# Portkey (Prisma AIRS AI Gateway) Docs: Latest Docs

> Comprehensive documentation for AI Gateway, Guardrails, Observability, and Governance features.

## Docs

### Introduction

- [What is Portkey?](https://docs.portkey.ai/docs/introduction/what-is-portkey.md): Portkey AI is a comprehensive platform designed to streamline and enhance AI integration for developers and organizations. It serves as a unified interface for interacting with over 250 AI models, offering advanced tools for control, visibility, and security in your Generative AI apps.
- [Make Your First Request](https://docs.portkey.ai/docs/introduction/make-your-first-request.md): Integrate Portkey and analyze your first LLM call in 2 minutes!
- [Portkey Features](https://docs.portkey.ai/docs/introduction/feature-overview.md): Explore the powerful features of Portkey

### Product

- [Coding Agents](https://docs.portkey.ai/docs/product/coding-agent.md): The governance layer for Claude Code, Codex, and other AI coding agents — centralized credentials, cost controls, observability, and provider failover for platform teams.
- [Open Source](https://docs.portkey.ai/docs/product/open-source.md)
- [Feature Comparison](https://docs.portkey.ai/docs/product/product-feature-comparison.md): Comparing Portkey's Open-source version and Dev, Pro, Enterprise plans.

#### Observability

- [Observability (OpenTelemetry)](https://docs.portkey.ai/docs/product/observability.md): Gain real-time insights, track key metrics, and streamline debugging with our comprehensive observability suite.
- [Logs](https://docs.portkey.ai/docs/product/observability/logs.md): The Logs section presents a chronological list of all the requests processed through Portkey.
- [Tracing](https://docs.portkey.ai/docs/product/observability/traces.md): The **Tracing** capabilities in Portkey empowers you to monitor the lifecycle of your LLM requests in a unified, chronological view.
- [Analytics](https://docs.portkey.ai/docs/product/observability/analytics.md)
- [Feedback](https://docs.portkey.ai/docs/product/observability/feedback.md): Portkey's Feedback APIs provide a simple way to get weighted feedback from customers on any request you served, at any stage in your app.
- [Metadata](https://docs.portkey.ai/docs/product/observability/metadata.md): Add custom context to your AI requests for better observability and analytics
- [Filters](https://docs.portkey.ai/docs/product/observability/filters.md)
- [Logs Export](https://docs.portkey.ai/docs/product/observability/logs-export.md): Easily access your Portkey logs data for further analysis and reporting
- [Model Pricing and Cost Management](https://docs.portkey.ai/docs/product/observability/cost-management.md): Learn how Portkey handles pricing data, cost calculations, and pricing updates across different deployment modes.
- [Budget Limits](https://docs.portkey.ai/docs/product/observability/budget-limits.md)
- [Auto-Instrumentation [BETA]](https://docs.portkey.ai/docs/product/observability/auto-instrumentation.md): Portkey's auto-instrumentation allows you to instrument tracing and logging for multiple LLM/Agent frameworks and view the logs, traces, and metrics in a single place.

##### OpenTelemetry

- [OpenTelemetry for LLM Observability](https://docs.portkey.ai/docs/product/observability/opentelemetry.md): Leverage OpenTelemetry with Portkey for comprehensive LLM application observability, combining gateway insights with full-stack telemetry.
- [Supported OTel Libraries](https://docs.portkey.ai/docs/product/observability/opentelemetry/list-of-supported-otel-instrumenters.md): Portkey works with any OpenTelemetry-compatible instrumentation. Here are some popular options.

#### AI Gateway

- [AI Gateway](https://docs.portkey.ai/docs/product/ai-gateway.md): The world's fastest AI Gateway with advanced routing & integrated Guardrails.
- [Configs](https://docs.portkey.ai/docs/product/ai-gateway/configs.md): This feature is available on all Portkey plans.
- [Custom hosts](https://docs.portkey.ai/docs/product/ai-gateway/custom-hosts.md): Route requests to privately hosted or local models using custom host URLs, and understand Portkey's host validation and security rules.
- [Remote MCP](https://docs.portkey.ai/docs/product/ai-gateway/remote-mcp.md): Portkey's AI gateway has MCP server support that many foundational model providers offer.
- [Beta Features](https://docs.portkey.ai/docs/product/ai-gateway/beta-features.md): Opt into early-access Portkey gateway capabilities using the x-portkey-beta header.
- [Conditional Routing](https://docs.portkey.ai/docs/product/ai-gateway/conditional-routing.md)
- [Cache (Simple & Semantic)](https://docs.portkey.ai/docs/product/ai-gateway/cache-simple-and-semantic.md): Speed up requests and reduce costs by caching LLM responses.
- [Fallbacks](https://docs.portkey.ai/docs/product/ai-gateway/fallbacks.md): Automatically switch to backup LLMs when the primary fails.
- [Automatic Retries](https://docs.portkey.ai/docs/product/ai-gateway/automatic-retries.md): Automatically retry failed LLM requests with exponential backoff.
- [Circuit Breaker](https://docs.portkey.ai/docs/product/ai-gateway/circuit-breaker.md): Automatically stop routing to unhealthy targets until they recover.
- [Realtime API](https://docs.portkey.ai/docs/product/ai-gateway/realtime-api.md): Use OpenAI's Realtime API with logs, cost tracking, and more!
- [gRPC (Beta)](https://docs.portkey.ai/docs/product/ai-gateway/grpc.md): Use gRPC as an alternative transport protocol for lower latency and efficient binary serialization
- [Load Balancing](https://docs.portkey.ai/docs/product/ai-gateway/load-balancing.md): Distribute traffic across multiple LLMs for high availability and optimal performance.
- [Canary Testing](https://docs.portkey.ai/docs/product/ai-gateway/canary-testing.md): You can use Portkey's AI gateway to also canary test new models or prompts in different environments.
- [Strict OpenAI Compliance](https://docs.portkey.ai/docs/product/ai-gateway/strict-open-ai-compliance.md)
- [Request Timeouts](https://docs.portkey.ai/docs/product/ai-gateway/request-timeouts.md): Manage unpredictable LLM latencies effectively with Portkey's **Request Timeouts**.
- [Files](https://docs.portkey.ai/docs/product/ai-gateway/files.md): Upload files to Portkey and reuse the content in your requests
- [Unified Batch Inference](https://docs.portkey.ai/docs/product/ai-gateway/batches.md): Run large‑scale inference jobs through one consistent endpoint
- [Fine-tuning](https://docs.portkey.ai/docs/product/ai-gateway/fine-tuning.md): Run your fine-tuning jobs with Portkey Gateway
- [Nitro Mode (Beta)](https://docs.portkey.ai/docs/product/ai-gateway/nitro-mode.md): Forward the request body directly to the provider without any transformations. Best when your request and response structure already matches the provider's API.

##### Universal API

- [Universal API](https://docs.portkey.ai/docs/product/ai-gateway/universal-api.md): One API for 200+ LLMs across every major provider. Use OpenAI's Chat Completions, Responses API, or Anthropic's Messages format -- Portkey translates between them all.
- [Chat Completions](https://docs.portkey.ai/docs/product/ai-gateway/chat-completions.md): Use OpenAI-compatible Chat Completions with any LLM provider through Portkey's AI Gateway.
- [Messages](https://docs.portkey.ai/docs/product/ai-gateway/messages-api.md): Use Anthropic's Messages format with any provider — 3000+ models, one endpoint.
- [Open Responses](https://docs.portkey.ai/docs/product/ai-gateway/responses-api.md): Use the Responses API with any LLM provider through Portkey's AI Gateway — fully compliant with the Open Responses specification.
- [Decisions](https://docs.portkey.ai/docs/product/ai-gateway/decisions-api.md): Get typed judgments (probability, choice, or score) from models through Portkey's /v1/decisions endpoint.

##### Multimodal Capabilities

- [Multimodal Capabilities](https://docs.portkey.ai/docs/product/ai-gateway/multimodal-capabilities.md)
- [Image Generation](https://docs.portkey.ai/docs/product/ai-gateway/multimodal-capabilities/image-generation.md): Portkey's AI gateway supports image generation capabilities that many foundational model providers offer.
- [Function Calling](https://docs.portkey.ai/docs/product/ai-gateway/multimodal-capabilities/function-calling.md): Portkey's AI Gateway supports function calling across major foundational models. Define functions in your API call, and the model can output the function name with parameters.
- [Vision](https://docs.portkey.ai/docs/product/ai-gateway/multimodal-capabilities/vision.md): Portkey's AI gateway supports vision models like GPT-4V by OpenAI, Gemini by Google and more.
- [Text-to-Speech](https://docs.portkey.ai/docs/product/ai-gateway/multimodal-capabilities/text-to-speech.md): Portkey's AI gateway supports text-to-speech models on OpenAI, Azure OpenAI, and Google Vertex AI.
- [Speech-to-Text](https://docs.portkey.ai/docs/product/ai-gateway/multimodal-capabilities/speech-to-text.md): Use Portkey's AI gateway to transcribe and translate audio using speech-to-text models across all supported providers.
- [Thinking Mode](https://docs.portkey.ai/docs/product/ai-gateway/multimodal-capabilities/thinking-mode.md)

##### Virtual Keys [Deprecated]

- [Virtual Keys](https://docs.portkey.ai/docs/product/ai-gateway/virtual-keys.md): Virtual Keys have been migrated to Model Catalog - learn about the new system
- [Budget Limits](https://docs.portkey.ai/docs/product/ai-gateway/virtual-keys/budget-limits.md): Budget Limits lets you set cost limits on providers/integrations
- [Rate Limits](https://docs.portkey.ai/docs/product/ai-gateway/virtual-keys/rate-limits.md): Set Rate Limts to your Integrations/Providers
- [Connect Bedrock with Amazon Assumed Role](https://docs.portkey.ai/docs/product/ai-gateway/virtual-keys/bedrock-amazon-assumed-role.md): How to create a new integration for Bedrock using Amazon Assumed Role Authentication

#### Model Catalog

- [Model Catalog](https://docs.portkey.ai/docs/product/model-catalog.md): A single pane to view and manage every AI provider and model in your organization. It provides centralized governance, discovery, and usage controls for all your AI resources.
- [Portkey Models](https://docs.portkey.ai/docs/product/model-catalog/portkey-models.md): Open-source pricing and configuration database for 2,300+ LLMs across 35+ providers
- [Integrations](https://docs.portkey.ai/docs/product/model-catalog/integrations.md): Securely store and manage AI provider credentials across your organization with centralized governance controls
- [Budget Limits](https://docs.portkey.ai/docs/product/model-catalog/budget-limits.md)
- [Rate Limits](https://docs.portkey.ai/docs/product/model-catalog/rate-limits.md)
- [Workspace Provisioning](https://docs.portkey.ai/docs/product/model-catalog/workspace-provisioning.md)
- [AI Model Provisioning](https://docs.portkey.ai/docs/product/model-catalog/model-provisioning.md)
- [Adding Custom Models](https://docs.portkey.ai/docs/product/model-catalog/custom-models.md): Learn how to add custom and fine-tuned models to your Portkey Model Catalog for seamless integration.
- [Adding Pricing Adjustments](https://docs.portkey.ai/docs/product/model-catalog/pricing-adjustments.md): Learn how to apply discount or markup multipliers to a Portkey Integration so cost tracking reflects your effective rate with a provider.
- [Overriding Model Details](https://docs.portkey.ai/docs/product/model-catalog/model-overrides.md): Learn how to set custom pricing for any base model in your Portkey Model Catalog to reflect your specific costs.
- [Connect Bedrock with Amazon Assumed Role](https://docs.portkey.ai/docs/product/model-catalog/connect-bedrock-with-amazon-assumed-role.md): How to create an integrate Bedrock using Amazon Assumed Role Authentication on Portkey
- [Workload Identity Federation](https://docs.portkey.ai/docs/product/model-catalog/workload-identity-federation.md): Connect OpenAI and Anthropic to Portkey without long-lived API keys, using short-lived tokens from Microsoft Entra ID, Okta, or any OIDC identity provider.

#### MCP Gateway

- [MCP Gateway](https://docs.portkey.ai/docs/product/mcp-gateway.md): Centralized authentication, access control, and observability for MCP servers.
- [Quickstart](https://docs.portkey.ai/docs/product/mcp-gateway/quickstart.md): Add DeepWiki to Portkey MCP Gateway and connect it to Claude.
- [Using MCP Servers](https://docs.portkey.ai/docs/product/mcp-gateway/using-mcp-servers.md): Connect to MCP servers from AI agents and applications.
- [Team Provisioning](https://docs.portkey.ai/docs/product/mcp-gateway/access-control.md): Control which workspaces and users can access MCP servers and their capabilities.
- [Tool Provisioning](https://docs.portkey.ai/docs/product/mcp-gateway/tool-provisioning.md): Control which tools, resources, and prompts are available to your organization and workspaces.
- [Authorization](https://docs.portkey.ai/docs/product/mcp-gateway/authorization.md): Control what users can access at the MCP server and tool level.
- [Observability](https://docs.portkey.ai/docs/product/mcp-gateway/observability.md): Log, monitor, and debug MCP interactions.
- [Integrations](https://docs.portkey.ai/docs/product/mcp-gateway/integrations.md): Connect MCP servers to AI agents and applications.
- [Guardrails](https://docs.portkey.ai/docs/product/mcp-gateway/guardrails.md): Apply security and compliance guardrails to MCP tool calls — regex filters, content validation, webhook checks, JSON schema enforcement, and more.

##### MCP Registry

- [MCP Registry](https://docs.portkey.ai/docs/product/mcp-gateway/mcp-registry.md): Add, manage, and govern MCP servers across your organization.
- [Add Internal MCP Servers](https://docs.portkey.ai/docs/product/mcp-gateway/internal-mcp-servers.md): Add your internal MCP servers to Portkey. Get enterprise-grade auth, access control, and logging without building it.
- [Add External MCP Servers](https://docs.portkey.ai/docs/product/mcp-gateway/external-mcp-servers.md): Connect third-party MCP servers like Linear, GitHub, Slack, and more through Portkey.
- [Registry API (Beta)](https://docs.portkey.ai/docs/product/mcp-gateway/registry-api.md): Serve your approved MCP servers as a standards-compliant catalog that governance-aware clients can consume.
- [MCP Advanced Configuration](https://docs.portkey.ai/docs/product/mcp-gateway/advanced-configuration.md): Control how the gateway authenticates, forwards context, and connects to upstream MCP servers.

##### Authentication

- [Authentication](https://docs.portkey.ai/docs/product/mcp-gateway/authentication.md): How authentication works in MCP Gateway.
- [OAuth](https://docs.portkey.ai/docs/product/mcp-gateway/authentication/oauth.md): Portkey's built-in OAuth 2.1 authentication for MCP Gateway.
- [Bring Your Own Auth](https://docs.portkey.ai/docs/product/mcp-gateway/authentication/external-oauth.md): Use your own identity provider for gateway authentication.
- [Identity Forwarding](https://docs.portkey.ai/docs/product/mcp-gateway/authentication/identity-forwarding.md): Pass authenticated user identity to MCP servers.
- [JWT Validation](https://docs.portkey.ai/docs/product/mcp-gateway/authentication/jwt.md): Validate JWTs from external identity providers.
- [OAuth Client Metadata](https://docs.portkey.ai/docs/product/mcp-gateway/authentication/oauth-client-metadata.md): Customize OAuth client metadata for MCP servers.
- [Forwarding Headers](https://docs.portkey.ai/docs/product/mcp-gateway/authentication/forwarding-headers.md): Pass headers from agent requests to MCP servers.
- [Custom Auth](https://docs.portkey.ai/docs/product/mcp-gateway/authentication/custom-auth.md): Configure custom authentication for MCP servers.

##### Reliability

- [Rate Limits](https://docs.portkey.ai/docs/product/mcp-gateway/rate-limits.md): Throttle MCP tool call requests and token consumption per API key, server, or tool.
- [Circuit Breakers](https://docs.portkey.ai/docs/product/mcp-gateway/circuit-breakers.md): Automatic failure handling for upstream MCP servers.

#### Agent Gateway

- [Agent Gateway](https://docs.portkey.ai/docs/product/agent-gateway.md): Centralized authentication, access control, and observability for your agents
- [Quickstart](https://docs.portkey.ai/docs/product/agent-gateway/quickstart.md): Get started with Agent Gateway
- [Agent Registry](https://docs.portkey.ai/docs/product/agent-gateway/registry.md): Manage your agent integrations
- [Agent Servers](https://docs.portkey.ai/docs/product/agent-gateway/servers.md): Host your agent servers
- [Advanced code snippets and examples](https://docs.portkey.ai/docs/product/agent-gateway/advanced-code-snippets-and-examples.md): Advanced code snippets and examples for the Agent Gateway

#### Prompt Studio

- [Prompt Engineering Studio](https://docs.portkey.ai/docs/product/prompt-engineering-studio.md)
- [Prompt Playground](https://docs.portkey.ai/docs/product/prompt-engineering-studio/prompt-playground.md)
- [Prompt Library](https://docs.portkey.ai/docs/product/prompt-engineering-studio/prompt-library.md)
- [Prompt Versioning & Labels](https://docs.portkey.ai/docs/product/prompt-engineering-studio/prompt-versioning.md)
- [Prompt Observability](https://docs.portkey.ai/docs/product/prompt-engineering-studio/prompt-observability.md)
- [Prompt Partials](https://docs.portkey.ai/docs/product/prompt-engineering-studio/prompt-partial.md): With Prompt Partials, you can save your commonly used templates (which could be your instruction set, data structure explanation, examples etc.) separately from your prompts and flexibly incorporate them wherever required.
- [Sharing Prompts and Partials](https://docs.portkey.ai/docs/product/prompt-engineering-studio/prompt-sharing.md): Share prompts and partials across workspaces in your organization with read-only access.
- [Prompt API](https://docs.portkey.ai/docs/product/prompt-engineering-studio/prompt-api.md): Learn how to integrate Portkey's prompt templates directly into your applications using the Prompt API
- [Tool Library](https://docs.portkey.ai/docs/product/prompt-engineering-studio/tool-library.md)
- [Integrations](https://docs.portkey.ai/docs/product/prompt-engineering-studio/prompt-integration.md)
- [Guides](https://docs.portkey.ai/docs/product/prompt-engineering-studio/prompt-guides.md): Learn how to get the most out of Portkey Prompts with these practical guides

#### Guardrails

- [Guardrails](https://docs.portkey.ai/docs/product/guardrails.md): Ship to production confidently with Portkey Guardrails on your requests & responses
- [Supported Endpoints & Capabilities](https://docs.portkey.ai/docs/product/guardrails/capabilities.md): Which endpoints, providers, input types, and execution modes Portkey Guardrails support.
- [List of Guardrail Checks](https://docs.portkey.ai/docs/product/guardrails/list-of-guardrail-checks.md)
- [Guardrails for Embedding Requests](https://docs.portkey.ai/docs/product/guardrails/embedding-guardrails.md): Apply security and data validation measures to vector embedding requests to protect sensitive information and ensure data quality.
- [Guardrails for Decisions Requests](https://docs.portkey.ai/docs/product/guardrails/decisions-guardrails.md): Apply guardrails to the caller-supplied state field on /v1/decisions requests, without scanning your own prompt instructions.
- [Creating Raw Guardrails (in JSON)](https://docs.portkey.ai/docs/product/guardrails/creating-raw-guardrails-in-json.md): With the raw Guardrails mode, we let you define your Guardrail checks & actions however you want, directly in code.
- [Forwarding Headers](https://docs.portkey.ai/docs/product/guardrails/forwarding-headers.md): Pass client request headers through to guardrail providers for trace correlation and session context.
- [PII Redaction](https://docs.portkey.ai/docs/product/guardrails/pii-redaction.md): Replace any sensitive data in requests with standard identifiers
- [Guardrails for Batches](https://docs.portkey.ai/docs/product/guardrails/guardrails-for-batches.md): Secure batch inference with Portkey Guardrails
- [Bring Your Own Guardrails](https://docs.portkey.ai/docs/integrations/guardrails/bring-your-own-guardrails.md): Integrate your custom guardrails with Portkey using webhooks

#### Administration

- [Enforcing Request Metadata](https://docs.portkey.ai/docs/product/administration/enforcing-request-metadata.md)
- [Enforcing Org Level Guardrails](https://docs.portkey.ai/docs/product/administration/enforce-orgnization-level-guardrails.md)
- [Enforcing Workspace Level Guardrails](https://docs.portkey.ai/docs/product/administration/enforce-workspace-level-guardials.md)
- [Configure Request Logging](https://docs.portkey.ai/docs/product/administration/configuring-request-logging.md): Control what data is stored for all LLM requests in your organization
- [Enforcing Default Configs on API Keys](https://docs.portkey.ai/docs/product/administration/enforce-default-config.md): Learn how to attach default configs to API keys for enforcing governance controls across your organization
- [Enforcing Saved-Only Resources](https://docs.portkey.ai/docs/product/administration/enforce-saved-only-config.md): Lock the Gateway to admin-curated providers, configs, and integrations by rejecting inline provider configuration at request time.
- [Enforce Budget Limits and Rate Limits for Your API Keys](https://docs.portkey.ai/docs/product/administration/enforce-budget-and-rate-limit.md): Configure budget and rate limits on API keys to effectively manage AI spending and usage across your organization
- [Enforce Workspace Budget and Rate Limits](https://docs.portkey.ai/docs/product/administration/enforce-workspace-budget-limts-and-rate-limits.md): Configure budget and rate limits at the workspace level to effectively manage AI spending and resource allocation
- [Configure Logs Access Permissions for Workspace](https://docs.portkey.ai/docs/product/administration/configure-logs-access-permissions-in-workspace.md)
- [Configure Analytics Access Permissions for Workspaces](https://docs.portkey.ai/docs/product/administration/configure-analytics-access-permissions.md)
- [Configure Data Visibility Settings for Workspaces](https://docs.portkey.ai/docs/product/administration/configure-data-visibility-settings.md)
- [Configure Provider Access Permissions](https://docs.portkey.ai/docs/product/administration/configure-virtual-key-access-permissions.md)
- [Configure API Key Access Permissions for Workspaces](https://docs.portkey.ai/docs/product/administration/configure-api-key-access-permissions.md)
- [Configure Prompt Access Permissions for Workspaces](https://docs.portkey.ai/docs/product/administration/configure-prompt-access-permissions.md)
- [Configure Guardrail Access Permissions for Workspaces](https://docs.portkey.ai/docs/product/administration/configure-guardrail-access-permissions.md)
- [Configure Integration Access Permissions for Workspaces](https://docs.portkey.ai/docs/product/administration/configure-integration-access-permissions.md)
- [Configure Workspace Provisioning for Your AI Integrations](https://docs.portkey.ai/docs/product/administration/configure-workspace-provisioning-for-your-ai-integrations.md)
- [Configure Model Access Permissioning for AI Integrations](https://docs.portkey.ai/docs/product/administration/configure-model-access-permissioning-for-ai-integratinon.md)
- [Enforce Rate Limits on Your AI Provider](https://docs.portkey.ai/docs/product/administration/enforce-rate-limits-on-your-ai-provider.md)
- [Enforce Budget Limits on Your AI Provider](https://docs.portkey.ai/docs/product/administration/enforce-budget-limits-on-your-ai-provider.md)

#### Enterprise Offering

- [Enterprise Offering](https://docs.portkey.ai/docs/product/enterprise-offering.md)
- [Access Control Management](https://docs.portkey.ai/docs/product/enterprise-offering/access-control-management.md): With customizable user roles, API key management, and comprehensive audit logs, Portkey provides the flexibility and control needed to ensure secure collaboration & maintain a strong security posture
- [Budget Limits](https://docs.portkey.ai/docs/product/enterprise-offering/budget-limits.md)
- [Security @ Portkey](https://docs.portkey.ai/docs/product/enterprise-offering/security-portkey.md): Portkey AI provides a secure, reliable AI gateway for the seamless integration and management of large language models (LLMs).
- [Logs Export](https://docs.portkey.ai/docs/product/enterprise-offering/logs-export.md)
- [Audit Logs](https://docs.portkey.ai/docs/product/enterprise-offering/audit-logs.md): Track and monitor all administrative activities across your Portkey organization with comprehensive audit logging.
- [Usage & Rate Limit Policies](https://docs.portkey.ai/docs/product/enterprise-offering/budget-policies.md): Create fine-grained controls over API usage and rate limits at the workspace level
- [Enterprise Components](https://docs.portkey.ai/docs/product/enterprise-offering/components.md)
- [KMS Integration](https://docs.portkey.ai/docs/product/enterprise-offering/kms.md): Customers can bring their own encryption keys to Portkey AI to encrypt data at storage.
- [Secret References](https://docs.portkey.ai/docs/product/enterprise-offering/secret-references.md): Reference secrets stored in external secret managers like AWS Secrets Manager, Azure Key Vault, and HashiCorp Vault instead of storing them directly in Portkey.

##### Org Management

- [Org Management](https://docs.portkey.ai/docs/product/enterprise-offering/org-management.md): A high-level introduction to Portkey's organization management structure and key concepts.
- [Organizations](https://docs.portkey.ai/docs/product/enterprise-offering/org-management/organizations.md): Understand the role and features of Organizations, the highest level of abstraction in Portkey's structure.
- [Workspaces](https://docs.portkey.ai/docs/product/enterprise-offering/org-management/workspaces.md): Explore Workspaces, the sub-organizational units that enable granular project and team management.
- [User Roles & Permissions](https://docs.portkey.ai/docs/product/enterprise-offering/org-management/user-roles-and-permissions.md): Learn about Portkey's comprehensive role-based access control system across Organizations and Workspaces.
- [API Keys (AuthN and AuthZ)](https://docs.portkey.ai/docs/product/enterprise-offering/org-management/api-keys-authn-and-authz.md): Discover how Admin and Workspace API Keys are used to manage access and operations in Portkey.
- [API Key Rotation](https://docs.portkey.ai/docs/product/enterprise-offering/org-management/api-key-rotation.md): Periodically replace API key secrets without downtime using manual or automatic rotation with configurable transition periods.
- [Gateway URLs](https://docs.portkey.ai/docs/product/enterprise-offering/org-management/gateway-urls.md): Configure custom gateway endpoints for your organisation's AI gateway and MCP gateway deployments.
- [JWT Authentication](https://docs.portkey.ai/docs/product/enterprise-offering/org-management/jwt.md): Configure JWT-based authentication for your organization in Portkey
- [SSO](https://docs.portkey.ai/docs/product/enterprise-offering/org-management/sso.md): SSO support for enterprises

###### SCIM

- [Overview](https://docs.portkey.ai/docs/product/enterprise-offering/org-management/scim/scim.md): SCIM integration with Portkey.
- [SCIM Group Management](https://docs.portkey.ai/docs/product/enterprise-offering/org-management/scim/group-management.md): Map SCIM groups to Portkey workspaces and roles without naming restrictions.
- [Azure Entra](https://docs.portkey.ai/docs/product/enterprise-offering/org-management/scim/azure-ad.md): Setup Azure Entra for SCIM provisioning with Portkey.
- [Okta](https://docs.portkey.ai/docs/product/enterprise-offering/org-management/scim/okta.md): Set up Okta for SCIM provisioning with Portkey.

###### Directory Sync

- [CIE Directory Sync](https://docs.portkey.ai/docs/product/enterprise-offering/org-management/directory-sync/cie-directory-sync.md): Sync users and groups from Palo Alto Networks Cloud Identity Engine (CIE) into SCM's AI Gateway for automated workspace provisioning.

##### OpenTelemetry(OTel)

- [OpenTelemetry(OTel) Export](https://docs.portkey.ai/docs/product/enterprise-offering/otel/otel.md): Export Portkey data to OpenTelemetry compatible endpoints for external observability
- [Analytics Export](https://docs.portkey.ai/docs/product/enterprise-offering/otel/analytics.md): Export Portkey analytics data to OpenTelemetry-compatible collectors for centralized observability
- [Complete Logs Export](https://docs.portkey.ai/docs/product/enterprise-offering/otel/complete-logs.md): Export complete LLM request/response logs to OpenTelemetry endpoints following GenAI semantic conventions

### Self-Hosting

- [Cache Behavior](https://docs.portkey.ai/docs/self-hosting/cache-behavior.md): How the Gateway cache works: population, TTL, sync, resync, and cache invalidation and refresh.
- [Prometheus Metrics](https://docs.portkey.ai/docs/self-hosting/prometheus-metrics.md): Comprehensive monitoring and observability for Portkey Enterprise Gateway through Prometheus metrics
- [Prisma AIRS AI Gateway: Major Performance Improvements Incoming](https://docs.portkey.ai/docs/self-hosting/major-performance-improvements.md): What the upcoming AI Gateway performance improvements mean for hybrid deployments, what changes in 2.30.0, and what your platform team should check.
- [FIPS-Compliant Images](https://docs.portkey.ai/docs/self-hosting/fips-compliant-images.md): FIPS 140-3 compliant container images for the Portkey Enterprise Gateway and Data Service

#### Hybrid Deployments

- [Enterprise Architecture](https://docs.portkey.ai/docs/self-hosting/hybrid-deployments/architecture.md): Comprehensive guide to Portkey's hybrid deployment architecture for enterprises
- [SCM Deployment Mode Architecture](https://docs.portkey.ai/docs/self-hosting/hybrid-deployments/scm-architecture.md): Architecture guide for Portkey deployed in SCM (Palo Alto Networks Strata Cloud Manager) mode — covering the two-plane model, component roles, identity flow, and how data is distributed across the system.
- [Gateway Registration](https://docs.portkey.ai/docs/self-hosting/hybrid-deployments/gateway-registration.md): Register your self-hosted AI Gateway with the Portkey Control Plane to enable configuration sync, analytics, and workspace access control.
- [GCP](https://docs.portkey.ai/docs/self-hosting/hybrid-deployments/gcp.md): This enterprise-focused document provides comprehensive instructions for deploying the Portkey software in a hybrid mode on Google Kubernetes Engine clusters, designed to meet the needs of large-scale, mission-critical applications. It includes specific recommendations for component sizing, high ava…

##### AWS

- [EKS](https://docs.portkey.ai/docs/self-hosting/hybrid-deployments/aws/eks.md): This enterprise-focused document provides comprehensive instructions for deploying the Portkey software in a hybrid mode on Amazon EKS clusters, designed to meet the needs of large-scale, mission-critical applications. It includes specific recommendations for component sizing, high availability, and…
- [ECS](https://docs.portkey.ai/docs/self-hosting/hybrid-deployments/aws/ecs.md): This enterprise-focused document provides comprehensive instructions for deploying the Portkey software on Amazon Elastic Container Service (ECS), tailored to meet the needs of large-scale, mission-critical applications. It includes specific recommendations for component sizing, high availability, a…
- [AWS Marketplace](https://docs.portkey.ai/docs/self-hosting/hybrid-deployments/aws/marketplace.md): This enterprise-focused document provides comprehensive instructions for deploying the Portkey software using AWS Marketplace.

##### Azure

- [AKS](https://docs.portkey.ai/docs/self-hosting/hybrid-deployments/azure/aks.md): This enterprise-focused document provides comprehensive instructions for deploying the Portkey software on Azure Kubernetes Service (AKS), tailored to meet the needs of large-scale, mission-critical applications. It includes specific recommendations for component sizing, high availability, and integ…
- [ACA](https://docs.portkey.ai/docs/self-hosting/hybrid-deployments/azure/aca.md): This enterprise-focused document provides comprehensive instructions for deploying the Portkey software on Azure Container Apps (ACA), tailored to meet the needs of large-scale, mission-critical applications. It includes specific recommendations for component sizing, high availability, and integrati…

#### Air-Gapped Deployments (Legacy)

- [Model Pricing for Air-Gapped Deployments](https://docs.portkey.ai/docs/self-hosting/airgapped/model-pricing.md): Configure model pricing and capabilities data for fully air-gapped Portkey deployments. Legacy — air-gapped is no longer offered for new deployments.

### Support

- [Upgrade to Model Catalog](https://docs.portkey.ai/docs/support/upgrade-to-model-catalog.md): Learn how to upgrade to Model Catalog to replace Virtual Keys
- [How to Contribute](https://docs.portkey.ai/docs/README.md)
- [Contact Us](https://docs.portkey.ai/docs/support/contact-us.md)
- [Developer Forum](https://docs.portkey.ai/docs/support/developer-forum.md): Are you navigating the challenging journey of transitioning LLMs from prototype stages to full-scale production? You're not alone. As this frontier of technology continues to expand, the roadmap isn't always clear. Best practices, guidelines, and efficient methodologies are still on the horizon.
- [Common Errors & Resolutions](https://docs.portkey.ai/docs/support/common-errors-and-resolutions.md): Since Portkey functions as a gateway - you may encounter Portkey-related, as well as non-Portkey related errors while using our services.
- [December '23 Migration](https://docs.portkey.ai/docs/support/portkeys-december-migration.md)