# LLMGrid.ai > LLMGrid — SaaS LLM Gateway with unified API, routing, observability, governance, and enterprise compliance ## Docs - [Console Navigation](https://docs.llmgrid.ai/guides/administration/Navigation.md): Understand the LLMGrid console sidebar and where to find key features. - [Sign in to LLMGrid](https://docs.llmgrid.ai/guides/administration/Signin.md): Access your LLMGrid workspace using email/password or supported SSO providers. - [Agents](https://docs.llmgrid.ai/guides/administration/agents.md): Create, configure, and manage agents with skills, capabilities, and publishing controls. - [AI Hub](https://docs.llmgrid.ai/guides/administration/aihub.md): Publish models, agents, and MCP servers to a public hub so developers can discover what is available. - [API Playground](https://docs.llmgrid.ai/guides/administration/api-playground.md): Configure routing strategies, fallbacks, retries, and reliability behavior for model requests. - [API Reference](https://docs.llmgrid.ai/guides/administration/api-reference.md): Reference documentation for using the OpenAI‑compatible proxy with LLMGrid. - [Billing & Subscriptions](https://docs.llmgrid.ai/guides/administration/billing.md): Manage your subscription plan, billing preferences, and available add-ons. - [Budgets](https://docs.llmgrid.ai/guides/administration/budgets.md): Create, manage, and assign budgets to control usage limits and request rates. - [Caching](https://docs.llmgrid.ai/guides/administration/caching.md): Configure, monitor, and validate response caching to improve performance and efficiency. - [Cost Tracking](https://docs.llmgrid.ai/guides/administration/cost-tracking.md): Configure cost calculations, apply provider discounts, and validate effective usage costs across the platform. - [Usage Dashboard](https://docs.llmgrid.ai/guides/administration/dashboard.md): Detailed visibility into usage, cost, tokens, and activity across tenants, teams, keys, models, and agents. - [FAQs](https://docs.llmgrid.ai/guides/administration/faqs.md): Frequently asked questions about LLMGrid features, usage, security, and operations. - [Guardrails](https://docs.llmgrid.ai/guides/administration/guardrails.md): Configure, apply, and monitor guardrails to govern model inputs, outputs, and tool execution across the platform. - [Request Logs](https://docs.llmgrid.ai/guides/administration/logs.md): Inspect, filter, and analyze individual API requests, responses, and execution details. - [MCP Servers](https://docs.llmgrid.ai/guides/administration/mcpserver.md): Configure and manage MCP servers to enable tool-based interactions for models and agents. - [Observability](https://docs.llmgrid.ai/guides/administration/observability.md): Monitor, analyze, and audit platform activity using logs, metrics, analytics, and alerts. - [Organizations](https://docs.llmgrid.ai/guides/administration/organizations.md): Create and manage organizations to segment access, enforce budgets and limits, and govern model usage at scale. - [Playground](https://docs.llmgrid.ai/guides/administration/playground.md): Interactively test models, routes, tools, guardrails, and data sources before production use. - [Prompts](https://docs.llmgrid.ai/guides/administration/prompts.md): Create, version, test, and reuse prompts with template variables, tools, and model parameters. - [Search Tools](https://docs.llmgrid.ai/guides/administration/search.md): Configure and manage search providers that can be used by models and agents for retrieval and grounding. - [Security & Compliance](https://docs.llmgrid.ai/guides/administration/security-complience.md): Understand the security, compliance, and governance features available in LLMGrid and how they are managed. - [Tag Management](https://docs.llmgrid.ai/guides/administration/tag-management.md): Create and manage tags to control model access, apply budgets, and support routing and cost attribution. - [Teams](https://docs.llmgrid.ai/guides/administration/teams.md): Create and manage teams, control access to models, and apply budgets and limits at the team level. - [Tenant Selection](https://docs.llmgrid.ai/guides/administration/tenent.md): LLMGrid supports a multi‑tenant model, where a single user account can belong to multiple tenants. - [Router Settings](https://docs.llmgrid.ai/guides/administration/untitled-page-2.md): Configure routing strategies, fallbacks, retries, and reliability behavior for model requests. - [Internal Users](https://docs.llmgrid.ai/guides/administration/users.md): Invite, manage, and govern internal users, roles, budgets, and key ownership across the tenant. - [Vector Stores](https://docs.llmgrid.ai/guides/administration/vector.md): Create, manage, and test vector stores used for storing and retrieving embeddings in retrieval‑augmented workflows. - [Virtual Keys](https://docs.llmgrid.ai/guides/administration/virtualkeys.md): Create, manage, and govern API keys with fine-grained controls for access, limits, routing, and logging. - [cURL](https://docs.llmgrid.ai/guides/developer-docs/c-url.md) - [LangChain](https://docs.llmgrid.ai/guides/developer-docs/lang-chain.md) - [LlamaIndex](https://docs.llmgrid.ai/guides/developer-docs/llama-index.md) - [Model Management](https://docs.llmgrid.ai/guides/developer-docs/modelmanagement.md): Add, configure, and operate models, credentials, routing, health checks, retries, aliases, and pricing metadata. - [Node.js](https://docs.llmgrid.ai/guides/developer-docs/node-js.md) - [Other popular platforms](https://docs.llmgrid.ai/guides/developer-docs/other-platforms.md) - [Python](https://docs.llmgrid.ai/guides/developer-docs/python-sdk.md): The LLMGrid Python SDK uses a unified completion() interface with OpenAI-compatible parameters and a standardized response shape - [LLMGrid SDK](https://docs.llmgrid.ai/guides/developer-docs/sdk.md): Use the LLMGrid SDK and OpenAI-compatible clients to call models through https://api.llmgrid.ai/v1 with consistent request/response formats. - [LLMGrid Overview](https://docs.llmgrid.ai/index.md): A unified platform for routing, governing, and observing LLM usage across models, tools, and agents. - [Quick Start Guide](https://docs.llmgrid.ai/quick-start.md): Get started with LLMGrid in minutes using the OpenAI‑compatible proxy and core governance features. ## OpenAPI Specs - [openapi](https://docs.llmgrid.ai/api-reference/openapi.json)