> ## Documentation Index
> Fetch the complete documentation index at: https://docs.portkey.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Frontend

<Card title="Schedule Call" href="https://portkey.sh/demo-21" icon="calendar" horizontal>
  Discuss how Portkey's AI Gateway can enhance your organization's AI infrastructure
</Card>

<Update label="1.9.3" description="2026-06-22">
  ## v1.9.3

  ***

  ### Organisation Settings

  * Added dashboard controls for **Data Plane Security Settings** at the organization and workspace levels, including workspace override handling for saved-only resource enforcement

  ### Anthropic Integrations

  * Added **Catch Overloaded Errors on Stream** to Anthropic advanced configuration so streaming `overloaded_error` responses can trigger retries and fallbacks
  * When enabled, the gateway detects Anthropic overloaded errors inside streaming responses and converts them to retriable 529 errors, allowing retry and fallback strategies to trigger

  ### Fixes and Improvements

  * **Logs**: Fixed Logs page crash when guardrail checks are missing from hook responses
  * **Tables**: Fixed resizable table column width handling
  * Fixes Secret Reference edit behavior for stale drawer values
  * Fixed calendar popover alignment in provider expiry configuration
</Update>

<Update label="1.9.2" description="2026-05-27">
  ## v1.9.2

  ***

  ### Organisation Settings

  * Org-level toggle for **default workspace user API key auto-create**; the default workspace setting is now controlled from organisation admin settings instead of workspace settings

  [Default Config Documentation](/product/administration/enforce-default-config)

  ### Gateway Registration

  * Added filters to the gateway registration list
  * Fixed add-button logic and create flow to handle production and non-production gateway quotas separately

  [Self-Hosting Documentation](/self-hosting/hybrid-deployments/architecture)

  ### Self-Hosting

  * New `VITE_PRESELECT_LOGIN_PERMISSION` environment variable to pre-select the login permission checkbox on private deployments

  [Self-Hosting Documentation](/self-hosting/hybrid-deployments/architecture)

  ### Fixes and Improvements

  * **Logs Export**: Fixed request/response token field keys in in-app export configuration
  * **Analytics**: Removed weighted feedback column from metadata summary table
  * **Workspaces**: Fixed workspace member search
  * **Navigation**: Further fix for invalid `org_id` in the URL when it doesn't match accessible organizations
  * Updated dependencies to patch security vulnerabilities
  * Bug fixes and performance improvements

  [Logs Export Documentation](/product/observability/logs-export)
  [Analytics Documentation](/product/observability/analytics)
</Update>

<Update label="1.9.1" description="2026-05-21">
  ## v1.9.1

  ***

  ### Azure Integrations

  * **Azure Workload Identity**: Configure `azureWorkloadClientId` and `azureWorkloadTenantId` in the dashboard for Azure OpenAI and Azure AI Foundry integrations using workload auth mode

  [Azure Authentication Documentation](/integrations/llms/azure-openai/authentication)

  ### Fixes and Improvements

  * **Org API Key Rotation**: Input field and validation error messaging improvements for org service API key rotation
  * **SCIM / Workspaces**: Fixed workspace "Created by" display for SCIM-provisioned users and default API key behavior
  * **Navigation**: Invalid `org_id` in the URL is corrected when it doesn't match the user's accessible organizations
  * Bug fixes and performance improvements

  [API Key Rotation Documentation](/product/enterprise-offering/org-management/api-key-rotation)
  [SCIM Documentation](/product/enterprise-offering/org-management/scim/scim)
</Update>

<Update label="1.9.0" description="2026-05-20">
  ## v1.9.0

  ***

  ### Fixes and Improvements

  * **Prompt & Partial Sharing**
    * Publish to org or selected workspaces; control visibility anytime
    * "Shared with me" tab for org-wide shared prompts and partials
    * Read-only preview before use
    * One-click fork into your workspace
    * Automatic partial detection for `{{> slug}}` references when sharing prompts
  * **Prompt Variables — Import & Export (CSV)**
    * Export all variables for the current prompt as CSV (`name`, `type`, `value`)
    * Import from CSV to set values in bulk (text and JSON supported)
  * Added new provider Scenario AI
  * Bug fixes and performance improvements
</Update>

<Update label="1.8.3" description="2026-05-18">
  ## v1.8.3

  ***

  ### Fixes and Improvements

  * Policy budget limit type now supports requests as well
  * Added new providers BytePlus and Fal AI
  * Bug fixes and performance improvements
</Update>

<Update label="1.8.2" description="2026-05-12">
  ## v1.8.2

  ***

  ### Fixes and Improvements

  * Auto create API key for organisation and workspace
  * Reset usage for budget allocation
  * Conditions update enabled for policy update
  * Bug fixes and performance improvements
</Update>

<Update label="1.8.1" description="2026-05-07">
  ## v1.8.1

  ***

  ### Fixes and Improvements

  * Provider level pricing adjustments
  * Secret reference for MCP registry
  * Bug fixes and performance improvements
</Update>

<Update label="1.8.0" description="2026-05-04">
  ## v1.8.0

  ***

  ### Fixes and Improvements

  * Design Library Changes
  * Added new provider - bedrock mantle
  * Bug fixes and performance improvements
</Update>

<Update label="1.7.6" description="2026-04-24">
  ## v1.7.6

  ***

  ### Fixes and Improvements

  * Guardrail Pagination support for Guardrail List page
  * Secret Reference Integration support for Azure OpenAI and Azure Foundry setup inside LLM Integrations
  * Bug fixes and performance improvements
</Update>

<Update label="1.7.5" description="2026-04-22">
  ## v1.7.5

  ***

  ### Fixes and Improvements

  * Org-Admin permissions for Logs Management at Org level and Workspace level
  * Guardrail Management security settings with per-role view/write toggles and workspace-level override
  * Bug fixes and performance improvements
</Update>

<Update label="1.7.4" description="2026-04-16">
  ## v1.7.4

  ***

  ### Fixes and Improvements

  * Support for Logs Path variable in UI
  * Support Portkey Metadata to Vertex Labels for better observability
  * Custom host support for Models provisioning
  * federated auth support for Entra-Auth for Azure Integrations
  * Bug fixes and performance improvements
</Update>

<Update label="1.7.3" description="2026-04-14">
  ## v1.7.3

  ***

  ### Fixes and Improvements

  * Support for Integrations specific Security Settings
  * Updated UI to support exclude Policy types
  * Documentation updates for `max_completion_tokens` for latest gpt models for Azure integrations
  * Bug fixes and performance improvements
</Update>

<Update label="1.7.2" description="2026-04-07">
  ## v1.7.2

  ***

  ### Fixes and Improvements

  * Support for Cache Pricing for models in LLM Integrations
  * Bug fixes and performance improvements
</Update>

<Update label="1.7.1" description="2026-04-02">
  ## v1.7.1

  ***

  ### Fixes and Improvements

  * Support for Policy with exclude conditions
  * Added column In API Key list to show the owner of User API Key
  * Bug fixes and performance improvements
</Update>

<Update label="1.7.0" description="2026-04-01">
  ## v1.7.0

  ***

  ### Fixes and Improvements

  * Gateway Registration UI added
  * API Key Rotation UI added
  * Last Reset Date is added in UI in Integrations, Providers, API Keys, Workspace Budgets
  * Added support to display Spans w/o filters and UI to toggle between in Trace View
  * Added detailed feature description for hidden/disabled features under Settings
  * Add Anthropic Cache ttl support from Playground/Prompts
  * Maximum session time now supported at Organisation level for Users
  * Support for Akto AI under plugins
  * Bug fixes and performance improvements
</Update>

<Update label="1.6.10" description="2026-03-21">
  ## v1.6.10

  ***

  ### Fixes and Improvements

  * Support added to collect Dashboard Gateway URL and MCP Gateway URL at Organisation level
  * Display nudge to add missing User API key if Generations or Completions calls are blocked
  * Bug fixes and performance improvements
</Update>

<Update label="1.6.9" description="2026-03-16">
  ## v1.6.9

  ***

  ### Fixes and Improvements

  * Added stale time configuration for two APIs to improve performance
  * Fixed clear input tag functionality
  * Corrected log URL path handling with license ID, creation time, and path
  * Fixed JSON schema copy functionality for providers on the Prompts page
  * Fixed cURL vulnerability
  * Resolved zlib vulnerability
  * Applied additional generic vulnerability fixes
</Update>

<Update label="1.6.8" description="2026-03-06">
  ## v1.6.8

  ***

  ### Fixes and Improvements

  * Introduced Zscaler integration
  * Upgraded Policy to version 2.0.0
  * Added WCAG-related accessibility improvements
  * Removed workspace option from workspace filter
  * Fixed analytics redirection to “Getting Started” page on refresh
  * Improved usage and rate limit validation before enabling actions
</Update>

<Update label="1.6.7" description="2026-03-02">
  ## v1.6.7

  ***

  ### Fixes and Improvements

  * New security reference feature
  * Fixed prompt-model mismatch issue in Playground UI
  * Added conditional redirection support
  * Improved filter validation with additional checks
  * Fixed multi-workspace detection to handle page state correctly
  * Added summary tables for improved data visibility
</Update>

<Update label="1.6.6" description="2026-02-23">
  ## v1.6.6

  ***

  ### Fixes and Improvements

  * Multiline variable support for Prompt Playground calls
  * Bug fixes and performance improvements
  * Ability to filter API keys by API Key Type (User, Service).
  * Ability to Sort the API key by column name.
</Update>

<Update label="1.6.5" description="2026-02-20">
  ## v1.6.5

  ***

  ### Fixes and Improvements

  * Added visibility of Budget inside Workspace Control
  * Bug fixes and performance improvements
</Update>

<Update label="1.6.4" description="2026-02-20">
  ## v1.6.4

  ***

  ### Fixes and Improvements

  * Support for Data Visibility security setting for self-only Logs and Analytics
</Update>

<Update label="1.6.3" description="2026-02-18">
  ## v1.6.3

  ***

  ### Fixes and Improvements

  * Support for User and Service key filter in API Key List page
  * Security setting for Prompts View and Management
  * Support for Workspace Budget periodic reset by date
</Update>

<Update label="1.6.2" description="2026-02-16">
  ## v1.6.2

  ***

  ### Fixes and Improvements

  * MCP Gateway Icon and Description updates
  * Support for multiple traces search in Logs and Analytics Filter
  * Security setting changes to view Analytics page
</Update>

<Update label="1.6.1" description="2026-02-04">
  ## v1.6.1

  ***

  ### Fixes and Improvements

  * Security setting UI Updates
  * SSO login support for multiple SSO enabled Organisations
  * API key creation support by Workspace Managers for Users
  * Policy management UI Updates
  * Organisation level multiple guardrails support
  * MCP capabilities support for the MCP Gateway
  * MCP access control support at Workspace level
  * Search support for Saved Filters
  * Logs Table column resize support
</Update>

<Update label="1.6.0" description="2026-01-07">
  ## v1.6.0

  ***

  ### Fixes and Improvements

  * Added configuration changes to sync with the models list and model capabilities specific to provider
  * Added UI support to add option to next reset date for API keys
</Update>

<Update label="1.5.7" description="2026-01-06">
  ## v1.5.7

  ***

  ### Fixes and Improvements

  * Added UI support for Retry Exhausted state for Logs
  * Added nested Prompt folder support on UI
  * Added Oracle Provider support on UI
  * Added option to execute Guardrails sequentially
  * Added support for breakdown of LLM requests and responses
</Update>

<Update label="1.5.6" description="2025-12-16">
  ## v1.5.6

  ***

  ### Fixes and Improvements

  * Added more AI Provider models support for ai21, anyscale, cerebras, cohere, deepinfra, fireworks, groq, mistral, novita, perplexity and together ai
</Update>

<Update label="1.5.5" description="2025-12-13">
  ## v1.5.5

  ***

  ### Fixes and Improvements

  * Added embedding text and completion support on getting started and model integrations
  * Added copy option on Prompt Playground on Each messages
  * Updated new Guardrails and Plugins support
</Update>

<Update label="1.5.4" description="2025-11-24">
  ## v1.5.4

  ***

  ### Fixes and Improvements

  * Provided support of stream parameter for gpt 5.1 models
  * Added confirmation modal before enabling SSO Only Login flow
  * Added UI support for SCIM group workspace mapping management
  * Added AWS region configuration support for Bedrock and Sagemaker service role authentication, enabling users to specify the AWS region when using service role-based authentication instead of access keys
</Update>

<Update label="1.5.3" description="2025-11-19">
  ## v1.5.3

  ***

  ### Fixes and Improvements

  * Added gemini-3-pro models for Google and VertexAI
  * Minor updates to support log fetch for configurable log store file path format released in Gateway v1.17.0
</Update>

<Update label="1.5.2" description="2025-11-18">
  ## v1.5.2

  ***

  ### Fixes and Improvements

  * The UI now supports completion calls in the Integrations section of the Getting Started page.
  * UI support for new Azure OpenAI models.
</Update>

<Update label="1.5.1" description="2025-11-18">
  ## v1.5.1

  ***

  ### Fixes and Improvements

  * Support for OpenAI gpt5.1 models
  * UI update to display any base64 url inside logs with option to download them.
  * Enhanced the Integrations interface: selected models are now prominently displayed at the top of the Update Integration Models page.
</Update>

<Update label="1.5.0" description="2025-11-17">
  ## v1.5.0

  ***

  ### Fixes and Improvements

  <Note>
    **Needs a Helm repo update(>app-1.4.0)**
  </Note>

  * Security patch — removed root user from container image (BREAKING CHANGE). The container image used by this chart no longer runs as root. The image now runs processes as a non-root UID and enforces a non-root container securityContext. Requires Helm repo upgrade (>app-1.4.0) to deploy the new image and chart settings.
  * New Security Feature to provide access to Workspace Members to Manage Configs
  * UI update to highlight Traces by their category
  * UI update to improve visibility of Logs with Guardrails
  * Update zhipu provider to include new models
  * Improve the accessibility of Login/Signup pages
</Update>

<Update label="1.4.9" description="2025-11-06">
  ## v1.4.9

  ***

  ### Fixes and Improvements

  * Added a JSON mode for prompt parameters, allowing real-time updates and easier editing.
  * Improvement of MCP Consent page to search by workspaces
  * Fix for Model Catalog page to display the Usage Limit on page load
  * Fix for Prompt Labels delete functionality. This will remove the label from the prompt version which it is assigned to before deletion.
  * Analytics Filter API key now have search functionality.
  * Support added for transcribe models under azure and OpenAI providers.
  * Added more detailed support for Logs with Tools. On hover fields, description and their types will be visible.
  * Configuration options for Contact Us, Discord, and custom support are now available.
  * Added support for new OpenAI Models.
</Update>

<Update label="1.4.8" description="2025-10-24">
  ## v1.4.8

  ***

  ### Fixes and Improvements

  * Added Support for Bedrock Service Role changes
  * Added missing tool\_choice and response\_format parameters to Groq provider
</Update>

<Update label="1.4.7" description="2025-10-22">
  ## v1.4.7

  ***

  ### Fixes and Improvements

  * Added Claude 4.5 Haiku models for Anthropic, AWS Bedrock, and VertexAI base providers
</Update>

<Update label="1.4.6" description="2025-10-17">
  ## v1.4.6

  ***

  ### API Key Enhancements

  * Added multiple rate limit support. It is now possible to set both cost-based and token-based rate limits on a single key
  * Introduced a security setting to restrict the maximum number of `User` API keys that can be created per user
  * Introduced a security setting to configure the default and maximum expiry of `User` API keys

  ### MCP Improvements

  * Updated the MCP OAuth consent screen to allow selection from eligible workspaces
  * Added better states for consent approval, rejection, and failures
  * Fixed an issue to allow Workspace admins to edit Workspace-created MCP integrations

  ### Fixes and Improvements

  * Hide embedding models in prompt playground
  * Allow updating base models for custom models
  * Made alias a required field for Azure-OpenAI deployment configurations
  * Added gpt-5-codex, gpt-5-pro, and several other OpenAI and Azure-OpenAI models
  * Added new Together AI and Grok models
  * Added AWS Bedrock Titan Embedding and Titan v1 models
</Update>

<Update label="1.4.3" description="2025-10-02">
  ## v1.4.3

  ***

  ### Fixes and Improvements

  * Added Claude Sonnet 4.5 models for Anthropic, AWS Bedrock, and VertexAI base providers
  * Updated the Model Catalog Workspace Provisioning page to display full workspace names instead of trimming them
</Update>

<Update label="1.4.2" description="2025-09-24">
  ## v1.4.2

  ***

  ### Fixes and Improvements

  * Added `gemini-2.5-flash-image-preview` model for vertex-ai and google base providers
</Update>

<Update label="1.4.1" description="2025-09-24">
  ## v1.4.1

  ***

  ### Configs Security Settings

  * Added configs under security settings along with Workspace Overrides option
</Update>

<Update label="1.4.0" description="2025-09-23">
  ## v1.4.0

  ***

  ### MCP Enhancements

  * Added enhancements for the MCP integrations and servers management
  * Updates to the MCP OAuth consent screen

  ### Fixes and Improvements

  * Added span name as tooltip for better trace visibility
  * Fixed Vertex AI Anthropic model name mapping issue
  * Fixed Azure-OpenAI `Add Model` button state in update view
  * Removed config, metadata, and rate limits fields for admin keys
  * Fixed display base\_url for Model Catalog Python SDK code snippets
</Update>