InfiniBand to Kubernetes, Triton/vLLM and AI gateways—plus vendor picks, cost control and governance. - [OpenCode Token Usage: How It Works and How to Optimize It](https://www.truefoundry.com/blog/opencode-token-usage-how-it-works-and-how-to-optimize-it): Understand OpenCode token usage, why costs spike at scale, and how to monitor, govern, and optimize token consumption across developers and automation. - [TrueFoundry on GCP: GKE, TPU, and Workload Identity Architecture](https://www.truefoundry.com/blog/how-truefoundry-integrates-with-gcp-the-control-plane-architecture): Technical deep dive on TrueFoundry's GCP integration. Covers split-plane security, GKE networking, Workload Identity Federation, and Spot VM orchestration. - [AWS Bedrock vs. AWS SageMaker: Key Differences & When to Switch](https://www.truefoundry.com/blog/aws-bedrock-vs-aws-sagemaker-for-ai-key-differences-you-should-know): A clear comparison of AWS Bedrock vs AWS SageMaker, covering pricing models, hidden trade‑offs, and why scaling teams choose TrueFoundry. - [MCP vs A2A: Compare Single-Agent & Multi-Agent Protocols](https://www.truefoundry.com/blog/mcp-vs-a2a): Explore MCP vs A2A differences: MCP boosts single-agent tasks, while A2A enables multi-agent collaboration, task sharing, and dynamic workflows. - [MCP Servers in Cursor: Setup, Configuration, and Security (2026 Guide)](https://www.truefoundry.com/blog/mcp-servers-in-cursor-setup-configuration-and-security-guide): Learn how to set up, configure, and secure MCP servers in Cursor. This 2026 guide covers stdio vs. Streamable HTTP, mcp.json best practices, tool limits, common errors, major 2025 CVEs, and how teams scale with an MCP Gateway. - [In 2026, AI Gateways Will Need to Become a Board-Level Priority](https://www.truefoundry.com/blog/in-2026-ai-gateways-will-need-to-become-a-board-level-priority): - [Best MCP Registries in 2026: Compared for Developers and Enterprises](https://www.truefoundry.com/blog/best-mcp-registries): Discover the best MCP registries in 2026. Compare top options by governance, enterprise readiness, and security to find the right fit for your agentic AI stack. - [Claude Code Sandboxing: Network Isolation, File System Controls, and Container Security](https://www.truefoundry.com/blog/claude-code-sandboxing): Learn how to sandbox Claude Code for enterprise use — network isolation, file system scoping, container-level controls, and data privacy protections explained for production teams. - [What Is MCP? Use Cases & Benefits Explained](https://www.truefoundry.com/blog/mcp): Discover what MCP (Model Context Protocol) is, how it works, and why it’s vital for AI workflows, enabling secure, modular, and efficient tool integration. - [Best OpenRouter Alternatives for Production AI Systems](https://www.truefoundry.com/blog/openrouter-alternatives): Explore OpenRouter alternatives designed for production AI, with deeper control, compliance readiness, and multi-model governance. - [Shadow AI Risk: What Leaders Must Do Now](https://www.truefoundry.com/blog/shadow-ai-risk): Shadow AI risk is growing as rigid enterprise AI platforms push teams toward unsanctioned tools. Learn how leaders can regain control securely. - [What is Shadow AI?](https://www.truefoundry.com/blog/what-is-shadow-ai): Clear explanation of what is shadow ai, including core concepts, architecture, real-world use cases, and adoption patterns. - [AI Gateway as the Control Plane for Modern GenAI Stacks](https://www.truefoundry.com/blog/ai-gateway-a-core-part-of-the-control-plane-in-the-modern-generative-ai-stack): In-depth breakdown of ai gateway a core part of the control plane in the modern generative ai stack, focusing on architecture, benefits,… - [An Architect’s POV: The Ideal Gen-AI Stack for On-Prem](https://www.truefoundry.com/blog/an-architects-pov-what-an-ideal-gen-ai-application-stack-must-deliver): From security and data residency to latency and cost control—an architect’s guide to the ideal Gen-AI stack for on-prem deployments with TrueFoundry. - [Maximizing ROI with ML/LLM Cost Optimization](https://www.truefoundry.com/blog/reduces-your-llm-infra-cost): Uncover TrueFoundry's strategies to slash infrastructure costs for ML/LLM models while boosting efficiency and returns on investment. - [TrueFoundry AI Gateway: FIPS Compliance on AWS & Azure Gov](https://www.truefoundry.com/blog/leveraging-the-truefoundry-ai-gateway-for-fips-compliance): Build sovereign AI on GovCloud. TrueFoundry’s Gateway ensures FIPS compliance, secure API key custody, and PII guardrails on AWS and Azure Government. - [Top 5 Obot MCP Gateway Alternatives](https://www.truefoundry.com/blog/obot-mcp-gateway-alternatives): Detailed comparison of obot mcp gateway alternatives, including strengths, limitations, and when to choose each for enterprise AI. - [AI Cost Observability for LLM and Agent Workloads](https://www.truefoundry.com/blog/ai-cost-observability): Learn how AI cost observability helps teams track, attribute, and control LLM spend across models, prompts, agents, and workflows using AI gateways. - [What Are Multi-Agent Systems?](https://www.truefoundry.com/blog/multi-agent-systems): In-depth breakdown of multi agent systems, focusing on architecture, benefits, challenges, and enterprise relevance. - [Is TrueFoundry ML Platform Right for You? | TrueFoundry](https://www.truefoundry.com/blog/is-truefoundry-ml-platform-right-for-you): Evaluate whether TrueFoundry's ML platform is the right fit for your organization with our comprehensive guide. Learn more in detail on this article. - [Top 8 Vertex AI Alternatives in 2026](https://www.truefoundry.com/blog/exploring-alternatives-to-vertexai): Discover 8 powerful Vertex AI alternatives that fit your needs. Compare tools and make informed choices with TrueFoundry's expert insights. - [Data Residency Comparison for AI Gateways | TrueFoundry](https://www.truefoundry.com/blog/ai-gateway-data-residency-comparison): Compare data residency support across leading AI Gateways. See how gateways enforce regional inference, deployment models, and compliance. - [TrueFoundry & Enkrypt AI Partnership for Responsible AI Governance](https://www.truefoundry.com/blog/a-partnership-for-responsible-ai-truefoundry-and-enkrypt-ai): TrueFoundry and Enkrypt AI partner to offer a full-stack solution for AI governance, security, and compliance. Learn how the combined power of an AI Gateway and advanced guardrails enables responsible AI deployment for enterprises. - [TrueML Talks #28: GenAI & LLMs for Sales Outreach](https://www.truefoundry.com/blog/genai-and-llms-for-sales-outreach-oneshot): Discover GenAI and LLMs strategies for sales outreach at OneShot on TrueML Talks #28. Optimize sales processes with ML insights. - [Observability in AI Gateways: Key Metrics and Examples](https://www.truefoundry.com/blog/observability-in-ai-gateway): Learn how observability using AI Gateway improves performance, cost tracking, reliability, and operational insights with key metrics and workflows. - [How to build an ITAR Compliant AI Gateway?](https://www.truefoundry.com/blog/what-is-itar): Learn how to design and deploy an ITAR-compliant AI Gateway that ensures secure, auditable, and policy-driven access to AI models and tools. Explore best practices, key requirements, and how TrueFoundry enables enterprise-grade compliance. - [Specialized Observability for Production Voice AI: ASR, RAG, and TTS Stacks](https://www.truefoundry.com/blog/beyond-the-log-file-why-specialized-observability-is-non-negotiable-for-production-voice-ai): A deep dive into the unique challenges of running large-scale, production-grade Voice AI stacks (ASR, TTS, RAG, Agents). Learn why standard APM tools are inadequate and how specialized observability, like TrueFoundry, is non-negotiable for ensuring system stability and preventing catastrophic failures. - [Helicone vs Portkey: Key Features, Pros, and Cons](https://www.truefoundry.com/blog/helicone-vs-portkey): Unsure between Helicone and Portkey? Compare how they stack up on observability, cost optimization, and deployment and choose the right gateway. - [True ML Talks #18 - Generative AI Discussion with Tushar Kant](https://www.truefoundry.com/blog/llm-and-machine-learning-platform-iitforum): Join True ML Talks #18 for a discussion on Generative AI with Tushar Kant. Explore advancements in AI technology. - [Agentic AI in Enterprises: Scaling Autonomous Systems](https://www.truefoundry.com/blog/agentic-ai-in-enterprise): Explore how agentic AI in enterprises can deploy autonomous, goal-driven AI agents, streamline workflows, & scale intelligent operations with TrueFoundry. - [AI Security Plaforms](https://www.truefoundry.com/blog/ai-security-platforms-and-gateways): Learn how AI Gateways serve as the enforcement engine of AI Security Platforms. Discover why enterprises trust TrueFoundry’s AI Gateway to secure LLMs, agents, and prompts with real-time guardrails, data residency, and governance. - [MCP Registry and AI Gateway](https://www.truefoundry.com/blog/mcp-registry-and-ai-gateway): Explore how MCP Registry and AI Gateway enable secure, scalable AI integrations with centralized discovery, access control, and observability. - [TrueFoundry Raises $19M Series A for Agentic AI](https://www.truefoundry.com/blog/announcing-our-19m-series-a-scaling-ai-deployment-with-autonomous-agents-on-autopilot): Practical guide to announcing our 19m series a scaling ai deployment with autonomous agents on autopilot, with setup steps, architecture… - [Authenticated gRPC Service on Kubernetes | TrueFoundry](https://www.truefoundry.com/blog/authenticated-grpc-service-on-eks-with-istio): Explore how TrueFoundry secures gRPC services on Kubernetes. Discover our solutions for enhancing communication reliability and security with authenticated services. - [Deploying LLMs at Scale | TrueFoundry](https://www.truefoundry.com/blog/deploying-llms-at-scale): Explore how TrueFoundry scales Large Language Model (LLM) deployments efficiently. Discover our solutions for managing LLM deployments at scale. - [Beyond DNS: Why Agents Need a Registry | TrueFoundry Engineering](https://www.truefoundry.com/blog/agent-gateway-series-part-2-of-7-service-registry-for-the-agentic-era): In a multi-agent system, knowing "where" an agent is isn't enough. You need to know "what" it can do. Learn how the Agent Registry enables semantic discovery and topology control. - [Automating GenAI Infrastructure Management with Autopilot](https://www.truefoundry.com/blog/automating-infrastructure-management-for-generative-ai-with-autopilot): In-depth breakdown of automating infrastructure management for generative ai with autopilot, focusing on architecture, benefits, challenges,… - [LLM Agents: The Complete Guide for 2026](https://www.truefoundry.com/blog/llm-agents): Learn what LLM agents are and how they leverage large language models to perform tasks, enhance planning, and manage memory for accurate AI assistance. - [Why AI Gateways Matter Beyond Traditional API Gateways](https://www.truefoundry.com/blog/why-an-ai-gateway-is-essential-beyond-a-standard-api-gateway): In-depth breakdown of why an ai gateway is essential beyond a standard api gateway, focusing on architecture, benefits, challenges, and… - [AI Guardrails in Enterprise: Ensuring Safe Innovation](https://www.truefoundry.com/blog/ai-guardrails-in-enterprise): In-depth breakdown of ai guardrails in enterprise, focusing on architecture, benefits, challenges, and enterprise relevance. - [Top 6 SageMaker Alternatives in 2026](https://www.truefoundry.com/blog/sagemaker-alternatives): Explore AWS SageMaker alternatives for enterprises with TrueFoundry. Built for flexible, scalable AI and LLM workflows with observability and cost control. - [LangGraph vs n8n: Choosing the Right Workflow Framework](https://www.truefoundry.com/blog/langgraph-vs-n8n): Compare n8n and LangGraph for automation and AI workflows. Learn the key differences, strengths, and best use cases to choose the right framework. - [Cost Considerations of Using an AI Gateway | TrueFoundry](https://www.truefoundry.com/blog/cost-considerations-of-using-an-ai-gateway): Learn how AI Gateways help enterprises monitor, control, and optimize LLM costs and how TrueFoundry enables predictable, governed AI spend. - [Kubernetes & MLOps: Challenges & Benefits](https://www.truefoundry.com/blog/kubernetes-machine-learning-introduction): Delve into the advantages and hurdles of incorporating Kubernetes into MLOps workflows. Uncover how Kubernetes boosts scalability and efficiency in ML operations. - [TrueFoundry's Strategy for Global AI/ML Data Residency: Decoupling Control & Data Plane for GDPR & CCPA Compliance](https://www.truefoundry.com/blog/decoupling-control-and-data-truefoundrys-strategy-for-global-ai-ml-data-residency): Learn how TrueFoundry ensures global AI/ML data residency compliance (GDPR, CCPA) by strictly decoupling the Control Plane from your Data Plane. Keep your sensitive model artifacts, training data, and inference logs within your own secure cloud region. - [TrueFoundry's Logging Architecture for AI Gateway](https://www.truefoundry.com/blog/logging-architecture-ai-gateway): How decoupling storage and compute (S3 + Delta Lake) with DataFusion gave us fast, zero-maintenance LLM observability for our AI Gateway that stays inside your cloud. - [Vercel AI Gateway vs OpenRouter](https://www.truefoundry.com/blog/vercel-ai-gateway-vs-openrouter): Compare Vercel AI Gateway and OpenRouter across architecture, deployment scope, and enterprise readiness and see where TrueFoundry fits for production AI. - [Introducing the TrueFoundry MCP Gateway for LLM Apps](https://www.truefoundry.com/blog/introducing-truefoundry-mcp-gateway): In-depth breakdown of introducing truefoundry mcp gateway, focusing on architecture, benefits, challenges, and enterprise relevance. - [Top Agentic AI Platforms in 2026](https://www.truefoundry.com/blog/agentic-ai-platforms): In-depth breakdown of agentic ai platforms, focusing on architecture, benefits, challenges, and enterprise relevance. - [Grok 4.1 Overview: Features, Performance & Use Cases](https://www.truefoundry.com/blog/grok-4-1): In-depth breakdown of grok 4 1, focusing on architecture, benefits, challenges, and enterprise relevance. - [LLM Cost Tracking Solution: Observability, Governance & Optimization](https://www.truefoundry.com/blog/llm-cost-tracking-solution): Implement the LLM cost tracking solution and gain granular observability, control spend, enforce governance, and optimize performance across LLM workloads. - [Coralogix Integration with the TrueFoundry AI Gateway](https://www.truefoundry.com/blog/coralogix-integration-with-truefoundry-ai-gateway): How coralogix integration with truefoundry ai gateway works in production, covering setup, observability, security, and enterprise AI workflows. - [Gartner on AI Gateways: Here’s what Enterprise AI Teams Should Know](https://www.truefoundry.com/blog/gartner-on-ai-gateways-heres-what-enterprise-ai-teams-should-know): Gartner’s latest research reveals how AI Gateways help enterprise teams scale agentic AI with governance, reliability, and cost control. - [Scaling to Zero in Kubernetes with Elasti and KEDA](https://www.truefoundry.com/blog/scaling-to-zero-in-kubernetes-a-deep-dive-into-elasti): In-depth breakdown of scaling to zero in kubernetes a deep dive into elasti, focusing on architecture, benefits, challenges, and enterprise… - [Last9 Integration with the TrueFoundry AI Gateway](https://www.truefoundry.com/blog/truefoundry-ai-gateway-integration-with-last9): How truefoundry ai gateway integration with last9 works in production, covering setup, observability, security, and enterprise AI workflows. - [API Auth & RBAC in AI Gateway – Secure Access Controls](https://www.truefoundry.com/blog/api-auth-rbac-in-gateway): Secure your AI Gateway with TrueFoundry’s API authentication and RBAC: enforce API-key validation, SSO (OIDC/SAML), YAML-based role policies, scoped service accounts, provider‑level access, and full audit trails—designed for enterprise-grade control, multi‑tenancy, and compliance. - [True ML Talks #23 - MLOps & LLMs Applications @ GitLab](https://www.truefoundry.com/blog/llm-and-machine-learning-platform-gitlab): Explore MLOps and LLMs applications at GitLab on True ML Talks #23. Gain insights into ML operations and advancements. - [LLMOps vs MLOps: A Complete Comparison Guide](https://www.truefoundry.com/blog/llmops-vs-mlops): Understand the difference between LLMOps and MLOps: TrueFoundry shows LLMOps adds gateway routing, token-level observability, fallback, and cost tracking on top of standard MLOps practices. - [AI Governance Frameworks 2025: Role of AI Gateways](https://www.truefoundry.com/blog/ai-governance-framework): Learn how AI governance frameworks ensure responsible innovation and how TrueFoundry’s AI Gateway operationalizes governance through unified access, compliance, and observability across all models. - [How to set up Gitops in Kubernetes](https://www.truefoundry.com/blog/setting-up-gitops-using-truefoundry): How to set up Gitops in Kubernetes - [LiteLLM vs TrueFoundry: The Right AI Gateway for Scale](https://www.truefoundry.com/blog/litellm-vs-truefoundry-ai-gateway): Compare LiteLLM and TrueFoundry AI Gateway for developers vs enterprises—routing, integrated playgrounds, observability, audit logs, guardrails, and 24×7 on‑prem support - [A Guide to Cloud Node Auto-Provisioning | TrueFoundry](https://www.truefoundry.com/blog/guide-to-node-auto-provisioning): Learn about Cloud Node Auto-Provisioning to streamline infrastructure. Explore methods for efficient resource allocation. - [TrueFoundry & Cerebras Partnership | Enterprise AI at Scale](https://www.truefoundry.com/blog/truefoundry-and-cerebras-announce-strategic-partnership): Discover how TrueFoundry and Cerebras partner to deliver high-performance, governed, and scalable AI solutions for enterprises worldwide. - [Cost tracking Claude Code with TrueFoundry's AI Gateway](https://www.truefoundry.com/blog/cost-tracking-claude-code-with-truefoundrys-ai-gateway): Learn how to effectively track and manage the costs of using Claude with TrueFoundry's AI Gateway. This guide provides step-by-step instructions to optimize your spending. - [TrueFoundry Recognized as a Hot Tech Vendor by HFS in GenAI for Enterprises](https://www.truefoundry.com/blog/truefoundry-recognized-as-a-hot-tech-vendor-by-hfs-in-genai-for-enterprises): TrueFoundry Recognized as a Hot Tech Vendor by HFS in GenAI for Enterprises - [Leading AI Gateway for LLM Workload Optimization](https://www.truefoundry.com/blog/leading-ai-gateway-for-llm-workload-optimization): Explore how leading AI gateway optimize LLM workloads in 2026 covering cost control, multi-model routing, observability, governance, and enterprise-scale architecture. - [TrueML Talks #29 - GenAI and LLMs for Location Intelligence](https://www.truefoundry.com/blog/genai-and-llms-for-location-intelligence-at-bean-ai): Explore GenAI and LLMs for Location Intelligence at Beans.AI on TrueML Talks #29. Unlock insights for spatial data analysis. - [Applications of GenAI at Google](https://www.truefoundry.com/blog/applications-of-genai-at-google): Dive into True ML's episode featuring Priya Mathur from Google, exploring ML challenges, innovations, generative AI, and trust-building in AI. - [7 Best LLM Observability Tools](https://www.truefoundry.com/blog/llm-observability-tools): Discover the 7 best LLM observability tools to monitor, evaluate, and optimize large language model performance. Compare features, pricing, and use cases. - [Patronus Integration with TrueFoundry's AI Gateway](https://www.truefoundry.com/blog/patronus-integration-with-truefoundrys-ai-gateway): How patronus integration with truefoundrys ai gateway works in production, covering setup, observability, security, and enterprise AI workflows. - [An In-depth Guide to Benchmarking LLMs](https://www.truefoundry.com/blog/benchmarking-llama2-falcon-and-mistral): Explore benchmarking insights for popular opensource LLMs: Llama2, Falcon, and Mistral. Enhance ML performance - [7 Best Vector Databases in 2025](https://www.truefoundry.com/blog/best-vector-databases): In this blog post, we will delve into the technical and enterprise considerations that will guide you in selecting the right vector database for your needs. - [Future of LLMs and WebRTC: A Deep Dive](https://www.truefoundry.com/blog/future-of-llms-and-webrtc-a-deep-dive): Future of LLMs and WebRTC: A Deep Dive - [Enterprise-Grade Prompt Evaluation for LLMs | TrueFoundry & Promptfoo](https://www.truefoundry.com/blog/enterprise-ready-prompt-evaluation-how-truefoundry-and-promptfoo-enable-confident-ai-at-scale): Learn how TrueFoundry and Promptfoo enable enterprise-grade prompt evaluation, governance, and reliability for production LLM applications through the AI Gateway. - [GenAI Showcase For Enterprises](https://www.truefoundry.com/blog/webinar-genai-showcase-for-enterprises): GenAI Showcase For Enterprises - [What Is LLM Proxy?](https://www.truefoundry.com/blog/llm-proxy): Learn what an LLM proxy is, how it simplifies model access, improves security, and supports scalability for enterprises using multiple LLMs. - [Langfuse vs Portkey – Key Differences & Features](https://www.truefoundry.com/blog/langfuse-vs-portkey): Compare Langfuse vs Portkey: features, architecture, trade-offs, and best use cases for LLM observability, routing, and scaling AI apps. - [Big Data and ML Practices at Palo Alto Networks](https://www.truefoundry.com/blog/big-data-and-ml-practices-at-palo-alto-networks): Big Data and ML Practices at Palo Alto Networks - [AI Gateway vs API Gateway: Know The Difference](https://www.truefoundry.com/blog/ai-gateway-vs-api-gateway): Learn how an API Gateway differs from an AI Gateway. Compare features, use cases, and benefits to understand which solution fits your architecture. - [Load Balancing in AI Gateway: Optimizing Performance](https://www.truefoundry.com/blog/load-balancing-in-ai-gateway): Discover how TrueFoundry’s AI Gateway offers weight‑based and latency‑based load balancing across multiple LLM endpoints—ensuring high availability, consistent latency, error resilience, and seamless canary rollouts via simple YAML configuration. - [Pangea Integration with TrueFoundry's AI Gateway](https://www.truefoundry.com/blog/pangea-integration-with-truefoundrys-ai-gateway): How pangea integration with truefoundrys ai gateway works in production, covering setup, observability, security, and enterprise AI workflows. - [EU AI Act Compliance Using Enterprise AI Gateways](https://www.truefoundry.com/blog/eu-ai-data-act): Learn how enterprise AI teams can meet EU AI Act requirements using an AI control plane and full-lifecycle governance. A practical compliance guide for enterprises. - [Prompt Management Tools for Production AI Systems](https://www.truefoundry.com/blog/prompt-management-tools): Learn what prompt management tools are, why teams need them in production, and how prompts integrate with AI gateways, agents, and observability. - [Build Vs Buy](https://www.truefoundry.com/blog/build-vs-buy): Build Vs Buy - [What Are Compound AI Systems?](https://www.truefoundry.com/blog/compound-ai-systems): Unpack compound AI systems with TrueFoundry: orchestrating multiple LLMs and tools in pipelines, with gateway-managed routing, observability, and fallback for reliable, multimodal workflows. - [LLM in Enterprise: A Complete Guide](https://www.truefoundry.com/blog/enterprise-in-llm): Explore how enterprise LLMs are transforming business operations in 2026. Learn key use cases, challenges, platforms, and how to deploy LLMs securely at scale. - [LLM-powered QA Chatbot on Your Cloud Data | TrueFoundry](https://www.truefoundry.com/blog/qa-chatbot-on-your-data-in-your-cloud-using-llms): Discover how TrueFoundry enables LLM-powered QA chatbots on your cloud data for efficient QA. Explore our solutions for enhancing QA processes and productivity. - [Breaking Down AI Gateway Usage: Customer and User-Level Analytics](https://www.truefoundry.com/blog/breaking-down-llm-usage-customer-and-user-level-analytics): Discover how TrueFoundry monitors large language model (LLM) usage and manages costs effectively. Learn about tracking tools, cost optimization strategies, and insights for enterprise-scale AI deployments. - [Build Low-Code AI Agent Flows Using Flowise & TrueFoundry](https://www.truefoundry.com/blog/building-low-code-ai-agent-flows-with-flowise-on-the-truefoundry-ai-gateway): In-depth breakdown of building low code ai agent flows with flowise on the truefoundry ai gateway, focusing on architecture, benefits,… - [Prompt Engineering Guide | Interacting with LLMs](https://www.truefoundry.com/blog/prompt-engineering-learning-to-interact-with-llms): Discover the art of prompt engineering and learn how to interact with Large Language Models (LLMs) effectively with TrueFoundry's guidance. - [What is Bottlerocket and how to use it in EKS? | TrueFoundry](https://www.truefoundry.com/blog/bottlerocket-in-eks): Learn about Bottlerocket and its usage in Amazon EKS (Elastic Kubernetes Service) with TrueFoundry's comprehensive guide. - [Large Language Models for Commercial Use | TrueFoundry](https://www.truefoundry.com/blog/all-about-license-for-llm-models): This blog post resolves doubts about the licensing of LLM models to avoid legal troubles when using, modifying, or sharing them. - [Kimi-K2 Thinking: Try It via Truefoundry 's AI Gateway](https://www.truefoundry.com/blog/kimi-k2-thinking-with-truefoundry-ai-gateway): Kimi-K2 leads agentic benchmarks with multi-step reasoning and tool orchestration. Spin it up fast using Truefoundry AI Gateway. - [MCP Access Control: Securing AI Agents with an MCP Gateway](https://www.truefoundry.com/blog/mcp-access-control): Learn how MCP access control secures AI agents by controlling model, tool, and server access using an enterprise AI Gateway - [Top 5 Azure ML Alternatives of 2025](https://www.truefoundry.com/blog/azure-ml-alternatives): Discover the best alternatives to Azure ML. Explore powerful, cost-effective machine learning platforms at TrueFoundry. - [MCP vs API: Key Differences and Future of AI Integration](https://www.truefoundry.com/blog/mcp-vs-api): Explore MCP vs API differences, use cases, and future trends for AI workflows. Learn how each enables secure, scalable, and intelligent system integration. - [TrueFoundry and the Rise of MCP Gateways in Enterprise AI](https://www.truefoundry.com/blog/truefoundry-and-the-mcp-gateway-revolution-insights-from-gartners-2025-report): Discover why MCP Gateways are critical for enterprise AI governance and how TrueFoundry enables secure, scalable, and compliant AI integration. - [Top Agent Gateways 2025](https://www.truefoundry.com/blog/top-agent-gateways): Explore the top Agent Gateways of 2025 and how they compare across observability, security, cost control, and multi-agent orchestration | TrueFoundry - [Observability in LLM Workflows: Metrics, Traces & Logs](https://www.truefoundry.com/blog/observability-in-llm-workflows): Explore how TrueFoundry brings full observability to LLM workflows with real-time metrics, end-to-end tracing, token-level cost tracking, and flexible integrations—turning black‑box AI pipelines into transparent, scalable, and auditable systems ready for enterprise use. - [What is LangChain? | Truefoundry](https://www.truefoundry.com/blog/langchain): Discover LangChain's role in simplifying AI development with LLMs, enabling chatbots, summarizers, and API interactions efficiently. - [How to Self Host n8n on Your Infrastructure with TrueFoundry](https://www.truefoundry.com/blog/self-host-n8n): A step by step guide to easily deploy and self host the open-source workflow automation tool, n8n, on your own Kubernetes cluster using the TrueFoundry platform. - [AI Agent Marketplaces](https://www.truefoundry.com/blog/ai-agent-marketplaces): Explore how AI agent marketplaces are reshaping enterprise automation. Learn about their architecture, use cases, monetization models, and how platforms like TrueFoundry enable secure, scalable deployment of intelligent agents. - [What Is AI Governance? Definition, Meaning & Key Principles](https://www.truefoundry.com/blog/what-is-ai-governance): Learn what AI governance is, its meaning, definition, and key principles for managing AI risks, ensuring accountability, transparency, and responsible use. - [Crewai vs LangGraph: Know The Differences](https://www.truefoundry.com/blog/crewai-vs-langgraph): Side-by-side comparison of crewai vs langgraph, covering features, architecture differences, trade-offs, and best use cases. - [Learn how AI gateways enforce data sovereignty and data residency at runtime across models, agents, and observability in enterprise AI systems.](https://www.truefoundry.com/blog/data-sovereignty-vs-data-residency): Learn how AI gateways enforce data sovereignty and data residency at runtime across models, agents, and observability in enterprise AI systems. - [Detailed Guide to What is an AI Gateway?](https://www.truefoundry.com/blog/ai-gateway): Learn what an AI gateway is and how it centralizes LLM routing, security, and costs. This guide explores the core concepts for scaling AI production. - [AI Agent Observability: Monitoring and Debugging Agent Workflows](https://www.truefoundry.com/blog/ai-agent-observability-tools): Learn how AI agent observability helps teams trace reasoning steps, tool calls, and costs to debug and operate autonomous agents in production. - [What Is Generative AI Gateway?](https://www.truefoundry.com/blog/generative-ai-gateway): Leverage the Generative AI Gateway to unify model access, accelerate innovation, and streamline AI-driven workflows across your business. - [What is MCP Server Authentication?](https://www.truefoundry.com/blog/mcp-server-authentication): In-depth breakdown of mcp server authentication, focusing on architecture, benefits, challenges, and enterprise relevance. - [How to Choose an AI Gateway](https://www.truefoundry.com/blog/how-to-choose-an-ai-gateway): Choosing the right AI Gateway is critical to scaling LLM applications securely and efficiently. Learn how to evaluate AI Gateways, what features matter, and how TrueFoundry simplifies enterprise-grade orchestration, governance, and cost control - [Multi-Agent Systems: Architecture, Benefits & Uses](https://www.truefoundry.com/blog/multi-agent-systems-mas): Explore how Multi-Agent Systems (MAS) enable intelligent, collaborative AI solutions. Learn their architecture, benefits, and how TrueFoundry powers scalable MAS deployments for real-world enterprise use cases. - [How to Detect Shadow AI in Enterprise | TrueFoundry](https://www.truefoundry.com/blog/how-to-detect-shadow-ai-and-turn-risk-into-enterprise-advantage): Discover 4 practical ways to detect Shadow AI risks—from expense audits to OAuth logs. Learn how TrueFoundry turns unmanaged AI into a secure enterprise advantage. - [Dedicated Prompt Management for Production AI | TrueFoundry](https://www.truefoundry.com/blog/why-production-ai-needs-dedicated-prompt-management): Stop treating LLM prompts as "magic strings." Learn why production-grade Generative AI systems require a dedicated Prompt Management System to manage versioning, collaboration, and deployment, and how TrueFoundry provides the essential infrastructure to scale your AI applications with engineering discipline. - [What is LLM Router?](https://www.truefoundry.com/blog/what-is-llm-router): Discover how an LLM Router optimizes AI workflows by automatically routing requests to the best large language model based on cost, performance, and context. - [The Policy Engine: Securing the Agentic Enterprise | TrueFoundry Engineering](https://www.truefoundry.com/blog/agent-gateway-series-part-5-of-7-the-policy-engine-of-ai-agent-gateway): In agentic systems, RBAC is not enough. You must secure your Intent. Learn how the Policy Engine uses Context Propagation and Graph Topology to prevent privilege escalation. - [What is Similarity Search & How Does it work? | TrueFoundry](https://www.truefoundry.com/blog/similarity-search): Explore how similarity search transforms data retrieval in e-commerce, NLP, and more. Learn key techniques and boost your system's efficiency. Read now! - [Cline with TrueFoundry AI Gateway: Setup Guide for VS Code](https://www.truefoundry.com/blog/cline-integration-with-truefoundry-ai-gateway): Learn how to connect Cline to TrueFoundry AI Gateway in VS Code. Step by step setup with budgets rate limits and logs so teams can code faster with control. - [TrueML Talks #25 - GenAI and LLMOps for GTM @ Twilio](https://www.truefoundry.com/blog/genai-and-llmops-for-gtm-twiilio): Discover GenAI and LLMOps strategies for GTM at Twilio on TrueML Talks #25. Explore ML applications for market expansion. - [TrueML Talks #26: Enterprise GenAI & LLMOps](https://www.truefoundry.com/blog/enterprise-genai-and-llmops): Join TrueML Talks #26 for insights on Enterprise GenAI and LLMOps with Labhesh Patel. Explore ML strategies for enterprises. - [What Is Prompt Engineering ?](https://www.truefoundry.com/blog/prompt-engineering): Master prompt engineering for LLMs with TrueFoundry. Learn effective techniques to craft prompts, fine-tune models, and enhance QA processes with state-of-the-art methods. - [Cost Comparison with Sagemaker](https://www.truefoundry.com/blog/cost-comparison-with-sagemaker): Cost Comparison with Sagemaker - [Leveraging AI/ML for Revolutionary Logistics at Sennder](https://www.truefoundry.com/blog/leveraging-ai-ml-for-revolutionary-logistics-at-sennder): Leveraging AI/ML for Revolutionary Logistics at Sennder - [SageMaker vs TrueFoundry: A Detailed Comparison](https://www.truefoundry.com/blog/sagemaker-vs-truefoundry): Explore the differences between Sagemaker and TrueFoundry, two prominent AI gateways, to make an informed decision for your business needs. - [Enterprise AI Interoperability with AI Gateways](https://www.truefoundry.com/blog/ai-interoperability): Learn how AI interoperability helps enterprises connect diverse models, agents, and tools seamlessly. Discover how TrueFoundry’s AI Gateway unifies APIs, enforces governance, and powers scalable, vendor-agnostic AI systems. - [LiteLLM vs OpenRouter: Which is Best For You?](https://www.truefoundry.com/blog/litellm-vs-openrouter): Learn how LiteLLM vs OpenRouter compares across features, architecture differences, trade-offs, and real-world use cases. - [TrueML #22 - ML Platform & LLMs @ Voiceflow](https://www.truefoundry.com/blog/llm-and-machine-learning-platform-voiceflow): Explore machine learning platform and LLMs at Voiceflow on TrueML #22. Join discussions on ML advancements and applications. - [Top 5 Helicone Alternatives](https://www.truefoundry.com/blog/helicone-alternatives): Detailed comparison of helicone alternatives, including strengths, limitations, and when to choose each for enterprise AI. - [LangChain vs LangGraph: Compare Features & Use Cases](https://www.truefoundry.com/blog/langchain-vs-langgraph): Explore the differences between LangChain vs LangGraph, their core features, workflows, and real-world use cases to choose the right framework for your AI projects. - [TrueFoundry: 2025 year-end review](https://www.truefoundry.com/blog/truefoundry-2025-year-end-review): - [What is AI Compliance? Definition and Important Standards](https://www.truefoundry.com/blog/what-is-ai-compliance): Master AI compliance with our guide on regulatory standards. Learn how AI Gateways automate data security and fairness for responsible innovation - [How should Enterprises evaluate LLM Gateway for Scale?](https://www.truefoundry.com/blog/how-should-enterprises-evaluate-llm-gateway-for-scale): Learn how enterprises can effectively evaluate LLM Gateways to ensure scalability, performance, and security in large language model deployments. Discover key factors for making informed decisions. - [Architecting the Agent Gateway: Unifying the Agentic Stack | TrueFoundry](https://www.truefoundry.com/blog/agent-gateway-series-part-1-of-7-truefoundry-agent-gateway): Moving from stateless LLM inference to stateful agentic workflows requires a new infrastructure layer. We introduce the 7 pillars of the Agent Gateway and explore Session Management and Identity. - [LLM Access Control: Securing Models, Agents, and AI Workloads](https://www.truefoundry.com/blog/llm-access-control): Learn what LLM access control means in production and how teams secure models, agents, and tools using gateway-based, policy-driven enforcement. - [Palo Alto Prisma AIRS Integration with TrueFoundry AI Gateway](https://www.truefoundry.com/blog/palo-alto-prisma-integration-with-truefoundry-ai-gateway): Secure every AI request with Prisma AIRS via TrueFoundry AI Gateway. Block prompt injection, prevent data leaks, add guardrails, and scale safely across models. - [TrueFoundry Architecture: Machine Learning on Kubernetes | TrueFoundry](https://www.truefoundry.com/blog/truefoundry-ml-platform-on-kubernetes): Dive into the architecture of TrueFoundry's Machine Learning on Kubernetes platform. Learn how our platform enables scalable MLOps workflows. - [Scaling Up Serving of Fine-tuned LoRA Models | TrueFoundry](https://www.truefoundry.com/blog/scaling-up-serving-of-fine-tuned-lora-models): Discover how TrueFoundry scales serving of fine-tuned models for performance. Explore solutions for managing model serving infrastructure. - [Top 5 Portkey Alternatives in 2026](https://www.truefoundry.com/blog/portkey-alternatives): Explore Portkey alternatives for enterprise LLM gateways. Compare policy-based routing, RBAC, auditing, cost tracking, and multi-model orchestration features. - [Top 8 Machine Learning Model Deployment Tools in 2026](https://www.truefoundry.com/blog/model-deployment-tools): Explore the top 8 machine learning model deployment tools in 2026. Learn about their features, benefits, and how to choose the best one for your ML needs. - [Semantic Caching for Large Language Models | TrueFoundry](https://www.truefoundry.com/blog/semantic-caching): Learn how semantic caching for large language models reduces inference cost and latency by reusing responses based on meaning, not exact prompts. - [TrueFoundry Announces SOC2 Type 2 and HIPPA Compliance](https://www.truefoundry.com/blog/truefoundry-announces-soc2-type-2-and-hippa-compliance): TrueFoundry Announces SOC2 Type 2 and HIPPA Compliance - [Braintrust Integration with TrueFoundry for LLM Eval](https://www.truefoundry.com/blog/truefoundry-integration-with-braintrust): How truefoundry integration with braintrust works in production, covering setup, observability, security, and enterprise AI workflows. - [Llama-2-13B Benchmarking: Performance Analysis](https://www.truefoundry.com/blog/benchmarking-llama-2-13b): Discover performance analysis for Llama-2-13B benchmarking. Unlock insights to enhance ML efficiency. - [Demystifying Transformer Architecture in Large Language Models](https://www.truefoundry.com/blog/transformer-architecture): Discover the inner workings of Transformer Architecture in Large Language Models (LLMs) and how it revolutionizes natural language processing tasks. - [LLMOps Guide: Streamline Your Machine Learning Operations](https://www.truefoundry.com/blog/llmops-mastering-the-art-of-managing-large-language-models-challenges-best-practices-and-future-trends): Discover how LLMOps revolutionizes machine learning operations with streamlined processes and enhanced efficiency. Learn more in detail on this article. - [Kong vs Portkey: Which AI Gateway Works for Enterprise LLM Infrastructure?](https://www.truefoundry.com/blog/kong-vs-portkey): Compare Kong vs Portkey for LLM workloads and enterprise AI. Learn where API and LLM gateways fall short, and how enterprises scale AI with TrueFoundry. - [TrueFoundry announces GDPR Compliance](https://www.truefoundry.com/blog/truefoundry-announces-gdpr-compliance): - [LLM Capability Explorer | TrueFoundry](https://www.truefoundry.com/blog/compare-llm-capabilities): Explore and test AI language models through TrueFoundry AI Gateway - [AI model gateways vendor lock-in prevention](https://www.truefoundry.com/blog/vendor-lock-in-prevention): Learn how AI model gateways prevent vendor lock-in by enabling interoperability, flexibility, and portability across model providers with TrueFoundry. - [Gemini 3 Explained: Capabilities, Use Cases & Benchmarks](https://www.truefoundry.com/blog/gemini-3): In-depth breakdown of gemini 3, focusing on architecture, benefits, challenges, and enterprise relevance. - [Agent DevOps: CI/CD, Evals, and Canary Deployments | TrueFoundry Engineering](https://www.truefoundry.com/blog/agent-gateway-series-part-7-of-7-agent-devops-ci-cd-evals-and-canary-deployments): You cannot kubectl apply an agent like a microservice. Prompts are fragile. Learn how to implement "Shadow Mode," Automated Evals, and Canary Rollouts to deploy AI safely. - [Nexos AI vs TrueFoundry: Features & Performance Comparison](https://www.truefoundry.com/blog/nexos-ai-vs-truefoundry-features-performance-comparison): Compare Nexos AI and TrueFoundry across features, performance, deployment, and pricing to choose the right enterprise AI gateway for your AI/ML workflows. - [What is MCP Proxy?](https://www.truefoundry.com/blog/what-is-mcp-proxy): An MCP Proxy manages and routes requests across multi-agent systems, enabling AI orchestration, monitoring, and secure workflows. Learn how it works. - [TrueFoundry: 2024 year-end review](https://www.truefoundry.com/blog/truefoundry-2024-year-end-review): TrueFoundry: 2024 year-end review - [Top 5 AWS MCP Gateway Alternatives](https://www.truefoundry.com/blog/aws-mcp-gateway-alternatives): Detailed comparison of aws mcp gateway alternatives, including strengths, limitations, and when to choose each for enterprise AI. - [TrueFoundry AI Gateway and LangSmith: Building Observable, Evaluated AI Systems](https://www.truefoundry.com/blog/truefoundry-ai-gateway-integration-with-langsmith): Learn how TrueFoundry’s AI Gateway integrates with LangSmith to enable LLM observability, OpenTelemetry tracing, continuous evals, and secure VPC deployments for production AI systems. - [Truefoundry AI Agent Gateway: Unifying the Agentic Stack](https://www.truefoundry.com/blog/unifying-the-agentic-stack-the-gateway-that-makes-multi-agent-systems-truly-work): Secure and scale multi-agent systems. Truefoundry’s Gateway manages MCP, A2A, and tool interactions with enterprise-grade security and observability - [5 Best AI Gateways in 2026 (For Enterprises)](https://www.truefoundry.com/blog/best-ai-gateway): Explore the best AI gateways that streamline LLM access, boost performance, ensure security, and enable monitoring for enterprise-scale AI applications. - [MCP Server Security Best Practices for Safe AI Deployments](https://www.truefoundry.com/blog/mcp-server-security-best-practices): Learn MCP server security best practices to protect AI systems with authentication, encryption, RBAC, and monitoring. Secure deployments and prevent data breaches. - [AI Model Deployment](https://www.truefoundry.com/blog/what-is-ai-model-deployment): Discover what AI model deployment means, how it works, and why it’s critical for scaling machine learning. Learn the process, challenges, and best practices for deploying AI models in production. - [LLM Gateway On-Premise Infrastructure](https://www.truefoundry.com/blog/llm-gateway-on-premise-infrastructure): Understand LLM gateway on-premise infrastructure, including architecture, deployment models, governance, and best practices for secure enterprise AI deployments. - [True ML Talks #16 - ML Pipeline @ Digits](https://www.truefoundry.com/blog/machine-learning-platform-digits): Explore machine learning pipelines at Digits on True ML Talks #16. Join discussions on ML operations and advancements. - [Machine Learning Deployments in 2023 | TrueFoundry](https://www.truefoundry.com/blog/ml-deployment-platform-2023): Delve into advanced insights and forecasts for ML deployments in 2023 by TrueFoundry. Stay ahead with our analysis of the evolving MLOps landscape. - [What is an Agent Gateway?](https://www.truefoundry.com/blog/agent-gateway): Learn what is an Agent Gateway, how it secures and scales AI agents. Explore the benefits of agentic gateways for enterprise-grade machine learning workflows. - [On-Premise LLM Deployment: Secure & Scalable AI Solutions](https://www.truefoundry.com/blog/on-prem-llms): Explore on-premise LLM deployment for secure, scalable AI. Learn benefits, tools, architecture, and best practices to maintain data control and high performance. - [What is Lora Fine Tuning? The Definitive Guide](https://www.truefoundry.com/blog/lora-fine-tuning): Learn how to fine-tune LoRA models for better performance. Explore techniques and strategies to optimize model accuracy and efficiency. - [What are AI Guardrails?](https://www.truefoundry.com/blog/ai-guardrails): Learn how AI Guardrails in TrueFoundry’s AI Gateway ensure LLM safety, compliance, and governance through centralized, configurable enterprise controls. - [Hosting Predictions with Kubernetes | TrueFoundry](https://www.truefoundry.com/blog/kubernetes-for-data-scientists-hosting-predictions): Explore how TrueFoundry leverages Kubernetes for scalable predictions. Discover seamless MLOps solutions for model deployment. - [TrueFoundry Deploys & Fine-tunes Open Source LLMs in Few Clicks](https://www.truefoundry.com/blog/truefoundry-deploy-fine-tune-open-source-llms): Discover how TrueFoundry simplifies deployment and tuning of Large Language Models with a few clicks. Explore our solutions for accelerating LLM adoption. - [Virtual MCP Server Explained: Aggregating Tools Across MCP Servers](https://www.truefoundry.com/blog/virtual-mcp-server): Learn what a Virtual MCP Server is, how it aggregates tools across multiple MCP servers, and why teams use it to simplify AI agent architectures at scale. - [25 Best MLOps Tools for Building & Scaling ML Workflows](https://www.truefoundry.com/blog/mlops-tools): Discover the best MLOps tools to build, deploy, and scale machine learning workflows. Compare features to choose the right platform for your ML projects. - [Rate Limiting in AI Gateway : The Ultimate Guide](https://www.truefoundry.com/blog/rate-limiting-in-llm-gateway): Learn how rate limiting in LLM Gateway works using request and token quotas, YAML policies, and fallback routing to maintain reliability and control AI costs. - [The A2A Protocol: Standardizing Agent Communication | TrueFoundry Engineering](https://www.truefoundry.com/blog/agent-gateway-series-part-3-of-7-truefoundry-powered-a2a-standardizing-the-internal-monologue): Agents built on different frameworks (LangChain, AutoGen, CrewAI) cannot naturally collaborate. Learn how the A2A Protocol creates a universal envelope for identity, tracing, and context propagation. - [Model Context Protocol (MCP): Architecture & Internals](https://www.truefoundry.com/blog/inside-the-model-context-protocol-mcp-architecture-motivation-internal-usage): In-depth breakdown of inside the model context protocol mcp architecture motivation internal usage, focusing on architecture, benefits,… - [Best Fine Tuning Tools For Precision & Efficiency](https://www.truefoundry.com/blog/top-tools-for-fine-tuning): Explore the best fine tuning tools to train, optimize, and deploy ML and LLM models efficiently. Compare features, benefits, and use cases. - [FinOps for Autonomous Systems: The A2A Economy | TrueFoundry Engineering](https://www.truefoundry.com/blog/agent-gateway-series-part-4-of-7-finops-for-autonomous-systems): Agents spend money with every thought. Without a "Central Bank," your multi-agent system is a financial risk. Learn how to implement budgets, circuit breakers, and chargebacks for AI. - [The Infrastructure for Winning Enterprise AI in 2026 with Truefoundry's MCP Gateway](https://www.truefoundry.com/blog/truefoundry-mcp-gateway-critical-infrastructure-for-productive-and-secure-enterprise-ai-in-2026): Stop 'context stuffing' your LLMs. Discover how Truefoundry's MCP Gateway delivers 99% token savings, N×M integration control, and vital OAuth 2.0 security for your agentic enterprise. - [TrueFoundry 2023 Year-End Review](https://www.truefoundry.com/blog/truefoundry-2023-year-end-review): Reflect on TrueFoundry's achievements and milestones in our 2023 year-end review. Explore the progress we've made and our vision for the future of MLOps. - [Total Cost Of Ownership](https://www.truefoundry.com/blog/understanding-total-cost-of-ownership-for-genai-infrastructure): Total Cost Of Ownership - [Secure Enterprise AI with MCP Gateway, AI Gateway & Guardrails](https://www.truefoundry.com/blog/enterprise-ai-security-with-mcp-gateway-runtime-guardrails): Learn how an AI Gateway and an MCP Gateway stop prompt injection, prevent data leakage, add RBAC/observability, and enforce runtime guardrails—practical patterns and checklists for secure enterprise AI. - [How Enterprises Scale AI: Tesseract Talks With Abhishek Chaudhary](https://www.truefoundry.com/blog/the-hidden-infrastructure-powering-scalable-enterprise-ai-tesseract-talks-with-abhishek-choudhary): Learn why AI gateways are becoming core enterprise infrastructure and how to scale AI with reliability, governance, and cost control, from Tesseract Talks with TrueFoundry’s CTO Abhishek Chaudhary - [Accelerating Time to Value for GenAI: Solutions for Enterprise](https://www.truefoundry.com/blog/helping-enterprises-accelerate-the-time-to-value-for-genai): Discover how our solutions empower enterprises to expedite the time to value for GenAI, enhancing operational efficiency and driving business growth. - [Geopatriation Explained: AI Data Sovereignty Guide](https://www.truefoundry.com/blog/geopatriation): Discover how geopatriation is redefining cloud and AI strategy. Learn why data residency and sovereignty are critical in the era of Agentic AI, and how TrueFoundry’s AI Gateway enables secure, region-aware, and compliant AI infrastructure at global scale. - [What is MCP Registry? Architecture, Benefits & Setup Guide](https://www.truefoundry.com/blog/what-is-mcp-registry): Learn what the MCP Registry is, its architecture, verification methods, and how to manage private registries in this detailed blog. - [On-Premises Generative AI Solutions | Secure & Scalable AI Deployment](https://www.truefoundry.com/blog/on-premises-generative-ai): Explore building on‑prem generative AI with TrueFoundry: deploy models securely behind corporate firewalls, with full gateway support—load balancing, lineage, authentication, and hybrid-cloud scaling. - [GPT-5.1 vs GPT-5: 9 Major Improvements You Need to Know](https://www.truefoundry.com/blog/gpt-5-1-analysis): Discover everything new in GPT-5.1 — improved reasoning, personalization, multimodal intelligence, code upgrades, and real prompt examples. Compare GPT-5.1 vs GPT-5. - [What Is MCP Hub?](https://www.truefoundry.com/blog/what-is-mcp-hub): Learn what MCP hub is, including its architecture, key concepts, real-world use cases, and how it enables scalable AI agent workflows. - [FinOps for AI](https://www.truefoundry.com/blog/finops-for-ai): Learn how FinOps practices can control cloud and LLM costs for AI teams. Explore how TrueFoundry enables token tracking, GPU optimization, and usage governance to help enterprises scale AI sustainably. - [Deploying Falcon-40B model on Amazon SageMaker](https://www.truefoundry.com/blog/deploy-falcon-40b-on-aws): Learn to deploy Falcon-40B language model on AWS cloud using LLMOps, compare costs on Sagemaker vs. TrueFoundry's EKS, and optimize performance. - [10 Best LLMOps Tools in 2026](https://www.truefoundry.com/blog/llmops-tools): Discover the LLMOps tools ecosystem: how TrueFoundry empowers you with observability dashboards, cost analytics, gateway controls, and integrations across deployment and monitoring stacks. - [Top 5 Envoy Proxy Alternatives](https://www.truefoundry.com/blog/envoy-proxy-alternatives): Detailed comparison of envoy proxy alternatives, including strengths, limitations, and when to choose each for enterprise AI. - [LLamaIndex vs LangGraph: Comparing LLM Frameworks](https://www.truefoundry.com/blog/llamaindex-vs-langgraph): Discover the key differences between LLamaIndex and LangGraph. Learn which framework fits best for RAG, workflows, and building production-ready AI apps. - [Why the TrueFoundry LLM Gateway Is Blazing Fast](https://www.truefoundry.com/blog/truefoundry-llm-gateway-is-blazing-fast): In-depth breakdown of truefoundry llm gateway is blazing fast, focusing on architecture, benefits, challenges, and enterprise relevance. - [The Black Box Recorder: Observability for the Agentic Era | TrueFoundry Engineering](https://www.truefoundry.com/blog/agent-gateway-series-part-6-of-7-observability-for-non-deterministic-systems): Debugging code is hard; debugging thoughts is harder. Learn how the Agent Gateway's "Black Box Recorder" captures immutable cognitive traces, ensuring compliance and explainability for autonomous systems. - [GenAI and LLMOps for Customer Success @ Level AI](https://www.truefoundry.com/blog/genai-llmops-for-customer-success-at-level-ai): Learn how Level AI leverage GenAI and LLMOps to solve Customer Success and Quality Assurance from Abhimanyu, Staff AI Research Engineer @ Level AI - [Turning AI Chaos into Control: A Conversation on Agentic AI with Tesseract Talks](https://www.truefoundry.com/blog/turning-ai-chaos-into-control-a-conversation-on-agentic-ai-with-tesseract-talks): As enterprises move from experimenting with large language models to deploying agentic AI systems in production, a new set of challenges is emerging. Teams are moving faster than ever, but often in different directions. Models, tools, frameworks, and agents are multiplying, and with that growth comes fragmentation. - [TrueFoundry becomes the 1st AI Gateway to announce ITAR Compliance](https://www.truefoundry.com/blog/truefoundry-announces-itar-compliance): - [Top 5 Kong AI Alternatives in 2026](https://www.truefoundry.com/blog/kong-ai-alternatives): Explore the top Kong gateway alternatives for 2026. Discover why TrueFoundry is the leading alternative to Kong for scalable AI and api lifecycle management. - [Identity is the New Perimeter: Securing Agentic AI via MCP Gateway](https://www.truefoundry.com/blog/truefoundry-mcp-gateway-identity-control-for-agentic-security): The Agentic Era shifts security from network and application to intent. Learn how the Truefoundry MCP Gateway enforces Zero Trust architecture by eliminating the 'Superuser' trap with user-level identity injection, centralized tool governance, and comprehensive audit logging for autonomous agents. - [RAG in Production - A Technical Deep Dive](https://www.truefoundry.com/blog/rag-in-production---a-technical-deep-dive): RAG in Production - A Technical Deep Dive - [Claude Code Limits: Quotas & Rate Limits Guide](https://www.truefoundry.com/blog/claude-code-limits-explained): Learn how Anthropic’s Claude Code rate limits work, from rolling windows to weekly caps and discover how TrueFoundry’s AI Gateway helps teams manage compute, optimize workflows, and ensure scalable, vendor-agnostic AI development. - [What is LLM Observability ? Complete Guide](https://www.truefoundry.com/blog/what-is-llm-observability): LLM observability is the end-to-end practice of instrumenting, collecting, and analyzing every inference event in a language model pipeline. It combines two core layers - [Benchmarking Llama-2-70B | TrueFoundry](https://www.truefoundry.com/blog/benchmarking-llama-2-70b): Gain efficiency insights from Llama-2-70B benchmarking. Optimize ML operations with valuable data analysis. - [3–15× Faster Docker Image Builds on Kubernetes with TF](https://www.truefoundry.com/blog/enabling-3-15x-faster-docker-image-builds-with-truefoundry-on-kubernetes): In-depth breakdown of enabling 3 15x faster docker image builds with truefoundry on kubernetes, focusing on architecture, benefits, challenges,… - [Best Prompt Engineering Tools in 2026 for AI Workflows](https://www.truefoundry.com/blog/prompt-engineering-tools): Discover the top prompt engineering tools for 2026 to optimize AI outputs, manage workflows, and enhance productivity for developers and teams. - [TrueFoundry Company Retreat 2022](https://www.truefoundry.com/blog/truefoundry-company-retreat-1-0): Join us as we reflect on the TrueFoundry Company Retreat 2022, a gathering aimed at fostering innovation and collaboration. - [Iris Flower Model with TrueFoundry](https://www.truefoundry.com/blog/with-truefoundry-deploying-a-machine-learning-model-has-never-been-easier): Learn to train and deploy an Iris flower classification model seamlessly with TrueFoundry. Explore our intuitive MLOps platform to optimize your ML projects. - [True ML Talks #10 - LLMs & GenAI @ Meta with Engineering Director](https://www.truefoundry.com/blog/innovating-with-llms-and-generative-ai-meta): Join True ML Talks #10 for discussions on LLMs and GenAI with Meta's Engineering Director. Gain insights into ML advancements. - [Accelerate Data Processing 30–40× with NVIDIA RAPIDS on TrueFoundry](https://www.truefoundry.com/blog/accelerate-data-processing-30-40x-with-nvidia-rapids-on-truefoundry): See how TrueFoundry + NVIDIA RAPIDS turbo-charges pandas & Spark jobs, cutting ETL runtimes by 30-40× with GPUs—benchmarks + quick-start guide inside. - [TrueFoundry 2022 Year-End Review](https://www.truefoundry.com/blog/truefoundry-2022-year-end-review): Reflect on TrueFoundry's achievements and milestones in our 2022 year-end review. Explore the progress we've made and our vision for the future of MLOps. - [Enabling the Large Language Models Revolution: GPUs on Kubernetes](https://www.truefoundry.com/blog/using-gpus-with-kubernetes): Explore how TrueFoundry powers the Large Language Models revolution with GPU-accelerated infrastructure on Kubernetes, optimizing LLM performance. - [True ML Talks #20 - Transformers, Embeddings & LLMs @ Turnitin](https://www.truefoundry.com/blog/transformers-embeddings-llms-turnitin): Discover insights into Transformers, Embeddings, and LLMs with an ML Scientist at Turnitin on True ML Talks #20. - [True ML Talks #7 - ML Platform @ Edge](https://www.truefoundry.com/blog/machine-learning-platform-edge): Discover insights into the machine learning platform at Edge on True ML Talks #7. Join discussions on ML advancements. - [5 Principles to Reduce your ML Cloud Costs](https://www.truefoundry.com/blog/reduce-your-machine-learning-cloud-cost): Learn how AI workloads affect cloud costs and discover strategies to optimize expenses with TrueFoundry's insights. Explore efficient AI workload management solutions. - [The Messy Middle: From IVR to Hybrid AI Systems](https://www.truefoundry.com/blog/the-messy-middle-surviving-the-transition-from-rule-based-ivr-to-agentic-systems): Discover how enterprises can survive the messy middle of customer experience transformation—navigating the limitations of legacy rule-based IVR and the challenges of adopting LLM-driven agentic systems. This blog by Pavel Fomitchov explores why businesses can’t wait on AI adoption, the hybrid approach powering real-world use cases, and the tradeoffs leaders must consider to balance efficiency, compliance, and customer satisfaction at scale. - [Benchmarking Mistral-7B: Latency, Cost, RPS Analysis](https://www.truefoundry.com/blog/benchmarking-mistral-7b): Evaluate performance with Mistral-7B benchmarking insights. Optimize ML operations for enhanced results - [Weights & Biases Integration Guide | TrueFoundry](https://www.truefoundry.com/blog/machine-learning-platform-integrations-wandb): Explore challenges in managing experiments and discover how TrueFoundry integrates with Weights & Biases to streamline experiment tracking and analysis. - [True ML Talks #12 - Cofounder @ Llama-Index](https://www.truefoundry.com/blog/prompt-engineering-llms-llama-index): Explore insights from the cofounder of Llama-Index on True ML Talks #12. Join discussions on ML advancements. - [True ML Talks #14: LLMs & Reinforcement Learning at CX Score](https://www.truefoundry.com/blog/llm-rl-cx-score): Join True ML Talks #14 for discussions on LLMs and Reinforcement Learning at CX Score. Explore applications in ML. - [Cursor Integration with TrueFoundry for AI Governance](https://www.truefoundry.com/blog/cursor-integration-with-truefoundry): Learn how to integrate the Cursor AI editor with the TrueFoundry AI Gateway. Centralize API keys, gain full observability, and control LLM costs and security. - [Dark launches: What they are and how to do them](https://www.truefoundry.com/blog/dark-launch-is-the-best-light-launch): Discover why dark launch is key for optimizing software deployments. Learn how TrueFoundry enables seamless, low-risk feature rollouts. - [Future-Proof Your Business with AI Center of Excellence](https://www.truefoundry.com/blog/ai-center-of-excellence-how-you-can-future-proof-your-business): Learn how to establish an AI Center of Excellence with TrueFoundry's guidance. Explore strategies for leveraging AI to drive innovation and gain a competitive edge. - [Hosted Jupyter Notebooks and VS Code on Kubernetes](https://www.truefoundry.com/blog/hosted-jupyter-notebooks-vs-code-on-kubernetes): Learn how TrueFoundry enables hosted Jupyter Notebooks and VS Code on Kubernetes for seamless dev workflows. Read more in detail on this blog post. - [Environment configuration - why, what and how?](https://www.truefoundry.com/blog/secrets-management): Discover the importance of environment configuration in ML workflows. Learn why it matters, what it entails, and how TrueFoundry simplifies the process for you. - [Training ML Models with TrueFoundry's Jobs](https://www.truefoundry.com/blog/training-machine-learning-models-using-jobs): Discover how TrueFoundry streamlines machine learning model training. Explore our MLOps solutions for faster development and experimentation. - [True ML Talks #8 - ML Platform @ Intuit](https://www.truefoundry.com/blog/machine-learning-platform-intuit): Join True ML Talks #8 for discussions on the machine learning platform at Intuit. Explore ML applications in finance. - [Fine-Tuning OpenAI Models with Confluence Data | TrueFoundry](https://www.truefoundry.com/blog/training-fine-tuning-of-llms-with-your-own-data): Discover TrueFoundry's advanced techniques for fine-tuning OpenAI models with your Confluence data, enhancing performance and accuracy. - [Drift Tracking: A Complete Guide | TrueFoundry](https://www.truefoundry.com/blog/guide-to-drift-tracking): Unlock drift tracking complexities with TrueFoundry's guide. Master model performance monitoring and data drift detection for top-notch ML results. - [Exploring the Diverse Applications of LLM Models](https://www.truefoundry.com/blog/large-language-models-applications): Explore LLMs' wide-ranging applications with TrueFoundry. Discover how LLMs revolutionize industries & unlock new possibilities. - [True ML Talks #3 - ML Platform @ Facebook](https://www.truefoundry.com/blog/ml-platform-at-facebook): Discover insights into the machine learning platform at Facebook on True ML Talks #3. Join discussions on ML advancements. - [SSH Server Containers for Development on Kubernetes](https://www.truefoundry.com/blog/ssh-server-containers-for-development-on-kubernetes): Explore how SSH server containers facilitate development on Kubernetes by enabling secure remote access and efficient containerized workflow management. - [AnythingLLM Integration Guide for Truefoundry AI Gateway](https://www.truefoundry.com/blog/unlocking-enterprise-grade-ai-integrating-anythingllm-with-truefoundrys-ai-gateway): Connect AnythingLLM to TrueFoundry’s AI Gateway in minutes. Step-by-step setup, cost controls, security, and low-code automation best practices for enterprise AI teams. - [True ML Talks #6 - ML Platform @ Nomad Health](https://www.truefoundry.com/blog/machine-learning-platform-nomad-health): Explore the machine learning platform at Nomad Health on True ML Talks #6. Join discussions on ML applications in healthcare. - [Building RAG using Cognita and MongoDB Atlas](https://www.truefoundry.com/blog/building-rag-using-truefoundry-and-mongodb-atlas): Building RAG using Cognita and MongoDB Atlas - [How to Deploy Your Agno AI Agent on TrueFoundry](https://www.truefoundry.com/blog/deploying-your-agno-agent-on-truefoundry): Practical guide to deploying your agno agent on truefoundry, with setup steps, architecture decisions, and production best practices. - [The $360K question about Large Language Models Economics](https://www.truefoundry.com/blog/economics-of-large-language-models): Explore the economics of Large Language Models with TrueFoundry. Learn about the costs, benefits, and considerations of adopting LLMs in your organization. - [Kubernetes Architecture for MLOps | TrueFoundry](https://www.truefoundry.com/blog/kubernetes-architecture-for-mlops): Explore the Kubernetes architecture for MLOps with TrueFoundry's expert insights. Learn how Kubernetes enables scalable and efficient machine learning workflows. - [Benchmarking Falcon-40B-Instruct: Latency, Cost, and RPS Evaluation](https://www.truefoundry.com/blog/benchmarking-falcon-40b): Benchmarking Falcon-40B-Instruct: latency, cost, and RPS insights to evaluate its suitability for business needs. Note: qualitative performance not covered. - [Latest Deployment Platform Updates | TrueFoundry](https://www.truefoundry.com/blog/truefoundry-deployment-platform-updates): Stay informed with TrueFoundry's latest updates on deployment platforms. Discover our innovative solutions for enhancing deployment efficiency and reliability. - [ChatGPT Plugins: Everything you need to know](https://www.truefoundry.com/blog/chatgpt-plugins): Gain insights into ChatGPT plugins with TrueFoundry. Explore how plugins enhance functionality and customize conversational AI experiences. - [Prompting, Fine-Tuning, or RAG: Choosing the Right Approach](https://www.truefoundry.com/blog/prompting-fine-tuning-or-rag): Discover the differences between prompting, fine-tuning, and RAG techniques for model optimization. - [Cluster Autoscaling for Big 3 Clouds | TrueFoundry](https://www.truefoundry.com/blog/cluster-autoscaling-for-big-3-clouds): Learn how TrueFoundry enables cluster autoscaling across major cloud platforms. Explore our scalability solutions for optimizing resource use and cost efficiency. - [How to Fine-Tune a Llama-2 (7B) to Beat ChatGPT](https://www.truefoundry.com/blog/fine-tune-a-llama-2-7b-to-beat-chatgpt): Learn strategies for fine-tuning a Llama-2 (7B) model to outperform ChatGPT with TrueFoundry's expert guidance. - [Fractional GPUs in Kubernetes | TrueFoundry](https://www.truefoundry.com/blog/fractional-gpus-in-kubernetes): Explore TrueFoundry's solutions for utilizing fractional GPUs in Kubernetes, optimizing resource allocation and performance with efficient MLOps strategies. - [Building Compound AI Systems with TrueFoundry & Mongo DB](https://www.truefoundry.com/blog/building-compound-ai-systems-with-truefoundry-mongo-db): Building Compound AI Systems with TrueFoundry & Mongo DB - [Adding OAuth2 to Jupyter Notebooks on Kubernetes | TrueFoundry](https://www.truefoundry.com/blog/adding-oauth2-to-notebooks-on-kubernetes): Discover how to enhance Jupyter Notebook security on Kubernetes with OAuth2 integration, guided by TrueFoundry. Explore our solutions for securing notebook - [GenAI as a Service For Enterprises](https://www.truefoundry.com/blog/genai-as-a-service-for-enterprises): Discover TrueFoundry’s GenAI‑as‑a‑Service offering: fully managed LLM pipelines with compliance-aware governance, observability, cost controls, and seamless integration into enterprise environments. - [Programmatic Data Labeling at Scale with Snorkel](https://www.truefoundry.com/blog/programmatic-data-labelling-at-snorkel-ai): Discover how Snorkel AI leverages programmatic data labelling techniques to enhance data annotation efficiency and accelerate machine learning model development. - [Deploy Multi-Agent Workflows with CrewAI on TrueFoundry](https://www.truefoundry.com/blog/how-to-deploy-multiagent-workflow-using-crewai-on-truefoundry): Practical guide to how to deploy multiagent workflow using crewai on truefoundry, with setup steps, architecture decisions, and production best… - [True ML Talks #21 - Machine Learning Platform @ Loblaw Digital](https://www.truefoundry.com/blog/machine-learning-platform-loblaw-digital): Discover insights into the machine learning platform at Loblaw Digital on True ML Talks #21. Join discussions on ML advancements. - [Application Development with Kubernetes | TrueFoundry](https://www.truefoundry.com/blog/application-development-with-kubernetes-2): Learn how TrueFoundry streamlines application development with Kubernetes. Explore our MLOps solutions for accelerating dev cycles & ensuring app reliability. - [Time's Impact on ML Models | TrueFoundry](https://www.truefoundry.com/blog/time-killed-my-ml-model): Explore the effects of time on machine learning models and discover strategies to mitigate its impact. Learn how TrueFoundry optimizes ML workflows. - [Understanding open source LLMs](https://www.truefoundry.com/blog/open-source-llms): Discover the impact of open-source Large Language Models (LLMs) on industries with TrueFoundry. See how organizations can use them to innovate and grow. - [True ML Talks #4 - ML Platform @ Salesforce](https://www.truefoundry.com/blog/ml-platform-at-salesforce): Join True ML Talks #4 for discussions on the machine learning platform at Salesforce. Explore ML applications in CRM. - [A 2-Person team serving model to 1.5M people with TrueFoundry](https://www.truefoundry.com/blog/2-people-serving-model-to-millions-truefoundry): Discover how a 2-person team leveraged TrueFoundry to serve models to 1.5 million users. Explore their journey on this blog post. - [Evaluating ML System Readiness | TrueFoundry](https://www.truefoundry.com/blog/ml-system-scoring): Learn how TrueFoundry evaluates ML systems' production readiness & technical debt. Discover our MLOps solutions for robust, reliable machine learning deployments. - [How to Build a Impactful ML Models | Challenges & Solutions](https://www.truefoundry.com/blog/impactful-ml-model): Uncover ML model challenges and how TrueFoundry aids. Discover solutions for seamless ML development and deployment. - [Dify Integration with TrueFoundry AI Gateway: A Step-by-Step Guide](https://www.truefoundry.com/blog/dify-integration): Learn to integrate Dify, the open-source low-code AI platform, with the TrueFoundry AI Gateway. Gain enterprise AI governance, cost management, and robust security for your applications. - [ML Tool Integrations #3 - Label Studio for Labelling Needs](https://www.truefoundry.com/blog/machine-learning-platform-integrations-label-studio): In this blog post, we are going to talk about Label Studio and how you can easily utilize Label Studio for Labelling via deploying it on TrueFoundry. - [True ML Talks #13 - ML Platform @ Cookpad](https://www.truefoundry.com/blog/machine-learning-platform-cookpad): Discover insights into the ML platform at Cookpad on True ML Talks #13. Join discussions on ML applications in cooking. - [ML Deployment as a Service: Architecture & Benefits](https://www.truefoundry.com/blog/ml-deployment-as-a-service): Practical guide to ml deployment as a service, with setup steps, architecture decisions, and production best practices. - [True ML Talks #5 - ML Platform @ Simpl](https://www.truefoundry.com/blog/machine-learning-platform-simpl): Join True ML Talks #5 for discussions on the machine learning platform at Simpl. Explore ML applications in fintech. - [Leveraging Fractional GPUs on Kubernetes | TrueFoundry](https://www.truefoundry.com/blog/leveraging-fractional-gpus-on-kubernetes): Leveraging Fractional GPUs on Kubernetes - [Highlights from TrueFoundry's Internal Hackathon](https://www.truefoundry.com/blog/truefoundry-generative-ai-hackathon): Explore highlights and innovations from TrueFoundry's hackathon. Discover creative solutions and insights by our team to drive innovation forward. - [Evolution of Machine Learning: A Deep Dive into Savin's Journey](https://www.truefoundry.com/blog/evolution-of-machine-learning-savins-journey): In this episode of #TrueMLtalks, Savin from Outerbounds shares insights into the MLOPs use cases in Netflix. - [Multi-Agent System with MCP: A Complete Guide](https://www.truefoundry.com/blog/multi-agent-system-with-mcp): Explore how a multi-agent system with MCP works, including its architecture, benefits, enterprise use cases, and implementation insights. - [Deploy Your First LangGraph Agent on TrueFoundry](https://www.truefoundry.com/blog/deploying-your-first-langgraph-agent-on-truefoundry): Practical guide to deploying your first langgraph agent on truefoundry, with setup steps, architecture decisions, and production best practices. - [True ML Talks #1 - ML Workflow @ Gong](https://www.truefoundry.com/blog/machinelearning-workflow-gong): Discover insights into the machine learning workflow at Gong on True ML Talks #1. Join discussions on ML advancements. - [Deploy & Monitor LangChain Apps with Truefoundry](https://www.truefoundry.com/blog/langchain-integration-with-truefoundry): Supercharge your LangChain apps. Learn how to deploy, monitor, and trace LLM applications in production using Truefoundry's unified AI Gateway. - [True ML Talks #9 - ML Platform @ DoorDash](https://www.truefoundry.com/blog/true-ml-talks-9-ml-platform-doordash): Join us in True ML Talks as we explore DoorDash's ML Platform with Hien Luu, covering ML use cases, scalable model serving, shadowing models, gRPC, and more. - [Enhancing Customer Support with Real-Time AI Assistance Using Cognita](https://www.truefoundry.com/blog/enhancing-customer-support-with-real-time-ai-assistance-using-cognita): SEO Meta Description Explore how TrueFoundry's Cognita framework enhances customer support with advanced AI capabilities. Discover its modular architecture, real-time query handling, multilingual support, and continuous improvement features, providing efficient, scalable, and accurate customer service solutions. Learn about seamless CRM integration, security measures, and proactive support analytics that boost customer satisfaction and operational efficiency. - [True ML Talks #17 - ML Platforms @ Slack, LLMs & SlackGPT](https://www.truefoundry.com/blog/machine-learning-platform-slack-llms-and-slackgpt): Explore ML platforms at Slack, along with LLMs and SlackGPT on True ML Talks #17. Join discussions on AI integration. - [Kubernetes for Data Scientists | TrueFoundry](https://www.truefoundry.com/blog/kubernetes-for-data-scientists): Explore how TrueFoundry utilizes Kubernetes for scalable infrastructure, empowering data scientists. Discover how our MLOps solutions boost collaboration and productivity. - [ML Tool Integrations #2: DVC for Data Versioning](https://www.truefoundry.com/blog/machine-learning-platform-integrations-dvc): Discover how integrating DVC with ML platforms streamlines version control and enhances collaboration for efficient machine learning workflows. - [True ML Talks #11 - LLMs, LLMops & GenAI @ Greenhouse CTO](https://www.truefoundry.com/blog/llms-llmops-and-genai-greenhouse): Join True ML Talks #11 for discussions on LLMs, LLMops, and GenAI with Greenhouse's CTO. Explore ML advancements in HR tech. - [LLM Locust: Benchmarking LLM Performance at Scale](https://www.truefoundry.com/blog/llm-locust-a-tool-for-benchmarking-llm-performance): In-depth breakdown of llm locust a tool for benchmarking llm performance, focusing on architecture, benefits, challenges, and enterprise… - [Auto-Deploy LLM Agents for Production GenAI Workloads](https://www.truefoundry.com/blog/autodeploy-llm-agent-to-for-genai-deployments): Practical guide to autodeploy llm agent to for genai deployments, with setup steps, architecture decisions, and production best practices. - [LLAMA 2 Model Benchmarks: Insights for Performance Evaluation](https://www.truefoundry.com/blog/llama-2-benchmarks): Explore LLAMA 2 model benchmarks to gain valuable insights for assessing performance and optimizing strategies effectively. - [True ML Talks #2 - ML Workflow @ Stitch Fix](https://www.truefoundry.com/blog/machinelearning-workflow-stitchfix): Join True ML Talks #2 for discussions on the machine learning workflow at Stitch Fix. Explore ML applications in fashion. - [Efficient ML Storage with Kubernetes Volumes](https://www.truefoundry.com/blog/volumes-on-kubernetes): This blog explores Kubernetes volumes, provisioning modes, storage classes on AWS, Azure, GCP, and using S3/EFS volumes. - [Fine-tune and deploy Llama 2 LLM models](https://www.truefoundry.com/blog/deploy-and-finetune-llama-2-on-your-cloud): Effortlessly deploy and optimize Llama 2 models on your cloud platform with our expert guidance. Maximize Large Language Models (LLMs) performance efficiently. - [n8n Integration with AI Gateway for Cost Control](https://www.truefoundry.com/blog/n8n-integration-with-truefoundry-ai-gateway): Scale your n8n workflows with enterprise-grade security, cost management, and observability. Learn to integrate n8n with the TrueFoundry AI Gateway in 3 simple steps. - [Simplifying Environment Variable Management | TrueFoundry](https://www.truefoundry.com/blog/managing-environment-variables-with-secretsfoundry): Explore how SecretsFoundry manages ML project variables easily. TrueFoundry secures sensitive data in your workflows. - [Helm Charts on ArtifactHub via GitHub Pages | TrueFoundry](https://www.truefoundry.com/blog/hosting-helm-charts-on-github-pages): Discover how to publish Helm charts on ArtifactHub via GitHub Pages with TrueFoundry's comprehensive deployment guide. - [From Hostel Dorm to Seed Funding | TrueFoundry](https://www.truefoundry.com/blog/announcing-our-seed-fund-message-from-the-founders): Follow TrueFoundry's journey from a dorm room to securing seed funding. Discover the milestones, challenges, and our vision for the future of AI. ### Resources | Truefoundry vs Competitors - [TrueFoundry vs Portkey: Choosing the Best AI Gateway](https://www.truefoundry.com/vs/portkey): TrueFoundry vs Portkey: explore key differences in enterprise AI Gateway and LLM operations, including deployment, observability, governance, and flexibility - [TrueFoundry vs SageMaker: A Detailed Comparison](https://www.truefoundry.com/vs/sagemaker): Compare TrueFoundry vs Amazon SageMaker for deploying, managing, and scaling AI in production with better speed and flexibility. ### Resources | Case Studies - [How NVIDIA Improves GPU Cluster Utilization with LLM Agents](https://www.truefoundry.com/case-study/how-nvidia-improves-gpu-cluster-utilization-with-llm-agents): Learn how NVIDIA improves GPU cluster utilization using LLM agents on TrueFoundry to scale AI workloads efficiently. - [How Innovaccer Centralized GenAI and Accelerated Deep Learning Deployment with Truefoundry](https://www.truefoundry.com/case-study/how-innovaccer-partnered-truefoundry): How Aviva Credito routed millions of LLM requests through a single AI Gateway to gain observability, model fallbacks, and provider-agnostic control. - [500M IVR Calls: Healthcare AI Platform Case Study](https://www.truefoundry.com/case-study/agent-to-handle-500-million-ivr-calls-one-ai-platform): Fortune 50 healthcare leader scaled agentic AI to 500M annual IVR calls with TrueFoundry's unified platform. Learn how they cut costs and latency. - [Adopt AI Scales Multi-Model Agents with TrueFoundry](https://www.truefoundry.com/case-study/how-adopt-scales-multi-model-agents-with-truefoundry): Learn how Adopt AI unified multi-provider LLM access, centralized observability, and scaled agentic workflows using TrueFoundry's AI Gateway. --- ## Developer Docs - [Setup Your Account - TrueFoundry Docs](https://www.truefoundry.com/docs/create-and-setup-your-account): Step-by-step guide for create and setup your account, explaining configuration, best practices, and real-world usage on TrueFoundry. - [Finetuning LLMs - TrueFoundry Docs](https://www.truefoundry.com/docs/finetuning-a-model-from-the-model-catalogue): Finetune Llama, Mistral, Mixtral and more on one or more GPUs - [Deploy Kubernetes Manifests - TrueFoundry Docs](https://www.truefoundry.com/docs/deploy-kubernetes-manifests): Learn how to deploy Kubernetes manifests directly through TrueFoundry's web interface with a complete example. - [Deploy Helm Charts - TrueFoundry Docs](https://www.truefoundry.com/docs/deploy-helm-charts): Complete guide to deploying Helm charts in TrueFoundry with support for multiple repository types, Kustomize integration, and advanced configurations - [Deploy MCP Server from npx/uvx - TrueFoundry Docs](https://www.truefoundry.com/docs/mcp-server-deployment/deploy-mcp-server-from-npx-uvx): Learn how to deploy an MCP server that you're currently using in VSCode/Cursor/Claude as a service on TrueFoundry. - [Introduction - TrueFoundry Docs](https://www.truefoundry.com/docs/introduction-to-a-service): Learn the basics of services, endpoints, and deployments. - [Ingress Controller Configuration - TrueFoundry Docs](https://www.truefoundry.com/docs/ingress-controller-configuration): Configure an ingress controller other than Istio with custom ingress class names and TLS certificate settings. - [View Metrics - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/analytics): Monitor LLM and MCP performance, costs, guardrails, routing, and caching from a unified metrics dashboard - [Deployment Guardrails and Policies - TrueFoundry Docs](https://www.truefoundry.com/docs/applying-custom-policies): Step-by-step guide for applying custom policies, explaining configuration, best practices, and real-world usage on TrueFoundry. - [Introduction to AI Gateway - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/intro-to-llm-gateway): TrueFoundry AI Gateway: A unified interface for accessing 1000+ LLMs with enterprise-grade security, observability, and governance - [Creating Your First Workflow - TrueFoundry Docs](https://www.truefoundry.com/docs/creating-your-first-workflow): Step-by-step guide for creating your first workflow, explaining configuration, best practices, and real-world usage on TrueFoundry. - [Interacting With Workflow - TrueFoundry Docs](https://www.truefoundry.com/docs/interacting-with-workflow): Learn how to trigger, monitor, and debug workflows. - [Huggingface Trainer Callback - TrueFoundry Docs](https://www.truefoundry.com/docs/huggingface-trainer-callback): Callback for Huggingface Trainer to automatically log metrics and checkpoints to TrueFoundry - [Truefoundry Overview - TrueFoundry Docs](https://www.truefoundry.com/docs/platform/overview): Truefoundry enables developer productivity and governance by making AI deployments easier and providing an AI gateway to access models, MCP servers and agents. - [Changelog - TrueFoundry Docs](https://www.truefoundry.com/docs/changelog): Step-by-step guide for changelog, explaining configuration, best practices, and real-world usage on TrueFoundry. - [Overview - TrueFoundry Docs](https://www.truefoundry.com/docs/mcp-server-deployment/mcp-server-deployment-overview): Learn how to deploy MCP servers on TrueFoundry. Covers HTTP and stdio-based servers from source code, npx/uvx packages, and custom implementations. - [Model Registry - TrueFoundry Docs](https://www.truefoundry.com/docs/model-registry): Store, version, and manage your ML models in the TrueFoundry model registry with stage transitions and metadata. - [Deploying LLMs - TrueFoundry Docs](https://www.truefoundry.com/docs/deploying-an-llm-model-from-the-model-catalogue): Deploy LLMs from the model catalogue. Simple steps to serve models in production. - [Secret Management - TrueFoundry Docs](https://www.truefoundry.com/docs/manage-secrets): Store and manage secrets securely using secret groups with role-based access control in TrueFoundry. - [Launch Jupyter Notebook - TrueFoundry Docs](https://www.truefoundry.com/docs/launch-notebooks): Launch notebooks for experimentation and development. - [Monitor Your Async Service - TrueFoundry Docs](https://www.truefoundry.com/docs/monitoring-your-async-service): Monitor async service health with consumer lag, processing rate, and latency metrics plus real-time logs. - [Key Concepts - TrueFoundry Docs](https://www.truefoundry.com/docs/key-concepts): Key concepts you need to understand before using TrueFoundry. - [Deploy MCP Server From Code - TrueFoundry Docs](https://www.truefoundry.com/docs/mcp-server-deployment/deploy-mcp-server-from-code): Learn how to deploy an MCP server from source code, whether it's in a public GitHub repository or code you've written yourself. - [Deploy your first Async Service - TrueFoundry Docs](https://www.truefoundry.com/docs/deploy-your-first-asyncservice): Deploy your first async service. Learn architecture, setup, and scaling basics. - [Generating TrueFoundry API Keys - TrueFoundry Docs](https://www.truefoundry.com/docs/generating-truefoundry-api-keys): Create and manage Personal Access Tokens and Virtual Accounts for programmatic TrueFoundry platform access. - [TrueFoundry MCP Gateway - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/mcp/mcp-overview): Centralized MCP gateway for enterprise AI agents—unified access, OAuth, security, observability, and guardrails for all your MCP servers. - [Integrations - TrueFoundry Docs](https://www.truefoundry.com/docs/integrations-overview): Overview of all supported integrations in the TrueFoundry platform. - [Introduction to Volume - TrueFoundry Docs](https://www.truefoundry.com/docs/introduction-to-volume): Understand how volumes work for persistent storage, shared data, and model checkpointing in TrueFoundry deployments. - [Access Control - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/gateway-access-control): Control access of models among teams, users and applications - [Deployment Options - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/modes-of-deployment): Explore the different Gateway deployment options ranging from self-hosting to fully managed - [Access Control - TrueFoundry Docs](https://www.truefoundry.com/docs/collaboration-and-access-control): Step-by-step guide for collaboration and access control, explaining configuration, best practices, and real-world usage on TrueFoundry. - [Getting Started - TrueFoundry Docs](https://www.truefoundry.com/docs/deploy-job-from-a-public-github-repository): Deploy jobs directly from a public GitHub repo. Simple setup with version control. - [Introduction - TrueFoundry Docs](https://www.truefoundry.com/docs/introduction-to-a-job): Understand what a job is and how it runs on TrueFoundry. - [Playground - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/prompt-playground): Create, test, save and compare prompts in the Playground. - [Workflow Concepts - TrueFoundry Docs](https://www.truefoundry.com/docs/workflow-concepts): Understand core workflow concepts including workflows, tasks, decorators, and task execution flow in TrueFoundry. - [Creating And Using Volumes - TrueFoundry Docs](https://www.truefoundry.com/docs/creating-a-volume): Step-by-step guide for creating a volume, explaining configuration, best practices, and real-world usage on TrueFoundry. - [Providers - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/supported-providers): Browse the full list of LLM providers and models supported by TrueFoundry AI Gateway across 15+ platforms. - [Prompt Versioning - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/prompt-versioning): Understand version history and the Prompt Registry; load specific versions into the Playground. - [Routing Config - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/load-balancing-overview): Global YAML-based routing configuration for TrueFoundry AI Gateway - [Ecosystem & Integrations - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/ecosystem): Discover the full ecosystem of tools, frameworks, and platforms that integrate with TrueFoundry AI Gateway. - [Deploying NVIDIA NIM Models - TrueFoundry Docs](https://www.truefoundry.com/docs/deploying-nvidia-nims): Deploy optimized TensorRT-LLM Engines using NIM Containers - [View Logs, Metrics And Events - TrueFoundry Docs](https://www.truefoundry.com/docs/monitor-your-service): Monitor your deployed services with pod-level logs, resource metrics, events, and Grafana dashboard integration. - [Prompt Management - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/prompt-management): Learn how to create, test, save, and version your prompts using TrueFoundry's AI Gateway for optimised AI interactions. - [TrueFoundry Python SDK - TrueFoundry Docs](https://www.truefoundry.com/docs/truefoundry_sdk): Complete Python SDK for TrueFoundry - Access and manage resources on TrueFoundry - [Autoscaling - TrueFoundry Docs](https://www.truefoundry.com/docs/autoscaling-overview): Step-by-step guide for autoscaling overview, explaining configuration, best practices, and real-world usage on TrueFoundry. - [Gateway Architecture - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/gateway-architecture): Learn how to use gateway architecture with TrueFoundry AI Gateway, including setup steps, use cases, and production-ready examples. - [Getting Started - TrueFoundry Docs](https://www.truefoundry.com/docs/deploy-first-service): Deploy your first service on TrueFoundry. From setup to live endpoint in minutes. - [Introduction - TrueFoundry Docs](https://www.truefoundry.com/docs/introduction-to-ml-repo): Overview of ML Repo for managing experiments and artifacts. - [Benchmarking LLMs - TrueFoundry Docs](https://www.truefoundry.com/docs/benchmarking-llms): Measure token generation throughput, Time to First Token (TTFT), Inter Token Latency of LLMs via the chat completions API - [Introduction to Async Service - TrueFoundry Docs](https://www.truefoundry.com/docs/introduction-to-async-service): Introduction to async services and event-driven execution. - [Introduction To Workflow - TrueFoundry Docs](https://www.truefoundry.com/docs/introduction-to-workflow): Powered by Flyte (An OpenSource Workflow Orchestrator) - [Setup For CLI - TrueFoundry Docs](https://www.truefoundry.com/docs/setup-cli): Install and configure the TrueFoundry CLI for managing deployments, experiments, and platform resources. - [Introduction - TrueFoundry Docs](https://www.truefoundry.com/docs/model-deployment-introduction): Introduction to the model deployment lifecycle from training and logging to serving models in production. - [List Secrets - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/secrets/list-secrets): List secrets associated with a user filtered with optional parameters passed in the body. - [Create multipart upload - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/artifacts/create-multipart-upload): Create a multipart upload for large files in an artifact version. - [Get MCP server authentication with auto-refresh (Admin only) - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/mcp-servers/get-mcp-server-authentication-with-auto-refresh-admin-only): Retrieves authentication details for the specified user. Automatically refreshes expired tokens for OAuth based servers. Requires admin access. - [Setting up Okta OAuth2 Authentication for MCP Servers - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/mcp/mcp-server-oauth-okta): Learn how to create and deploy an OAuth2-authenticated MCP server using Okta and fastMCP, then integrate it with TrueFoundry AI Gateway. - [Get Application - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/applications/get-application): Get Application associated with the provided application ID. - [Chat Completions API (/chat/completions) - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/chat-completions-overview): Learn how to use TrueFoundry's unified Chat Completions API to interact with models from multiple providers through a consistent interface - [Environment Variables And Secrets - TrueFoundry Docs](https://www.truefoundry.com/docs/environment-variables-and-secrets): Manage environment variables and secrets securely across services. - [Rerank Documents - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/rerank/rerank-documents): Rerank documents based on the given query and parameters. - [Using tfy apply - TrueFoundry Docs](https://www.truefoundry.com/docs/using-tfy-apply): preview and apply changes to your resources using tfy apply - [Arize - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/arize): Learn how to export LLM Gateway traces to Arize using OpenTelemetry integration. - [Get ML Repo - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/mlrepos/get-ml-repo): Get an ML Repo by its ID. - [Delete Application - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/applications/delete-application): Delete Application associated with the provided application ID. - [Github - TrueFoundry Docs](https://www.truefoundry.com/docs/github-integration-set-up): Create a GitHub App and configure the integration with TrueFoundry for repository access and CI/CD. - [Download Models/Artifacts - TrueFoundry Docs](https://www.truefoundry.com/docs/download-and-cache-models): Download and cache models efficiently to reduce cold starts and latency. - [Resend Invite - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/users/resend-invite): Resend the invite to the user - [Creating A Databricks Task - TrueFoundry Docs](https://www.truefoundry.com/docs/databricks-task): Learn how to trigger Databricks jobs from a TrueFoundry workflow using DatabricksJobTaskConfig, configure workspace and job settings, and set up authentication. - [Workspaces - TrueFoundry Docs](https://www.truefoundry.com/docs/truefoundry_sdk/workspaces): SDK methods to list, get, create, and manage workspaces with cluster and FQN-based filtering options. - [Configure Job Trigger - TrueFoundry Docs](https://www.truefoundry.com/docs/deploy-a-cron-job): Deploy cron jobs on TrueFoundry with step-by-step instructions, configs, and examples. - [Set Up CI/CD - TrueFoundry Docs](https://www.truefoundry.com/docs/setting-up-cicd-for-your-service): Configure CI/CD pipelines for your services using GitHub Actions, GitLab CI/CD, Bitbucket, or Jenkins. - [Stage artifact version - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/artifacts/stage-artifact-version): Stage an artifact version for upload, returning storage location and version ID. - [List Users - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/scim-v2/list-users): TrueFoundry offers an enterprise-grade AI Gateway combining LLM, MCP, and Agent Gateways—empowering businesses to connect, monitor, and govern agentic AI applications across providers from a unified control plane. - [Creating A Spark Task - TrueFoundry Docs](https://www.truefoundry.com/docs/spark-task): Learn how to run PySpark jobs as tasks in a TrueFoundry workflow, configure Spark resources, and monitor runs with the Spark UI. - [Model Versions - TrueFoundry Docs](https://www.truefoundry.com/docs/truefoundry_sdk/model_versions): SDK methods to create, tag, list, and manage individual model versions in your TrueFoundry ML repos. - [Get virtual account - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/virtual-accounts/get-virtual-account): Get virtual account by id - [Slack - TrueFoundry Docs](https://www.truefoundry.com/docs/slack-bot-integration): Set up a Slack Bot integration with TrueFoundry to receive deployment alerts and platform notifications. - [PII/PHI Detection Guardrail - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/tfy-pii): Detect and redact PII or PHI in LLM inputs, outputs, and MCP tool calls using the built-in TrueFoundry guardrail. - [Manage User Roles & Permissions - TrueFoundry Docs](https://www.truefoundry.com/docs/platform/manage-user-roles-and-permissions): Configure custom roles with scoped permissions for AI Gateway, MCP servers, agents, and platform resources. - [Batch API (/batches) - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/batch-predictions-with-truefoundry-llm-gateway): Process jobs asynchronously using TrueFoundry's batch prediction API - [TrueFoundry Client - TrueFoundry Docs](https://www.truefoundry.com/docs/truefoundry_sdk/main_client): Reference for the main TrueFoundry SDK client class with apply and other top-level management methods. - [Create or Update Secret Group - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/secret-groups/create-or-update-secret-group): Creates a new secret group or updates an existing one based on the provided manifest. - [Text to Speech API - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/text-to-speech): Convert text to speech through TrueFoundry's AI Gateway - [Virtual Models - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/virtual-model): Route requests across multiple model providers with load balancing, failover, and retries using a single model name - [Cancel an Ongoing Deployment - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/applications/cancel-an-ongoing-deployment): Cancel an ongoing deployment associated with the provided application ID and deployment ID. - [Agent API - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/agents/use-mcp-server-in-code-agent): Learn how to use TrueFoundry's Agent API to integrate MCP servers into your applications for tool-using AI assistants. - [Add and List Models - TrueFoundry Docs](https://www.truefoundry.com/docs/apply-api-create-models): Learn how to add and list models (OpenAI, Anthropic, AWS Bedrock, etc.) using TrueFoundry APIs with comprehensive examples - [Create Application Deployment - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/applications/create-application-deployment): Create a new Application Deployment based on the provided manifest. - [Update User - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/scim-v2/update-user): TrueFoundry offers an enterprise-grade AI Gateway combining LLM, MCP, and Agent Gateways—empowering businesses to connect, monitor, and govern agentic AI applications across providers from a unified control plane. - [Deepgram - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/deepgram): Add and configure Deepgram Models in TrueFoundry's AI Gateway - [Scale Service to 0 - TrueFoundry Docs](https://www.truefoundry.com/docs/scale-service-to-0): Auto-scale services to zero replicas when idle and automatically restart them on incoming traffic using Elasti. - [Set Resources - TrueFoundry Docs](https://www.truefoundry.com/docs/resources-cpu-memory-storage): Configure CPU, memory, ephemeral storage, GPU, and shared memory resources for your TrueFoundry deployments. - [Delete User - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/users/delete-user): Delete user if they are not a collaborator in any resource and not part of any team other than everyone. - [Prompt Injection Guardrail - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/tfy-prompt-injection): Detect and block prompt injection and jailbreak attempts in LLM inputs using TrueFoundry's built-in Prompt Injection guardrail. - [Users - TrueFoundry Docs](https://www.truefoundry.com/docs/truefoundry_sdk/users): SDK methods to list, get, create, update, and manage user accounts within your TrueFoundry tenant. - [PagerDuty - TrueFoundry Docs](https://www.truefoundry.com/docs/pagerduty-integration): Set up PagerDuty as a notification channel for TrueFoundry alerts and incident management. - [Ml Repos - TrueFoundry Docs](https://www.truefoundry.com/docs/truefoundry_sdk/ml_repos): SDK methods to create, update, list, and manage ML repository entities for experiment and model tracking. - [Define Ports And Domains - TrueFoundry Docs](https://www.truefoundry.com/docs/define-ports-and-domains): Define ports and domains for your services. Configure routing, exposure, and access correctly. - [Audio Translation API - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/audio-translation): Convert audio files to text using translations models through TrueFoundry's AI Gateway - [Delete artifact version - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/artifacts/delete-artifact-version): Delete an artifact version by its ID. - [MCP Gateway URL and Transport Changes — v0.130 - TrueFoundry Docs](https://www.truefoundry.com/docs/change-announcements/mcp-gateway-url-transport-v0.130): v0.130 introduces smarter MCP Gateway URLs with OAuth chaining and a breaking change in transport protocol handling. - [Get Secret Group - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/secret-groups/get-secret-group): Get Secret Group by id. This method does not return the secret values of the associatedSecrets in the response. A separate API call to /v1/secrets/{id} should be made to fetch the associated secret value. - [Control Plane Upgrade - TrueFoundry Docs](https://www.truefoundry.com/docs/platform/control-plane-upgrade): Upgrade the control plane safely with minimal downtime. - [Image Generation API (/images/generations) - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/image-generation): Generate images from text prompts through TrueFoundry's AI Gateway - [Infra Set Up For Workflows - TrueFoundry Docs](https://www.truefoundry.com/docs/infra-set-up-for-workflows): Infrastructure setup guide for running workflows reliably at scale. - [Get Job Run - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/jobs/get-job-run): Get Job Run for provided jobRunName and jobId - [List Resource Types - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/scim-v2/list-resource-types): TrueFoundry offers an enterprise-grade AI Gateway combining LLM, MCP, and Agent Gateways—empowering businesses to connect, monitor, and govern agentic AI applications across providers from a unified control plane. - [Register Users - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/users/register-users): This endpoint allows tenant administrators to register users within their tenant. - [Cancel Batch - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/batch/cancel-batch): Cancel a running batch process - [Delete Resources - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/apply/delete-resources): Deletes resources of specific types, such as provider-account, cluster, workspace, or application. - [Agent App - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/agent/agent-app): Generate completions using agent app configuration. The model, MCP servers, system prompt, and guardrails are automatically provided from the agent app configuration. - [All enums - TrueFoundry Docs](https://www.truefoundry.com/docs/truefoundry_sdk/enums): Reference for all enumeration types in the TrueFoundry SDK including CloudProvider and component names. - [Speech to Text API - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/audio-transcription): Convert audio files to text using speech-to-text models through TrueFoundry's AI Gateway - [Delete User - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/scim-v2/delete-user): TrueFoundry offers an enterprise-grade AI Gateway combining LLM, MCP, and Agent Gateways—empowering businesses to connect, monitor, and govern agentic AI applications across providers from a unified control plane. - [Transcribe Audio - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/audio/transcribe-audio): Transcribes audio into the input language. - [List Addons - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/clusters/list-addons): List addons for the provided cluster. Pagination is available based on query parameters. - [Messages API (/messages) - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/messages-overview): Learn how to use Messages API through TrueFoundry's AI Gateway for interacting with Claude models. - [Environment Variables And Secrets - TrueFoundry Docs](https://www.truefoundry.com/docs/environment-variables-and-secrets-jobs): Configure environment variables and secrets specifically for jobs. - [Claude Enterprise Security Guide For Developers - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/mcp/enterprise-security-claude): A guide to Claude enterprise security for admins to govern access, secure data, and monitor deployments across web, desktop, and CLI interfaces. - [Secret Store - TrueFoundry Docs](https://www.truefoundry.com/docs/integrations-secret-store): Use secret stores to manage credentials securely across deployments. - [Pause / Resume Service - TrueFoundry Docs](https://www.truefoundry.com/docs/pause-resume-service): Pause services to shut down all replicas and save costs, then resume them without losing your configuration. - [Truefoundry Architecture - TrueFoundry Docs](https://www.truefoundry.com/docs/platform/architecture): Truefoundry provides a split-plane architecture to decouple compute, gateway and control-plane and can be deployed on your own infrastructure. - [Setup AI Gateway in Your Organization - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/setup-ai-gateway-in-org): Configure AI Gateway operations for your organization: enable SSO, manage access, and control how users sign in and use the gateway. - [Getting Started - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/guardrails-getting-started): Learn how to set up and implement guardrails to ensure safe and compliant LLM interactions and MCP tool invocations - [List ML Repos - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/mlrepos/list-ml-repos): List ML Repos with optional filtering by name. - [Upload File - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/files/upload-file): Upload a new file - [List artifacts - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/artifacts/list-artifacts): List artifacts with optional filtering by FQN, ML Repo, name, or run ID. - [Post moderations - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/moderations/post-moderations): API reference for post moderations, covering request parameters, responses, and examples for integrating with TrueFoundry. - [Files API (/files) - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/file-endpoints): Upload, manage, and retrieve files through TrueFoundry's AI Gateway - [Delete cluster - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/clusters/delete-cluster): Delete cluster associated with provided cluster id - [Apply tags to prompt version - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/prompts/apply-tags-to-prompt-version): Apply tags to a prompt version. - [Google Model Armor Guardrail Integration - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/google-model-armor): Integrate Google Cloud Model Armor with TrueFoundry AI Gateway for prompt injection, harmful content, PII, and malicious URI detection. - [Gitlab - TrueFoundry Docs](https://www.truefoundry.com/docs/gitlab-integration-set-up): Create a GitLab application and configure the integration with TrueFoundry for repository access and CI/CD. - [Creating A Map Task - TrueFoundry Docs](https://www.truefoundry.com/docs/creating-a-map-task): Step-by-step guide for creating a map task, explaining configuration, best practices, and real-world usage on TrueFoundry. - [Security and Compliance - TrueFoundry Docs](https://www.truefoundry.com/docs/platform/security-and-compliance): Learn about Truefoundry's enterprise-grade security features, compliance certifications, and data protection measures - [Deploy AI Gateway - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/install-only-llm-gateway): Learn how to use install only llm gateway with TrueFoundry AI Gateway, including setup steps, use cases, and production-ready examples. - [Personal Access Tokens - TrueFoundry Docs](https://www.truefoundry.com/docs/truefoundry_sdk/personal_access_tokens): SDK methods to list, create, and manage personal access tokens for TrueFoundry API authentication. - [Proxy API (/proxy) - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/proxy-api): Route requests directly to AI provider endpoints while maintaining TrueFoundry features like logging, rate limiting, and budget management - [Get MCP server by ID - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/mcp-servers/get-mcp-server-by-id): Retrieves a single MCP server by its ID. - [Get Audit Logs - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/audit-logs/get-audit-logs): Get paginated audit logs filtered by parameters passed in the query. - [TFY Agent - TrueFoundry Docs](https://www.truefoundry.com/docs/tfy-agent): Learn how the TFY Agent connects compute-plane clusters to the TrueFoundry control plane via secure WebSocket. - [Delete Team - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/teams/delete-team): Deletes the Team associated with the provided Id. - [Artifact Versions - TrueFoundry Docs](https://www.truefoundry.com/docs/truefoundry_sdk/artifact_versions): SDK methods to create, tag, list, and manage individual artifact versions in your TrueFoundry ML repos. - [Get Nvidia NIM Model Deployment Specifications - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/model-deployments/get-nvidia-nim-model-deployment-specifications): Fetches deployment specifications for a NIM Model - [Delete prompt version - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/prompts/delete-prompt-version-1): Delete a prompt version by manifest. - [Delete model - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/models/delete-model): Delete a model by its ID. - [Export OpenTelemetry Data - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/export-opentelemetry-data): Learn how to export OpenTelemetry traces with TrueFoundry AI Gateway for comprehensive observability. - [HashiCorp Vault - TrueFoundry Docs](https://www.truefoundry.com/docs/hashicorp): Integrate HashiCorp tools for secrets and infrastructure management. - [Get artifact version - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/artifacts/get-artifact-version): Get an artifact version by its ID. - [Setup GitOps - TrueFoundry Docs](https://www.truefoundry.com/docs/setup-gitops-using-truefoundry): Enable GitOps with TrueFoundry—store deployment configuration in Git and sync with a single CLI command. - [Pause an Application - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/applications/pause-an-application): Pause a running application by scaling to 0 replicas - [SQL Sanitizer Guardrail - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/sql-sanitizer): Detect and sanitize risky SQL patterns in LLM outputs using TrueFoundry's built-in SQL Sanitizer guardrail. - [Liveness/Readiness Probe - TrueFoundry Docs](https://www.truefoundry.com/docs/liveness-readiness-probe): Configure liveness and readiness probes for services. - [SSO Overview - TrueFoundry Docs](https://www.truefoundry.com/docs/sso): Enable single sign-on for TrueFoundry with identity providers like GSuite, Azure AD, Okta, or Keycloak. - [Update Secret Group - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/secret-groups/update-secret-group): Updates the secrets in a secret group with new values. A new secret version is created for every secret that has a modified value and any omitted secrets are deleted. The returned updated secret group does not have any secret values in the associatedSecrets field. A separate API call to /v1/secrets/{id} should be made to fetch the associated secret value. - [Trigger Job - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/jobs/trigger-job): Trigger Job for provided deploymentId or applicationId - [Overview - TrueFoundry Docs](https://www.truefoundry.com/docs/model-deployment/overview): Overview of model deployment options and patterns. - [Update, Rollback, Promote - TrueFoundry Docs](https://www.truefoundry.com/docs/update-rollback-promote-your-service): Update service versions, rollback to previous deployments, and promote services between environments safely. - [Getting Started - TrueFoundry Docs](https://www.truefoundry.com/docs/ml-repo-quickstart): Get started with ML Repo by creating a repository, setting up the CLI, and logging your first experiment. - [Image Variation API (/images/variations) - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/image-variation): Generate creative variations of existing images using TrueFoundry AI Gateway - [Delete artifact - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/artifacts/delete-artifact): Delete an artifact by its ID. - [Create Batch - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/batch/create-batch): Creates a new batch process - [Teams - TrueFoundry Docs](https://www.truefoundry.com/docs/truefoundry_sdk/teams): SDK methods to list, create, and manage teams for your TrueFoundry tenant with pagination support. - [Delete ML Repo - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/mlrepos/delete-ml-repo): Delete an ML Repo by its ID. - [Authentication and Security - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/mcp/mcp-gateway-auth-security): Complete guide to authentication, authorization, and security for MCP Servers in TrueFoundry AI Gateway - [Configure Ports - TrueFoundry Docs](https://www.truefoundry.com/docs/configure-ports): Step-by-step guide for configure ports, explaining configuration, best practices, and real-world usage on TrueFoundry. - [Delete MCP server authentication - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/mcp-servers/delete-mcp-server-authentication): Deletes the current user's OAuth 2.1 authentication for an MCP server integration. - [Jobs - TrueFoundry Docs](https://www.truefoundry.com/docs/truefoundry_sdk/jobs): SDK methods to list job runs, trigger job executions, and manage job lifecycle with filtering options. - [List Personal Access Tokens - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/personal-access-tokens/list-personal-access-tokens): List Personal Access Tokens created by the user in the current tenant. - [Quick Start Guide: Setup & Integration - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/quick-start): Quickly set up the TrueFoundry AI Gateway, connect model providers, and access LLMs with step-by-step instructions. - [Custom Guardrail/Plugins Configuration - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/custom-guardrails): Configure custom guardrails for validation and security. - [Sync virtual account token to secret store - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/virtual-accounts/sync-virtual-account-token-to-secret-store): Syncs the virtual account token to the configured secret store. Returns the updated JWT with sync metadata including timestamp and error (if any). - [Self-Hosted Models - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/self-hosted-models): Learn how to add and configure self-hosted or external AI models to TrueFoundry AI Gateway for centralized management and inference. - [Authenticate To GCP Using IAM Serviceaccount - TrueFoundry Docs](https://www.truefoundry.com/docs/authenticate-to-gcp-using-iam-serviceaccount): Step-by-step guide for authenticate to gcp using iam serviceaccount, explaining configuration, best practices, and real-world usage on… - [Create or update MCP server - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/mcp-servers/create-or-update-mcp-server): Creates a new MCP server or updates an existing one. - [Get model - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/models/get-model): Get a model by its ID. - [Generate stdio MCP manifest from stdio configuration JSON - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/mcp-servers/generate-stdio-mcp-manifest-from-stdio-configuration-json): Parses a single-entry mcpServers object and returns a stdio MCP server manifest. - [Create User - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/scim-v2/create-user): TrueFoundry offers an enterprise-grade AI Gateway combining LLM, MCP, and Agent Gateways—empowering businesses to connect, monitor, and govern agentic AI applications across providers from a unified control plane. - [List Associated Active Deployments for Multiple Secrets - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/secrets/list-associated-active-deployments-for-multiple-secrets): Returns the union of active deployments associated with any of the given secret IDs. Only secrets the user has read access to are considered. - [Create or Update a Team - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/teams/create-or-update-a-team): Creates a new team or updates an existing team. It ensures that the team name is unique, valid, and that the team has at least one member. The members of the team are added or updated based on the provided emails. - [Chat Completions - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/chat/chat-completions): Generate chat-based completions using the specified model. - [Cedar Guardrails - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/cedar-guardrails): Learn how to use Cedar policy language to create fine-grained access control guardrails for MCP tool invocations - [List Clusters - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/clusters/list-clusters): Retrieves a list of all latest Clusters. Pagination is available based on query parameters. - [Using Raw Container Task - TrueFoundry Docs](https://www.truefoundry.com/docs/container-task): Step-by-step guide for container task, explaining configuration, best practices, and real-world usage on TrueFoundry. - [Introduction - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/guardrails-overview): Learn about guardrails for ensuring safety, compliance, and quality in LLM interactions and MCP tool invocations - [Creates a variation of an image. - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/image/creates-a-variation-of-an-image): Generates a variation of a given image. - [Hosted Stdio-based MCP Server - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/mcp/stdio-mcp-server): Run a hosted MCP server via stdio and expose it through the gateway. - [Models - TrueFoundry Docs](https://www.truefoundry.com/docs/truefoundry_sdk/models): SDK methods to get, list, and manage model entities stored in TrueFoundry ML repository collections. - [Delete a Virtual Account - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/virtual-accounts/delete-a-virtual-account): Delete a virtual account associated with the provided virtual account id. - [SDK Types - TrueFoundry Docs](https://www.truefoundry.com/docs/truefoundry_sdk/types): Comprehensive reference for all data types in the TrueFoundry SDK including Account, Application, and Cluster. - [Get Cluster - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/clusters/get-cluster): Get cluster associated with provided id - [Create or Update MLRepo - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/mlrepos/create-or-update-mlrepo): Creates or updates an MLRepo entity based on the provided manifest. - [Setup Alerts - TrueFoundry Docs](https://www.truefoundry.com/docs/setup-alerts): Configure Prometheus AlertManager alerts with Email, Slack, or PagerDuty notification channels for monitoring. - [Artifacts and Artifact Versions - TrueFoundry Docs](https://www.truefoundry.com/docs/log-artifacts): Uploading files and directories as Artifacts. Downloading contents of Artifact to disk. - [Delete Job Run - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/jobs/delete-job-run): Delete Job Run for provided jobRunName and jobId - [Log & Monitor Custom Metrics - TrueFoundry Docs](https://www.truefoundry.com/docs/log-monitor-custom-metrics): Monitor logs and custom metrics for observability. - [Create or update artifact version - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/artifacts/create-or-update-artifact-version): Create or update an artifact version. - [Get model version - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/models/get-model-version): Get a model version by its ID. - [AWS - TrueFoundry Docs](https://www.truefoundry.com/docs/integration-provider-aws): Integrate AWS services with TrueFoundry. Configure access and resources. - [List Groups - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/scim-v2/list-groups): TrueFoundry offers an enterprise-grade AI Gateway combining LLM, MCP, and Agent Gateways—empowering businesses to connect, monitor, and govern agentic AI applications across providers from a unified control plane. - [Get User - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/users/get-user): Get User associated with provided User id - [List Job Runs - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/jobs/list-job-runs): List Job Runs for provided Job Id. Filter the data based on parameters passed in the query - [Truefoundry Gateway Plane Architecture - TrueFoundry Docs](https://www.truefoundry.com/docs/platform/gateway-plane-architecture): Architecture of the TrueFoundry AI Gateway, designed for high availability, low latency, and scalable LLM integration in production environments. - [Anthropic Stream Overload Fallback - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/anthropic-stream-overload-fallback): How TrueFoundry AI Gateway handles Anthropic overloaded_error in streaming with automatic fallback. - [List Users - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/users/list-users): List all users of tenant filtered by query and showInvalidUsers. Pagination is available based on query parameters. - [Rerank API (/rerank) - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/rerank): Learn how to use the Rerank API through TrueFoundry Gateway to enhance search relevance by scoring and reordering document results. - [Using Prompts - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/using-prompts): Learn how to use using prompts with TrueFoundry AI Gateway, including setup steps, use cases, and production-ready examples. - [Redirect And Mirror Traffic - TrueFoundry Docs](https://www.truefoundry.com/docs/intercepts): Understand intercepts and how they modify request and execution flow. - [Update Group - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/scim-v2/update-group): TrueFoundry offers an enterprise-grade AI Gateway combining LLM, MCP, and Agent Gateways—empowering businesses to connect, monitor, and govern agentic AI applications across providers from a unified control plane. - [TrueFoundry ML Client - TrueFoundry Docs](https://www.truefoundry.com/docs/truefoundry-ml-reference): TrueFoundry ML client reference for tracking experiments, logging artifacts, and managing models programmatically. - [ElevenLabs - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/elevenlabs): Add and configure ElevenLabs Models in TrueFoundry's AI Gateway - [Revoke All Personal Access Tokens - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/personal-access-tokens/revoke-all-personal-access-tokens): Revoke All Personal Access Tokens for the user with the given email - [Get token for a virtual account - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/virtual-accounts/get-token-for-a-virtual-account): Get token for a virtual account by id - [Rate Limiting - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/ratelimiting): Learn how to configure rate limiting in TrueFoundry AI Gateway to control usage, manage costs, and set limits based on users, teams, or applications. - [Get Deployment details - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/applications/get-deployment-details): Get Deployment associated with the provided application ID and deployment ID. - [Budget Limiting - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/budgetlimiting): Set and enforce cost boundaries across teams, users, and models to prevent runaway costs and maintain financial control - [List Teams for User - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/teams/list-teams-for-user): Retrieve all teams associated with the authenticated user. If the user is a tenant admin, returns all teams for the tenant. Pagination is available based on query parameters - [Get Team - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/teams/get-team): Get Team associated with provided team id - [Rollout Strategy - TrueFoundry Docs](https://www.truefoundry.com/docs/rollout-strategy): Configure how to rollout a new version of your application - [List Application Deployments - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/applications/list-application-deployments): Fetch all deployments for a given application ID with optional filters such as deployment ID or version. Supports pagination. - [Delete MCP server by name - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/mcp-servers/delete-mcp-server-by-name): Deletes an MCP server by its name. - [Data Directories - TrueFoundry Docs](https://www.truefoundry.com/docs/truefoundry_sdk/data_directories): SDK methods to get, list, create, and manage data directories for file storage in TrueFoundry. - [Get or Create Personal Access Token - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/personal-access-tokens/get-or-create-personal-access-token): Get an existing Personal Access Token by name, if it doesn't exist, it will create a new one and return the PAT data along with a fresh token. - [List available models - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/models/list-available-models): Lists the models that the requesting user is authorized to access. - [Azure Repos - TrueFoundry Docs](https://www.truefoundry.com/docs/azure-repos-integration-set-up): Follow this step to enable Azure Repos integrations - [Delete Group - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/scim-v2/delete-group): TrueFoundry offers an enterprise-grade AI Gateway combining LLM, MCP, and Agent Gateways—empowering businesses to connect, monitor, and govern agentic AI applications across providers from a unified control plane. - [List Virtual Accounts - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/virtual-accounts/list-virtual-accounts): List virtual accounts for the tenant. - [TrueFoundry AI Gateway Playground - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/playground-overview): Experiment with AI models, configure settings, set up guardrails, connect MCP servers, and create reusable prompts in the Playground. - [Get Service Provider Configuration - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/scim-v2/get-service-provider-configuration): TrueFoundry offers an enterprise-grade AI Gateway combining LLM, MCP, and Agent Gateways—empowering businesses to connect, monitor, and govern agentic AI applications across providers from a unified control plane. - [Gemini CLI - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/gemini-cli): This guide provides instructions for integrating Gemini CLI with TrueFoundry's AI Gateway - [Databricks - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/databricks-models): Add and configure Databricks models in TrueFoundry's AI Gateway - [Get prompt version - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/prompts/get-prompt-version): Get a prompt version by its ID. - [Live / Realtime API (/live) - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/live-api): Bidirectional realtime streaming (Live API) over WebSocket through TrueFoundry's AI Gateway - [List Model Response Input Items - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/responses/list-model-response-input-items): List input items for a specific model response - [List Provider Integrations - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/provider-integrations/list-provider-integrations): Get provider integrations for a tenant with optional filtering by type, fqn or id. Pagination is available based on query parameters. - [Migrate Sagemaker Pytorch Endpoint - TrueFoundry Docs](https://www.truefoundry.com/docs/model-deployment/migrate-from-sagemaker-pytorch-endpoint): Migrate SageMaker PyTorch endpoints to TrueFoundry. - [Simplified GitOps CI/CD with tfy apply — v0.132 - TrueFoundry Docs](https://www.truefoundry.com/docs/change-announcements/simplified-gitops-cicd-v0.132): From v0.132, use a single tfy apply command to replace complex per-file CI/CD scripts for GitOps workflows. - [Using the Common Tools MCP Server - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/mcp/common-tools-mcp-server): Connect and use tools from the Common Tools MCP Server managed by TrueFoundry - [Download Logs - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/logs/download-logs): Download logs associated with the specified workload, including Jobs, Services, Job Runs, Pods, or Workflows. Logs are filtered based on the provided query parameters. - [Activate User - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/users/activate-user): Activate user associated with the provided email within the tenant. - [Add authentication to your Endpoints - TrueFoundry Docs](https://www.truefoundry.com/docs/endpoint-authentication): Configure endpoint authentication. Secure your services with tokens and access rules. - [Caching (Exact and Semantic) - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/caching): Learn how caching works in the TrueFoundry AI Gateway for faster responses. - [Agent Responses - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/agent/agent-responses): Generate responses using the specified model with integrated external tools. - [Get Model Response - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/responses/get-model-response): Get a specific model response - [Configure Data Routing - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/data-routing): Configure storage destinations for AI Gateway request logs and metrics. Route traces to custom object stores based on Enterprise plan. - [Claude Code - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/claude-code): How to connect Claude Code with the TrueFoundry AI Gateway. - [TrojAI DEFEND Integration - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/trojai): Integrate TrojAI DEFEND with TrueFoundry AI Gateway for real-time AI firewall protection, PII detection, and prompt injection prevention. - [Resolve Dependency Tree - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/apply/resolve-dependency-tree): Resolves the dependency tree for the given manifests. - [AWS SQS - TrueFoundry Docs](https://www.truefoundry.com/docs/aws-sqs): Step-by-step guide for aws sqs, explaining configuration, best practices, and real-world usage on TrueFoundry. - [Get File Content - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/files/get-file-content): Get content of a specific file - [Clusters - TrueFoundry Docs](https://www.truefoundry.com/docs/truefoundry_sdk/clusters): SDK methods to list, get, create, and manage Kubernetes clusters registered with your TrueFoundry tenant. - [Get artifact - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/artifacts/get-artifact): Get an artifact by its ID. - [Deploy Programatically - TrueFoundry Docs](https://www.truefoundry.com/docs/deploy-service-programatically): Programmatically deploy services using TrueFoundry APIs and automation workflows. - [List prompt versions - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/prompts/list-prompt-versions): List prompt versions with optional filtering by tag, FQN, prompt ID, ML Repo, name, or version. - [Create or Update Cluster - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/clusters/create-or-update-cluster): Create or Update cluster with provided manifest - [Delete prompt - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/prompts/delete-prompt): Delete a prompt by its ID. - [Prompt Versions - TrueFoundry Docs](https://www.truefoundry.com/docs/truefoundry_sdk/prompt_versions): SDK methods to apply tags, get, list, and manage prompt versions for your TrueFoundry prompt library. - [Redeploy - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/applications/redeploy): Creates a new deployment with the same manifest as the given deployment. - [List artifact versions - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/artifacts/list-artifact-versions): List artifact versions with optional filtering by tag, FQN, artifact ID, ML Repo, name, version, run IDs, or run steps. - [Create Group - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/scim-v2/create-group): TrueFoundry offers an enterprise-grade AI Gateway combining LLM, MCP, and Agent Gateways—empowering businesses to connect, monitor, and govern agentic AI applications across providers from a unified control plane. - [Create or update model version - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/models/create-or-update-model-version): Create or update a model version. - [Image Edit API (/images/edits) - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/image-edit): Edit and transform images using text prompts via TrueFoundry AI Gateway - [Applications - TrueFoundry Docs](https://www.truefoundry.com/docs/truefoundry_sdk/applications): SDK methods to list, get, create, update, and delete TrueFoundry applications with filtering and pagination. - [Apply tags to artifact version - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/artifacts/apply-tags-to-artifact-version): Apply tags to an artifact version. - [List model versions - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/models/list-model-versions): List model versions with optional filtering by tag, FQN, model ID, ML Repo, name, version, run IDs, or run steps. - [List Files - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/files/list-files): List all files - [List files in artifact version - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/artifacts/list-files-in-artifact-version): List files and directories in an artifact version. - [Get Secret - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/secrets/get-secret): Get Secret associated with provided id. The secret value is not returned if the control plane has DISABLE_SECRET_VALUE_VIEW set - [Launch a SSH Server - TrueFoundry Docs](https://www.truefoundry.com/docs/launch-an-ssh-server): Launch an SSH server for debugging and secure access. - [Delete artifact version - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/artifacts/delete-artifact-version-1): Delete an artifact version by manifest. - [Creating A Conditional Task - TrueFoundry Docs](https://www.truefoundry.com/docs/conditional-task): Step-by-step guide for conditional task, explaining configuration, best practices, and real-world usage on TrueFoundry. - [Get File - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/files/get-file): Get information about a specific file - [Cost Tracking - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/cost-tracking): Set up and manage cost tracking for AI model usage with public and private pricing options. - [List MCP servers - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/mcp-servers/list-mcp-servers): Lists all MCP servers for the current tenant with pagination. - [Email Integration - TrueFoundry Docs](https://www.truefoundry.com/docs/email-integration): Set up email integrations for alerts and notifications in TrueFoundry. - [Mark stage failure - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/artifacts/mark-stage-failure): Mark a staged artifact version as failed. - [Create or Update Resources - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/apply/create-or-update-resources): Applies a given manifest to create or update resources of specific types, such as provider-account, cluster, workspace, or ml-repo. - [API Access to Logs - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/fetch-request-logs): Learn how to fetch Gateway request logs using the spans query API for different use cases. - [Creating A Cron Workflow - TrueFoundry Docs](https://www.truefoundry.com/docs/cron-workflow): Schedule recurring workflows with cron on TrueFoundry. Learn setup, timing options, retries, and best practices. - [API Access to Metrics - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/fetch-raw-metrics): Query Gateway model metrics for usage, cost, and performance analytics via API. - [Audit Logging - TrueFoundry Docs](https://www.truefoundry.com/docs/platform/audit-logging): Track and monitor all platform activities with comprehensive audit logs for security, compliance, and troubleshooting - [Create or Update Workspace - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/workspaces/create-or-update-workspace): Creates a new workspace or updates an existing one based on the provided manifest. - [Secret Groups - TrueFoundry Docs](https://www.truefoundry.com/docs/truefoundry_sdk/secret_groups): SDK methods to list, create, and manage secret groups and their associated secrets in TrueFoundry. - [GCP - TrueFoundry Docs](https://www.truefoundry.com/docs/integration-provider-gcp): Integrate GCP services into your TrueFoundry environment. - [Artifacts - TrueFoundry Docs](https://www.truefoundry.com/docs/truefoundry_sdk/artifacts): SDK methods to get, list, and manage artifact entities stored in TrueFoundry ML repository collections. - [Authenticate To AWS Services Using IAM Service Account - TrueFoundry Docs](https://www.truefoundry.com/docs/use-aws-services-using-iam-serviceaccount): Connect your TrueFoundry applications to AWS services from EKS using IAM roles and ServiceAccounts. - [Prompts - TrueFoundry Docs](https://www.truefoundry.com/docs/truefoundry_sdk/prompts): SDK methods to get, list, and manage prompt entities in your TrueFoundry prompt library. - [Environments - TrueFoundry Docs](https://www.truefoundry.com/docs/truefoundry_sdk/environments): SDK methods to list, create, and manage environments for organizing workspaces into dev, staging, and production. - [Remote Agents - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/agents/remote-agents): Register agents running on any platform — Bedrock, Vertex AI, LangGraph, or custom infrastructure — into a single control plane with RBAC, metrics, traces, and governance. - [Sticky Routing - TrueFoundry Docs](https://www.truefoundry.com/docs/sticky-routing): Pin user requests using consistent hash based routing - [Deactivate User - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/users/deactivate-user): Deactivate user associated with the provided email within the tenant. - [Check Virtual Account Exists - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/virtual-accounts/check-virtual-account-exists): Check whether a Virtual Account with the given name exists in the current tenant. - [Create or Update a Virtual Account - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/virtual-accounts/create-or-update-a-virtual-account): Creates a new virtual account or updates an existing one based on the provided manifest. - [Get Logs - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/logs/get-logs): Fetch logs for various workload components, including Services, Jobs, Workflows, Job Runs, and Pods. Logs are filtered based on the provided query parameters. - [Getting Started - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/mcp/mcp-server-getting-started): Learn how to create MCP Server Groups, add MCP servers, and use them in the TrueFoundry AI Gateway playground. - [Access Cloud Services Like S3 - TrueFoundry Docs](https://www.truefoundry.com/docs/access-data-from-s3-or-other-clouds-services): Guide to accessing S3 and cloud data sources from services deployed on TrueFoundry. - [Configure Data Access - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/data-access): Control who can access which request traces and metrics in the AI Gateway. - [List Workspace - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/workspaces/list-workspace): List workspaces associated with the user. Optional filters include clusterId, fqn, and workspace name. Pagination is available based on query parameters. - [Alerts - TrueFoundry Docs](https://www.truefoundry.com/docs/truefoundry_sdk/alerts): SDK methods to list and manage alerts for applications and clusters with timestamp-based filtering. - [Moderation API (/moderations) - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/moderation): Learn how to use the OpenAI Moderations API through TrueFoundry's AI Gateway to identify potentially harmful content in text and images. - [Get Workspace - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/workspaces/get-workspace): Get workspace associated with provided workspace id - [Delete MCP server by ID - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/mcp-servers/delete-mcp-server-by-id): Deletes an MCP server by its ID. - [List batches - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/batch/list-batches): List all batches - [Check user registration - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/users/check-user-registration): Check if a user is registered with the platform - [Create or update prompt version - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/prompts/create-or-update-prompt-version): Create or update a prompt version. - [Invite User - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/users/invite-user): Invite a user to the tenant - [Resume an Application - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/applications/resume-an-application): Resume a paused application by scaling back to the original number of replicas - [View Traces - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/request-logging): Control which requests are traced using headers or environment variables. - [Manage External Identity - TrueFoundry Docs](https://www.truefoundry.com/docs/external-identity): Bring your own Auth by setting up external identity for secure authentication and access control. - [Patch Group - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/scim-v2/patch-group): TrueFoundry offers an enterprise-grade AI Gateway combining LLM, MCP, and Agent Gateways—empowering businesses to connect, monitor, and govern agentic AI applications across providers from a unified control plane. - [Deploy Programatically - TrueFoundry Docs](https://www.truefoundry.com/docs/deploy-job-programatically): Deploy jobs programmatically using APIs. Automate job creation and execution. - [Virtual Accounts - TrueFoundry Docs](https://www.truefoundry.com/docs/truefoundry_sdk/virtual_accounts): SDK methods to list, create, and manage virtual accounts for programmatic access to TrueFoundry services. - [Get Group - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/scim-v2/get-group): TrueFoundry offers an enterprise-grade AI Gateway combining LLM, MCP, and Agent Gateways—empowering businesses to connect, monitor, and govern agentic AI applications across providers from a unified control plane. - [Authentication - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/authentication): Authenticate with the TrueFoundry AI Gateway using Personal Access Tokens (PATs) or Virtual Account Tokens (VATs). - [Model Responses - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/responses/model-responses): Generate model responses using the specified model. - [List Secret Groups - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/secret-groups/list-secret-groups): List the secret groups associated with a user along with the associated secrets for each group. Filtered with the options passed in the query fields. Note: This method does not return the secret values of the associatedSecrets in the response. A separate API call to /v1/secrets/{id} should be made to fetch the associated secret value. - [Delete prompt version - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/prompts/delete-prompt-version): Delete a prompt version by its ID. - [Content Moderation Guardrail - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/tfy-content-moderation): Detect and block harmful content in LLM inputs/outputs using TrueFoundry's built-in Content Moderation guardrail. - [List prompts - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/prompts/list-prompts): List prompts with optional filtering by FQN, ML Repo, or name. - [Change Password - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/users/change-password): Change password for the authenticated user. Requires clientId and loginId in the request body. - [Virtual MCP Server - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/mcp/virtual-mcp-server): Combine tools from multiple MCP servers into a single curated virtual MCP server without extra deployments. - [Update User Profile Picture - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/users/update-user-profile-picture): Update the profile picture URL for the authenticated user - [OpenAPI to MCP Server - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/mcp/openapi-mcp-server): Automatically generate MCP servers from your existing OpenAPI specifications to expose your APIs as AI-callable tools. - [Models and Model Versions - TrueFoundry Docs](https://www.truefoundry.com/docs/log-models): Uploading files and directories as Models. Downloading models to disk. - [Create Personal Access Token - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/personal-access-tokens/create-personal-access-token): Create Personal Access Token - [Get signed URLs for artifact version - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/artifacts/get-signed-urls-for-artifact-version): Get pre-signed URLs for reading or writing files in an artifact version. - [Delete file - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/files/delete-file): Deletes a specified file - [Logs - TrueFoundry Docs](https://www.truefoundry.com/docs/truefoundry_sdk/logs): SDK methods to fetch logs for services, jobs, workflows, and pods with timestamp-based filtering options. - [Configure Guardrails - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/guardrails-configuration): Learn how to create and configure guardrail rules to enforce security and compliance policies for LLM interactions and MCP tool invocations - [Apply tags to model version - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/models/apply-tags-to-model-version): Apply tags to a model version. - [Generate MCP tools from an OpenAPI specification - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/mcp-servers/generate-mcp-tools-from-an-openapi-specification): Returns MCP tool definitions from an OpenAPI specification. - [Task Config - TrueFoundry Docs](https://www.truefoundry.com/docs/task-config): Configure task settings including environment variables, resources, volume mounts, and service accounts for workflows. - [Cartesia - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/cartesia): Add and configure Cartesia Models in TrueFoundry's AI Gateway - [Traces - TrueFoundry Docs](https://www.truefoundry.com/docs/truefoundry_sdk/traces): SDK methods to query trace spans with time-range filtering for observability and debugging workflows. - [Bitbucket - TrueFoundry Docs](https://www.truefoundry.com/docs/bitbucket-integration-set-up): Create a Bitbucket OAuth Consumer app and configure the integration with TrueFoundry for repository access. - [Delete Secret - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/secrets/delete-secret): Deletes a secret and its versions along with its values. - [Use blob storage with your Spark job - TrueFoundry Docs](https://www.truefoundry.com/docs/deploy-a-spark-job-with-blob-storage): Run Spark jobs with blob storage. Configure data access, storage, and execution. - [Finetune API (/fine_tuning) - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/finetune): Fine-tune models using TrueFoundry's AI Gateway with OpenAI or Vertex AI providers - [Docker Build Secrets - TrueFoundry Docs](https://www.truefoundry.com/docs/docker-build-secrets): Securely pass sensitive information during Docker image builds without exposing them in image layers. - [Auth Overrides - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/mcp/mcp-server-auth-overrides): Replace a server's default credentials with user-specific tokens for MCP servers in TrueFoundry AI Gateway - [Delete model version - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/models/delete-model-version): Delete a model version by its ID. - [Azure - TrueFoundry Docs](https://www.truefoundry.com/docs/integration-provider-azure): Connect Azure services to TrueFoundry with secure configurations. - [Using MCP Gateway in Your Agent - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/mcp/use-mcp-gateway-in-agent): Learn how to integrate MCP servers into your agent with the right authentication approach for your use case. - [Get Schema - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/scim-v2/get-schema): TrueFoundry offers an enterprise-grade AI Gateway combining LLM, MCP, and Agent Gateways—empowering businesses to connect, monitor, and govern agentic AI applications across providers from a unified control plane. - [Regex Pattern Match Guardrail - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/regex-pattern-matching): Detect and redact sensitive patterns in LLM inputs/outputs and MCP tool invocations using TrueFoundry's built-in Regex Pattern Matching guardrail. - [Create Secret Group - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/secret-groups/create-secret-group): Creates a secret group with secrets in it. A secret version for each of the created secret is created with version number as 1. The returned secret group does not have any secret values in the associatedSecrets field. A separate API call to /v1/secrets/{id} should be made to fetch the associated secret value. - [Get Deployment Specifications - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/model-deployments/get-deployment-specifications): Fetches deployment specifications for a model version or a HuggingFace model URL. - [Check Personal Access Token Exists - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/personal-access-tokens/check-personal-access-token-exists): Check whether a Personal Access Token with the given name exists in the current tenant. - [Delete model version - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/models/delete-model-version-1): Delete a model version by manifest. - [List Associated Active Deployments - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/secrets/list-associated-active-deployments): List the active deployments that are associated with a secret. - [Compaction API (/responses/compact) - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/compaction): Learn how to use the Compaction API through TrueFoundry Gateway to manage long-running conversations by reducing context size while preserving state. - [Update User - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/scim-v2/update-user-1): TrueFoundry offers an enterprise-grade AI Gateway combining LLM, MCP, and Agent Gateways—empowering businesses to connect, monitor, and govern agentic AI applications across providers from a unified control plane. - [Get Cluster status - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/clusters/get-cluster-status): Get the status of provided cluster - [Recovering a Failed Workflow Execution - TrueFoundry Docs](https://www.truefoundry.com/docs/recovering-workflow-execution): Resume a failed workflow execution from the exact step where it failed. - [Terminate Job - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/jobs/terminate-job): Terminate Job for provided deploymentId and jobRunName - [Code Safety Linter Guardrail - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/code-safety-linter): Detect unsafe code patterns in LLM outputs using TrueFoundry's built-in Code Safety Linter guardrail. - [Delete Secret Group - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/secret-groups/delete-secret-group): Deletes the secret group, its associated secrets and secret versions of those secrets. - [Generate images from a prompt - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/image/generate-images-from-a-prompt): Creates an image given a prompt. - [Embeddings API (/embeddings) - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/embed): Generate vector embeddings through TrueFoundry's AI Gateway - [Get Application Resources - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/applications/get-application-resources): Retrieves the ArgoCD resources for the specified application. - [Create a Virtual Model - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/virtual-model-advanced): Step-by-step guide to creating virtual models, configuring targets, and using them in your application - [Get Batch - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/batch/get-batch): Get information about a specific batch process - [Events - TrueFoundry Docs](https://www.truefoundry.com/docs/truefoundry_sdk/events): SDK methods to retrieve Kubernetes and TrueFoundry events for pods, job runs, and application monitoring. - [Secret Management API - TrueFoundry Docs](https://www.truefoundry.com/docs/apply-api-secret-management): Create and manage secret groups using TrueFoundry REST API with examples for create, update, and search. - [Kustomize Support - TrueFoundry Docs](https://www.truefoundry.com/docs/kustomize): Use Kustomize to patch or add Kubernetes resources to your TrueFoundry deployment configurations. - [Delete Personal Access Token - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/personal-access-tokens/delete-personal-access-token): Delete Personal Access Token associated with the provided serviceAccountId - [Regenerate token for a virtual account - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/virtual-accounts/regenerate-token-for-a-virtual-account): Regenerate token for a virtual account by id. The old token will remain valid for the specified grace period. - [Creating A Workflow With Different Container Images - TrueFoundry Docs](https://www.truefoundry.com/docs/creating-a-workflow-with-gpu-and-non-gpu-image): Step-by-step guide for creating a workflow with gpu and non gpu image, explaining configuration, best practices, and real-world usage on… - [Overview - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/agents/agent-registry): The single place to build, register, discover, and govern every AI agent in your organization — whether built on TrueFoundry or running anywhere else. - [Globally Distributed SAAS Gateway - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/globally-distributed-saas): Learn about Truefoundry's globally distributed AI Gateway infrastructure deployed across multiple regions and cloud providers - [Delete a JWT for a virtual account - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/virtual-accounts/delete-a-jwt-for-a-virtual-account): Delete a JWT for a virtual account by id - [Edit images based on a prompt - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/image/edit-images-based-on-a-prompt): Edits an image given the original image and a prompt. - [Application Versions - TrueFoundry Docs](https://www.truefoundry.com/docs/truefoundry_sdk/application_versions): SDK methods to list and manage deployment versions for TrueFoundry applications with pagination support. - [Get Finetuning Specifications - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/model-deployments/get-finetuning-specifications): Fetches finetuning specifications for a model version or a HuggingFace model URL - [Sync application - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/applications/sync-application): Syncs the application for the specified application. - [Dockerize Your Code - TrueFoundry Docs](https://www.truefoundry.com/docs/dockerize-code): Learn how to dockerize your code for deployment on TrueFoundry. - [Delete Model Response - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/responses/delete-model-response): Delete a specific model response - [Parameterize A Job - TrueFoundry Docs](https://www.truefoundry.com/docs/deploy-a-job-with-additional-parameters): Deploy jobs with custom parameters. Learn flags, overrides, and runtime configuration. - [Get Batch Output - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/batch/get-batch-output): Get output of a specific batch process - [TrueFoundry Agents - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/agents/truefoundry-agents): Build, publish, and share AI agents natively on TrueFoundry with model selection, MCP tools, sandboxed execution, and built-in observability. - [Generate Embeddings - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/embeddings/generate-embeddings): Generate embeddings for the given input using the specified model. - [Delete Workspace - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/workspaces/delete-workspace): Deletes the workspace with the given workspace ID. - Removes the associated namespace from the cluster. - Deletes the corresponding authorization entry. - [Get User - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/scim-v2/get-user): TrueFoundry offers an enterprise-grade AI Gateway combining LLM, MCP, and Agent Gateways—empowering businesses to connect, monitor, and govern agentic AI applications across providers from a unified control plane. - [Get filtered spans data with detailed attributes - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/traces/get-filtered-spans-data-with-detailed-attributes): TrueFoundry offers an enterprise-grade AI Gateway combining LLM, MCP, and Agent Gateways—empowering businesses to connect, monitor, and govern agentic AI applications across providers from a unified control plane. - [Secrets - TrueFoundry Docs](https://www.truefoundry.com/docs/truefoundry_sdk/secrets): SDK methods to list, create, update, and manage secrets with filtering options in TrueFoundry. - [Get prompt - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/prompts/get-prompt): Get a prompt by its ID. - [Responses API (/responses) - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/responses-api): Learn how to use OpenAI's Responses API through TrueFoundry Gateway for creating, retrieving, and managing text and multimodal completions. - [Update User Roles - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/users/update-user-roles): This endpoint allows tenant administrators to update the roles of a user within their tenant. - [Mounting Volumes/Files - TrueFoundry Docs](https://www.truefoundry.com/docs/mounting-volumes-service): Mount volumes, secrets, or configuration strings to your services for persistent data and runtime settings. - [Deprecation of Common Tools in Playground and Settings — v0.135 - TrueFoundry Docs](https://www.truefoundry.com/docs/change-announcements/deprecation-of-common-tools-v0-135-0): Built-in common tools are deprecated from Playground and Settings in v0.135.0 and fully removed after 15 May 2026. - [List models - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/models/list-models): List models with optional filtering by FQN, ML Repo, name, or run ID. - [Get MCP server by name - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/mcp-servers/get-mcp-server-by-name): Retrieves a single MCP server by its name. - [Secrets Detection Guardrail - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/secrets-detection): Detect and redact sensitive credentials and secrets in LLM inputs/outputs and MCP tool invocations using TrueFoundry's built-in Secrets Detection guardrail. - [List Applications - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/applications/list-applications): Retrieves a list of all latest applications. Supports filtering by application ID, name, type, and other parameters. Pagination is available based on query parameters. - [Use Secret Manager in Integrations - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/secret-manager-in-ai-gateway): Store API keys and other sensitive credentials in Secret manager and reference them in Model, MCP server, and Guardrail integrations. - [List Schemas - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/scim-v2/list-schemas): TrueFoundry offers an enterprise-grade AI Gateway combining LLM, MCP, and Agent Gateways—empowering businesses to connect, monitor, and govern agentic AI applications across providers from a unified control plane. - [Get Team Permissions - TrueFoundry Docs](https://www.truefoundry.com/docs/api-reference/teams/get-team-permissions): Get all role bindings associated with a team. - [xAI - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/xai): Add and configure xAI (Grok) models in TrueFoundry's AI Gateway - [AWS Sagemaker - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/aws-sagemaker): Configure and use AWS Sagemaker models through TrueFoundry's AI Gateway - [Set Retries And Timeout - TrueFoundry Docs](https://www.truefoundry.com/docs/retries-and-timeout): Configure retry policies and timeout settings for jobs to improve reliability and manage compute resources. - [Control Plane Monitoring - TrueFoundry Docs](https://www.truefoundry.com/docs/platform/controlplane-monitoring): Monitor your self-hosted TrueFoundry control plane using Prometheus metrics and Grafana dashboards. - [Palo Alto Prisma AIRS Integration - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/palo-alto-airs): Learn how to use palo alto airs with TrueFoundry AI Gateway, including setup steps, use cases, and production-ready examples. - [External SSO (OIDC/SAML) - TrueFoundry Docs](https://www.truefoundry.com/docs/deploy-control-plane-with-external-oauth): Deploy the TrueFoundry Control Plane without TrueFoundry Auth Server using any external OIDC or SAML identity providers for authentication. - [AWS Bedrock - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/aws-bedrock): Configure and use AWS Bedrock models through TrueFoundry's AI Gateway with cross-region support - [Qwen Code CLI - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/qwen-cli): Use Qwen Code CLI with TrueFoundry AI Gateway to interact with AI models from your terminal - [Patronus AI Integration - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/patronus): Learn how to use patronus with TrueFoundry AI Gateway, including setup steps, use cases, and production-ready examples. - [Attaching Mounts - TrueFoundry Docs](https://www.truefoundry.com/docs/attaching-mounts): Step-by-step guide for attaching mounts, explaining configuration, best practices, and real-world usage on TrueFoundry. - [Making Your First Request - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/making-llm-requests-via-gateway): Get your Gateway Base URL, Model ID, and API key to start calling LLMs through the TrueFoundry AI Gateway. - [Legacy MCP OAuth Routes Removal — v0.134 - TrueFoundry Docs](https://www.truefoundry.com/docs/change-announcements/legacy-mcp-oauth-routes-removal): Legacy unscoped MCP OAuth routes are being removed in favor of scoped OAuth Protected Resource Metadata endpoints (RFC 9728). - [Log Feedback on requests - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/feedback-for-traces): Learn how to create, modify, and retrieve feedback for trace spans. - [User, Team, Account and Tenant Management - TrueFoundry Docs](https://www.truefoundry.com/docs/platform/user-team-account-management): A high level introduction to Truefoundry's account management hierarchy and key concepts. - [Together AI - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/together-ai): Learn how to add and configure Together AI models in TrueFoundry AI Gateway for seamless integration and inference. - [OpenAI Codex CLI - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/openai-codex-cli): Use OpenAI Codex CLI with TrueFoundry LLM Gateway to interact with AI models from your terminal - [Mounting Volumes - TrueFoundry Docs](https://www.truefoundry.com/docs/mounting-volumes-job): Mount persistent volumes to jobs for sharing data across training runs without re-downloading datasets. - [Langfuse - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/langfuse): Learn how to use langfuse with TrueFoundry AI Gateway, including setup steps, use cases, and production-ready examples. - [OIDC with Azure AD - TrueFoundry Docs](https://www.truefoundry.com/docs/openid-connect-with-azure-ad): Configure OpenID Connect with Azure AD or Microsoft Entra ID for single sign-on access to TrueFoundry. - [Truefoundry Compute Plane Architecture - TrueFoundry Docs](https://www.truefoundry.com/docs/platform/compute-plane-architecture): Architecture of the TrueFoundry Compute Plane which handles all the models, services, jobs and pipelines deployed by the users. - [Cluster migration with Velero - TrueFoundry Docs](https://www.truefoundry.com/docs/cluster-migration-with-velero): Move a TrueFoundry-connected Kubernetes cluster to a new cluster using Velero backups. - [Azure Prompt Shield Guardrail Integration - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/azure-prompt-shield): Configure Azure Prompt Shield with the TrueFoundry AI Gateway for jailbreak and prompt injection detection. - [OIDC with Okta - TrueFoundry Docs](https://www.truefoundry.com/docs/openid-connect-with-okta): Configure OpenID Connect with Okta to enable single sign-on for TrueFoundry dashboard access. - [Artifact - TrueFoundry Docs](https://www.truefoundry.com/docs/artifact): Step-by-step guide for artifact, explaining configuration, best practices, and real-world usage on TrueFoundry. - [GraySwan Cygnal Integration - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/grayswan-cygnal): Learn how to use GraySwan Cygnal with TrueFoundry AI Gateway for policy violation detection and content safety monitoring. - [Configure Queue - TrueFoundry Docs](https://www.truefoundry.com/docs/configure-queue): Step-by-step guide for configure queue, explaining configuration, best practices, and real-world usage on TrueFoundry. - [truefoundry.ml.MlFoundryRun - TrueFoundry Docs](https://www.truefoundry.com/docs/truefoundry-ml-reference/runs): Python SDK reference for ML run management including properties like dashboard link, FQN, and run status. - [Deploy Gateway Plane - TrueFoundry Docs](https://www.truefoundry.com/docs/platform/deploy-gateway-plane): Installation guide of deploying the gateway plane on your own infrastructure. - [Logging Data in Job Runs - TrueFoundry Docs](https://www.truefoundry.com/docs/job-runs-and-logging): Track job runs and view logs for debugging and monitoring. - [Models - TrueFoundry Docs](https://www.truefoundry.com/docs/models): Python SDK reference for the ModelVersion class including properties like FQN, metadata, metrics, and parameters. - [Post Cluster Configurations - TrueFoundry Docs](https://www.truefoundry.com/docs/post-cluster-configurations): Complete post-cluster setup steps including DNS record creation and blob storage attachment for TrueFoundry. - [Access Data From S3 Or Other Clouds - TrueFoundry Docs](https://www.truefoundry.com/docs/access-data-from-s3-or-other-clouds-jobs): Learn how to access data from S3 and other cloud storage in batch jobs on TrueFoundry. - [Autoscaling - TrueFoundry Docs](https://www.truefoundry.com/docs/autoscaling): Step-by-step guide for autoscaling, explaining configuration, best practices, and real-world usage on TrueFoundry. - [SambaNova - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/sambanova): Add and configure SambaNova models through TrueFoundry's AI Gateway - [Create Calculator MCP Server - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/mcp/create-calculator-mcp-server): Learn how to build a simple calculator MCP server that provides basic math operations using FastMCP. - [Roo Code - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/roo-code): Learn how to use roo code with TrueFoundry AI Gateway, including setup steps, use cases, and production-ready examples. - [Cost Monitoring - TrueFoundry Docs](https://www.truefoundry.com/docs/cost-monitoring): Step-by-step guide for cost monitoring, explaining configuration, best practices, and real-world usage on TrueFoundry. - [Passing Files/Artifacts Between Tasks - TrueFoundry Docs](https://www.truefoundry.com/docs/passing-filesartifacts-between-tasks): Use FlyteFile and FlyteDirectory to pass files and directories between tasks in TrueFoundry workflows. - [OIDC with Keycloak - TrueFoundry Docs](https://www.truefoundry.com/docs/openid-connect-with-keycloak): Register a Keycloak client and integrate it with TrueFoundry for OpenID Connect based authentication. - [Cline - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/cline): Documentation for using Cline with the TrueFoundry AI Gateway. - [Model Discovery - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/model-discovery): Use the /models API to programmatically list all available models in your TrueFoundry AI Gateway. - [Google Vertex - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/google-vertex): Add and configure Google Vertex AI models including Gemini, Anthropic, and Mistral in TrueFoundry's AI Gateway - [Running Workflow Locally - TrueFoundry Docs](https://www.truefoundry.com/docs/running-workflow-locally): Run TrueFoundry workflows locally for rapid testing and debugging before deploying to the platform. - [GCP - TrueFoundry Docs](https://www.truefoundry.com/docs/infrastructure/gcp-compute-plane-setup): This page provides an overview of the architecture, requirements and steps to install the TrueFoundry compute plane cluster in GCP - [MlFlow - TrueFoundry Docs](https://www.truefoundry.com/docs/model-deployment/deploy-model-mlflow): Deploy MLflow models on TrueFoundry with examples for Scikit-Learn, Transformers, and custom PyFunc models. - [Native SDK Support - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/native-sdk-support): Use OpenAI, Google Gen AI, Anthropic, and boto3 SDKs with the TrueFoundry AI Gateway - [Truefoundry Control Plane - TrueFoundry Docs](https://www.truefoundry.com/docs/platform/control-plane-architecture): Architecture of the TrueFoundry Control Plane which is the brain of the Truefoundry platform. - [Fiddler Integration - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/fiddler): Learn how to use fiddler with TrueFoundry AI Gateway, including setup steps, use cases, and production-ready examples. - [Mistral AI - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/mistral): Add and configure Mistral AI models in TrueFoundry's AI Gateway - [AWS Multi-Model Server - TrueFoundry Docs](https://www.truefoundry.com/docs/model-deployment/deploy-model-mms): Deploying sample MNIST model with AWS Multi-Model Server - [Configure Sidecar - TrueFoundry Docs](https://www.truefoundry.com/docs/configure-sidecar): Step-by-step guide for configure sidecar, explaining configuration, best practices, and real-world usage on TrueFoundry. - [Dynatrace - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/dynatrace): Learn how to export LLM Gateway traces to Dynatrace using OpenTelemetry OTLP integration. - [Handling Failure using Failure Task/Node - TrueFoundry Docs](https://www.truefoundry.com/docs/handling-workflow-failure): Handle workflow failures gracefully using retries, alerts, and recovery steps. - [OpenRouter - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/openrouter): Add and configure OpenRouter models in TrueFoundry's AI Gateway - [SAML V2 With Azure AD - TrueFoundry Docs](https://www.truefoundry.com/docs/saml-v2-with-azure-ad): Configure SAML v2 authentication with Azure AD to enable enterprise single sign-on for TrueFoundry. - [Overview - TrueFoundry Docs](https://www.truefoundry.com/docs/tracing/overview): Overview of LLM tracing concepts including traces, spans, and attributes for observability in AI applications. - [Braintrust - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/braintrust): Guide to integrating Braintrust with the TrueFoundry AI Gateway. - [Installation and Deployment Overview - TrueFoundry Docs](https://www.truefoundry.com/docs/platform/deployment-overview): Description of the different deployment options for Truefoundry. - [Goose - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/goose): Learn how to use goose with TrueFoundry AI Gateway, including setup steps, use cases, and production-ready examples. - [Monitor Your Job - TrueFoundry Docs](https://www.truefoundry.com/docs/monitor-your-job): Monitor job execution using real-time logs, metrics dashboards, and events in the TrueFoundry platform. - [Azure OpenAI - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/azure-openai): Add and configure Azure OpenAI models through TrueFoundry's AI Gateway - [Gemini CLI Model Registration Requirement — v0.118 - TrueFoundry Docs](https://www.truefoundry.com/docs/change-announcements/gemini-cli-model-registration-v0.118): From v0.118.1, all Gemini CLI models must be registered in the TrueFoundry Gateway for cost calculation and attribution. - [CrowdStrike Integration - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/crowstrike): Learn how to use CrowdStrike (formerly Pangea) with TrueFoundry AI Gateway, including setup steps, use cases, and production-ready examples. - [Enkrypt AI Guardrail Integration - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/enkrypt-ai): Learn how to use enkrypt ai with TrueFoundry AI Gateway, including setup steps, use cases, and production-ready examples. - [Akto Integration - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/akto): Learn how to use Akto with TrueFoundry AI Gateway for LLM security, prompt injection detection, and policy violation monitoring. - [Manage Teams - TrueFoundry Docs](https://www.truefoundry.com/docs/platform/team-management): Detailed guide to how to add, manage and delete teams in Truefoundry - [Prometheus Grafana Integration - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/prometheus-grafana-integration): Learn how to monitor your TrueFoundry AI Gateway using Prometheus metrics and Grafana dashboards for performance, cost, and usage insights. - [Set Concurrency Limit - TrueFoundry Docs](https://www.truefoundry.com/docs/concurrency-limits): Step-by-step guide for concurrency limits, explaining configuration, best practices, and real-world usage on TrueFoundry. - [OpenAI - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/openai): Add and configure OpenAI models in TrueFoundry's AI Gateway - [Cursor - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/cursor): Set up Cursor with the TrueFoundry AI Gateway for AI-powered development. - [GitHub Copilot - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/github-copilot): Route GitHub Copilot requests through TrueFoundry AI Gateway for observability, governance, and custom model access. - [AI21 - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/ai21): Add and configure AI21 language models in TrueFoundry's AI Gateway - [AWS Bedrock Guardrail Integration - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/bedrock-guardrails): Learn how to use Amazon Bedrock guardrails via the TrueFoundry AI Gateway. - [OpenAI Moderation Integration - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/openai-moderations): Learn how to use openai moderations with TrueFoundry AI Gateway, including setup steps, use cases, and production-ready examples. - [Interacting With Your Job - TrueFoundry Docs](https://www.truefoundry.com/docs/interacting-with-your-job): Interact with running jobs. Logs, status, retries, and controls. - [Routing Config - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/load-balancing-configuration): Global YAML-based routing configuration for TrueFoundry AI Gateway - [Cloudera - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/cloudera): Add and configure Cloudera models in TrueFoundry's AI Gateway - [Using Dockerfile For Python Function Task - TrueFoundry Docs](https://www.truefoundry.com/docs/python-function-tasks-with-dockefile): Use a custom Dockerfile with Python function tasks in TrueFoundry workflows to install extra dependencies. - [MCP Server Groups Removal — v0.112 - TrueFoundry Docs](https://www.truefoundry.com/docs/change-announcements/mcp-server-groups-removal-v0.112): MCP Server Groups are removed from v0.112. MCP Servers are now standalone, top-level resources with simplified management. - [FastAPI - TrueFoundry Docs](https://www.truefoundry.com/docs/model-deployment/deploy-model-fastapi): Deploy a scikit-learn iris classification model as a FastAPI service on TrueFoundry step by step. - [Open WebUI - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/open-webui): Learn how to use open webui with TrueFoundry AI Gateway, including setup steps, use cases, and production-ready examples. - [Example Of Task Config With Different Parameters - TrueFoundry Docs](https://www.truefoundry.com/docs/example-of-task-config-with-different-parameters): See task config examples with different parameters and execution options. - [Claude Code Max - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/claude-code-max): How to connect Claude Code Max with the TrueFoundry AI Gateway. - [Manage Users - TrueFoundry Docs](https://www.truefoundry.com/docs/platform/user-management): Detailed guide to how to add, manage and delete users in Truefoundry - [Azure Entra ID Certificate Based Authentication - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/azure-entra-certificate-auth): Configure certificate-based authentication for Azure OpenAI, Azure AI Foundry models, and Azure guardrails (PII, Content Safety, Prompt Shield) - [Azure PII Guardrail Integration - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/azure-pii): Set up Azure PII detection and redaction using the TrueFoundry AI Gateway. - [HuggingFace - TrueFoundry Docs](https://www.truefoundry.com/docs/model-deployment/deploy-model-from-huggingface): Deploying any model from HuggingFace Hub using optimized model servers - [Truefoundry.Ml - TrueFoundry Docs](https://www.truefoundry.com/docs/mlfoundry): Python SDK reference for the TrueFoundry.ml module including get_client, MlFoundry class, and data directory methods. - [TensorFlow Serve (TFServe) - TrueFoundry Docs](https://www.truefoundry.com/docs/model-deployment/deploy-tfserve): Deploying sample MNIST model with TensorFlow Serve - [Last9 - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/last9): Learn how to export LLM Gateway traces to Last9 using OpenTelemetry integration. - [LoadBalancer/Ingress - TrueFoundry Docs](https://www.truefoundry.com/docs/loadbalancers): Set up load balancers to distribute traffic efficiently. - [Google Gemini - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/google-gemini): Add and configure Google Gemini models in TrueFoundry's AI Gateway - [Groq - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/groq): Add and configure Groq models in TrueFoundry's AI Gateway for high-performance inference - [x-tfy-routing-config Header Removal — v0.133 - TrueFoundry Docs](https://www.truefoundry.com/docs/change-announcements/routing-config-header-removal-v0.133): The x-tfy-routing-config request header is retired from AI Gateway in v0.133. Migrate routing logic to Virtual Models. - [TorchServe - TrueFoundry Docs](https://www.truefoundry.com/docs/model-deployment/deploy-torchserve): Deploy a sample MNIST model using TorchServe on TrueFoundry with Docker-based configuration. - [LangSmith - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/langsmith): Learn how to export LLM Gateway traces to LangSmith using OpenTelemetry integration. - [Request Headers & Metadata - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/request-headers): Configure request headers for authentication, metadata tagging, logging, retries, and timeouts in the AI Gateway. - [Manage Virtual Accounts - TrueFoundry Docs](https://www.truefoundry.com/docs/platform/virtual-account-management): Detailed guide to how to add, manage and delete Virtual Accounts in Truefoundry - [truefoundry.ml - TrueFoundry Docs](https://www.truefoundry.com/docs/truefoundry-ml-reference/truefoundry-ml): Complete reference for the truefoundry.ml module including get_client, data classes, and logging functions. - [Cohere - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/cohere): Add and configure Cohere models in TrueFoundry's AI Gateway - [Perplexity AI - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/perplexity-ai): Add and configure Google Perplexity models in TrueFoundry's AI Gateway. - [Adding Retries And Handling Failures - TrueFoundry Docs](https://www.truefoundry.com/docs/adding-retries-and-handling-failures): Learn how to configure retries and handle failures in production workflows. - [Azure Foundry - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/azure-ai-foundry): Add and configure Azure AI Foundry models in TrueFoundry's AI Gateway - [Using TPUs - TrueFoundry Docs](https://www.truefoundry.com/docs/using-tpus): Deploy apps on Single Host TPU v4, v5e, v5p slices - [Using Fractional GPUs - TrueFoundry Docs](https://www.truefoundry.com/docs/using-fractional-gpus): Share a single GPU across multiple workloads using Nvidia MIG and TimeSlicing for cost-efficient deployments. - [Coralogix - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/coralogix): Learn how to export LLM Gateway traces to Coralogix using OpenTelemetry integration. - [Adding Alerts For Workflow - TrueFoundry Docs](https://www.truefoundry.com/docs/adding-alerts-for-workflow): Learn how to add alerts for workflows to track execution and failures. - [Cerebras - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/cerebras): Add and configure Cerebras models through TrueFoundry's AI Gateway - [Guardrails YAML Schema Change — v0.116 - TrueFoundry Docs](https://www.truefoundry.com/docs/change-announcements/guardrails-yaml-schema-change-v0.116): MCP Guardrails feature launched in v0.116 introduces breaking changes to the guardrails YAML schema for GitOps users. - [Session Management - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/session-management): Track and manage multi-turn conversations in TrueFoundry AI Gateway. - [Add Alerts To Your Job - TrueFoundry Docs](https://www.truefoundry.com/docs/add-alerts-to-your-job): Step-by-step guide to adding alerts for jobs to monitor failures and performance. - [OpenAI Swarm - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/openai-swarm): Learn how to use openai swarm with TrueFoundry AI Gateway, including setup steps, use cases, and production-ready examples. - [Deploy Compute Plane - TrueFoundry Docs](https://www.truefoundry.com/docs/infrastructure/deploy-compute-plane): Connect Kubernetes Cluster in your cloud account to TrueFoundry Control Plane - [Adding Environment Variable - TrueFoundry Docs](https://www.truefoundry.com/docs/adding-environment-variable): How to add and manage environment variables for jobs and services on TrueFoundry. - [Configuring Resources - TrueFoundry Docs](https://www.truefoundry.com/docs/configuring-resources): Step-by-step guide for configuring resources, explaining configuration, best practices, and real-world usage on TrueFoundry. - [Deepinfra - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/deepinfra): Add and configure Deepinfra models in TrueFoundry's AI Gateway - [Azure Content Safety Guardrail Integration - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/azure-content-safety): Configure Azure Content Safety with the TrueFoundry AI Gateway. - [LitServe - TrueFoundry Docs](https://www.truefoundry.com/docs/model-deployment/deploy-litserve): Deploying sample Whisper Speech to Text model with LitServe - [Anthropic - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/anthropic): Add and configure Anthropic's Claude models in TrueFoundry's AI Gateway - [Scikit Learn / XGBoost - TrueFoundry Docs](https://www.truefoundry.com/docs/model-deployment/deploy-sklearn-xgboost): Deploying Scikit Learn and XGBoost models with FastAPI or PyTriton - [Elastic - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/elastic): Learn how to export LLM Gateway traces to Elastic Cloud using OpenTelemetry integration. - [Deploy AI Gateway - TrueFoundry Docs](https://www.truefoundry.com/docs/platform/deploy-control-plane-and-gateway-plane): Learn how to deploy TrueFoundry's AI Gateway on your own infrastructure with detailed compute requirements and installation instructions. - [Snowflake Cortex - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/snowflake-cortex): Add and configure Cortex models through TrueFoundry's AI Gateway - [OPA Guardrails - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/opa-guardrails): Learn how to use Open Policy Agent (OPA) to create flexible, policy-driven guardrails for LLM inputs, outputs, and MCP tool invocations - [New Relic - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/newrelic): Learn how to export LLM Gateway traces to New Relic using OpenTelemetry integration. - [Setting up Azure Entra ID OAuth2 Authentication for MCP Servers - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/mcp/mcp-server-oauth-azure): Learn how to create and deploy an OAuth2-authenticated MCP server using Azure Entra ID and fastMCP, then integrate it with TrueFoundry AI Gateway. - [OpenCode - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/opencode): Learn how to integrate OpenCode with TrueFoundry AI Gateway for secure, governed AI-powered coding in the terminal, desktop, or IDE. - [Langflow - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/langflow): Learn how to use langflow with TrueFoundry AI Gateway, including setup steps, use cases, and production-ready examples. - [LangChain - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/langchain): Learn how to use langchain with TrueFoundry AI Gateway, including setup steps, use cases, and production-ready examples. - [Deploy And Run Job Using Python SDK - TrueFoundry Docs](https://www.truefoundry.com/docs/deploy-job-using-python-sdk): Use the Python SDK to deploy jobs on TrueFoundry. Code-driven deployments made easy. - [Deploy Control Plane and Compute Plane - TrueFoundry Docs](https://www.truefoundry.com/docs/deploy-control-and-compute-plane): Deploy TrueFoundry Control Plane and Compute Plane in your own infrastructure - [Langroid - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/langroid): Learn how to use langroid with TrueFoundry AI Gateway, including setup steps, use cases, and production-ready examples. - [Phidata - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/phidata): Learn how to use phidata with TrueFoundry AI Gateway, including setup steps, use cases, and production-ready examples. - [Agno AI - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/agno): Documentation on integrating Agno with the TrueFoundry AI Gateway. - [Choosing an Azure Resource Type - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/azure-models-guide): Understand Azure OpenAI vs Azure AI Foundry and choose the right integration for TrueFoundry's AI Gateway - [n8n - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/n8n): Learn how to use n8n with TrueFoundry AI Gateway, including setup steps, use cases, and production-ready examples. - [Azure - TrueFoundry Docs](https://www.truefoundry.com/docs/infrastructure/azure-compute-plane-setup): This page provides an overview of the architecture, requirements and steps to install the TrueFoundry compute plane cluster in Azure - [LiveKit - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/livekit): Learn how to use livekit with TrueFoundry AI Gateway, including setup steps, use cases, and production-ready examples. - [Instructor - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/instructor): Learn how to use instructor with TrueFoundry AI Gateway, including setup steps, use cases, and production-ready examples. - [Flowise - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/flowise): Learn how to use flowise with TrueFoundry AI Gateway, including setup steps, use cases, and production-ready examples. - [Generic - TrueFoundry Docs](https://www.truefoundry.com/docs/infrastructure/generic-compute-plane-setup): This page provides an overview of the architecture, requirements and steps to install the TrueFoundry compute plane cluster in your generic cluster - [OpenAI Agents SDK - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/openai-agents-sdk): Learn how to use openai agents sdk with TrueFoundry AI Gateway, including setup steps, use cases, and production-ready examples. - [Dify - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/dify): Guide to integrating Dify with the TrueFoundry AI Gateway. - [Pydantic AI - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/pydantic-ai): Learn how to use pydantic ai with TrueFoundry AI Gateway, including setup steps, use cases, and production-ready examples. - [Jan AI - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/jan): Learn how to use jan with TrueFoundry AI Gateway, including setup steps, use cases, and production-ready examples. - [LibreChat - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/librechat): Learn how to use librechat with TrueFoundry AI Gateway, including setup steps, use cases, and production-ready examples. - [Add TLS Certificates - TrueFoundry Docs](https://www.truefoundry.com/docs/add-certificate-for-tls): Configure secure HTTPS access to your TrueFoundry deployment - [AnythingLLM - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/anythingllm): Learn how to connect AnythingLLM with the TrueFoundry AI Gateway. - [Strands Agents - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/strands): Learn how to use strands with TrueFoundry AI Gateway, including setup steps, use cases, and production-ready examples. - [Customizing CI/CD Templates - TrueFoundry Docs](https://www.truefoundry.com/docs/customizing-cicd-templates): Learn how to customize CI/CD templates on TrueFoundry for faster, consistent deployments. - [DSPy - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/dspy): Learn how to use dspy with TrueFoundry AI Gateway, including setup steps, use cases, and production-ready examples. - [AWS - TrueFoundry Docs](https://www.truefoundry.com/docs/infrastructure/aws-compute-plane-setup): This page provides an architecture overview, requirements and steps to setup a TrueFoundry compute plane cluster in AWS - [CrewAI - TrueFoundry Docs](https://www.truefoundry.com/docs/ai-gateway/crewai): Learn how to deploy CrewAI agents using the TrueFoundry AI Gateway. - [Customize Build Workflow - TrueFoundry Docs](https://www.truefoundry.com/docs/customize-build-workflow): Inject custom logic into TrueFoundry's image build pipeline for services, jobs, and workflows. Run scripts before, during, or after the build and push steps. - [Install Helm Chart - TrueFoundry Docs](https://www.truefoundry.com/docs/installing-control-plane-using-helm-chart): Guide to install and customize the control-plane helm chart - [Azure - TrueFoundry Docs](https://www.truefoundry.com/docs/azure-control-plane): Provisioning Control Plane Infrastructure on Azure - [AWS - TrueFoundry Docs](https://www.truefoundry.com/docs/aws-control-plane): This page provides an architecture overview, requirements and steps to setup a TrueFoundry control plane cluster in AWS. - [GCP - TrueFoundry Docs](https://www.truefoundry.com/docs/gcp-control-plane): Provision TrueFoundry control plane infrastructure on Google Cloud Platform using OpenTofu or Terraform. - [Deploy Generic Control Plane - TrueFoundry Docs](https://www.truefoundry.com/docs/generic-control-plane): Learn how to deploy TrueFoundry's Control Plane on your generic Kubernetes cluster with detailed compute requirements and installation instructions. --- ## Industries and solutions we serve - [GenAI for Enterprise Application Suites | TrueFoundry Platform](https://www.truefoundry.com/solutions/application-suites): Deploy scalable AI apps seamlessly with TrueFoundry’s AI Gateway — a platform enabling organization-wide intelligence and automation. - [GenAI and AI Gateway for Insurance | TrueFoundry Platform](https://www.truefoundry.com/solutions/insurance): Automate claims and underwriting with TrueFoundry’s AI Gateway — a platform driving faster insights, risk analysis, and personalized policies. - [GenAI for Communications, Media & Services | TrueFoundry](https://www.truefoundry.com/solutions/media-and-communication): Improve service quality and personalization with TrueFoundry’s AI Gateway — a platform built for telcos and media organizations driving intelligent engagement - [AI/ML leaders](https://www.truefoundry.com/solutions/aimlleaders): Discover how AI and ML leaders use TrueFoundry to scale teams, accelerate delivery, and run reliable AI systems. - [GenAI for HR & Recruiting Teams | TrueFoundry Platform](https://www.truefoundry.com/solutions/human-resources-and-recruiting): Enhance talent acquisition and employee experience using TrueFoundry’s AI Gateway — a platform enabling smarter workforce operations. - [GenAI for Finance Teams | TrueFoundry Platform](https://www.truefoundry.com/solutions/finance): Increase accuracy, compliance, and reporting automation with TrueFoundry’s AI Gateway — a platform designed for finance digital transformation. - [GenAI and AI Gateway for Marketing teams | TrueFoundry Platform](https://www.truefoundry.com/solutions/marketing): Personalize journeys and boost campaign ROI with TrueFoundry’s AI Gateway — a platform for real-time insights and marketing intelligence. - [GenAI for the Digital Workplace | TrueFoundry Platform](https://www.truefoundry.com/solutions/digital-workplace): Boost productivity and collaboration with TrueFoundry’s AI Gateway — a platform empowering AI copilots across daily workflows. - [GenAI for Power & Utilities | TrueFoundry Platform](https://www.truefoundry.com/solutions/power-and-utilities): Modernize grid management and asset performance using TrueFoundry’s AI Gateway — a platform built for resilient energy operations. - [GenAI and AI Gateway for Education | TrueFoundry Platform](https://www.truefoundry.com/solutions/education): Enhance student outcomes and efficiency with TrueFoundry’s AI Gateway — a platform powering intelligent learning, analytics, and administrative automation. - [GenAI and AI Gateway for Government Offices | TrueFoundry Platform](https://www.truefoundry.com/solutions/government): Enhance citizen services and digital trust through TrueFoundry’s AI Gateway — a secure platform for modernization in the public sector. - [GenAI for Healthcare & Life Sciences | TrueFoundry Platform](https://www.truefoundry.com/solutions/healthcare-life-sciences): Accelerate clinical innovation and operational precision with TrueFoundry’s AI Gateway — a compliant platform for providers and life sciences leaders. - [GenAI and AI Gateway for IT Operations | TrueFoundry Platform](https://www.truefoundry.com/solutions/it-operations): Proactively manage systems and reliability using TrueFoundry’s AI Gateway — a platform enabling automated IT observability and remediation. - [GenAI for Sales & Lead Management | TrueFoundry Platform](https://www.truefoundry.com/solutions/sales-and-lead-management): Accelerate deal cycles with TrueFoundry’s AI Gateway — a platform improving lead qualification, forecasting, and revenue analytics. - [GenAI for Security and Compliance | TrueFoundry Platform](https://www.truefoundry.com/solutions/security-and-compliance): Strengthen threat detection and governance via TrueFoundry’s AI Gateway — a secure enterprise AI platform with built-in compliance. - [GenAI for Customer Support & CRM | TrueFoundry Platform](https://www.truefoundry.com/solutions/customer-support-crm): Improve resolution speed and personalization using TrueFoundry’s AI Gateway — a platform that integrates AI copilots into every customer interaction. - [GenAI for Banking & Investment Services | TrueFoundry](https://www.truefoundry.com/solutions/banking-and-financial-services): Transform financial operations with TrueFoundry’s AI Gateway — a secure and scalable platform for fraud prevention, automation, and smarter decisioning in banking and investment services. - [GenAI and AI Gateway for Retail | TrueFoundry Platform](https://www.truefoundry.com/solutions/retail): Optimize merchandising, forecasting, and CX with TrueFoundry’s AI Gateway — a platform supporting smarter commerce and shopper personalization. - [GenAI for Technology Companies | TrueFoundry Platform](https://www.truefoundry.com/solutions/technology): Drive productivity and innovation using TrueFoundry’s AI Gateway — a platform enabling scalable AI across engineering and product functions. - [GenAI for Oil & Gas Companies | TrueFoundry Platform](https://www.truefoundry.com/solutions/oil-and-gas): Improve production reliability and safety with TrueFoundry’s AI Gateway — an intelligence-driven platform for the energy sector.