Portkey-AI · vrv-panw · Sep 15, 2026
diff --git a/aigw/api-reference/admin-api/introduction.mdx b/aigw/api-reference/admin-api/introduction.mdx
@@ -43,19 +43,6 @@ Once your resources are configured, you'll want to measure performance and usage
   </Card>
 </CardGroup>
 
-### User and Workspace Administration
-
-Beyond resources and analytics, you'll need to manage who has access to your AI Gateway environment:
-
-<CardGroup cols={2}>
-  <Card title="Users & Invites" href="/api-reference/admin-api/control-plane/users/retrieve-a-user">
-    Manage user accounts, permissions, and access. Send and manage user invitations.
-  </Card>
-  <Card title="Workspaces & Members" href="/api-reference/admin-api/control-plane/workspaces/create-workspace">
-    Create workspaces and manage team membership and permissions within workspaces.
-  </Card>
-</CardGroup>
-
 ## Authentication Strategy
 
 Now that you understand what the Admin API can do, let's explore how to authenticate your requests. The AI Gateway uses a sophisticated access control system with two types of API keys, each designed for different use cases:
@@ -199,8 +186,8 @@ Now that you understand the Admin API ecosystem, authentication, and permissions
 
 For developers looking to integrate with the Admin API, we provide a complete OpenAPI specification that you can use with your API development tools:
 
-<Card title="OpenAPI Specification" icon="file-code" href="/api-reference/admin-api/open-api-specification">
-  Download the OpenAPI spec for the Admin API
+<Card title="OpenAPI Specification" icon="file-code" href="/aigw/api-reference/inference-api/open-api-specification">
+  A single specification covers both the gateway and the Admin API
 </Card>
 
 ## Need Support?

diff --git a/aigw/api-reference/inference-api/agentic-usage.mdx b/aigw/api-reference/inference-api/agentic-usage.mdx
@@ -178,12 +178,6 @@ The skill source is available at: [github.com/portkey-ai/skills](https://github.
 Contributions and feedback are welcome.
 
 <CardGroup cols={2}>
-  <Card title="Python SDK Docs" icon="python" href="/api-reference/sdk/python">
-    Full Python SDK documentation
-  </Card>
-  <Card title="TypeScript SDK Docs" icon="js" href="/api-reference/sdk/node">
-    Full TypeScript SDK documentation
-  </Card>
   <Card title="Skills Repository" icon="github" href="https://github.com/portkey-ai/skills">
     View the skills source on GitHub
   </Card>

diff --git a/aigw/api-reference/inference-api/open-api-specification.mdx b/aigw/api-reference/inference-api/open-api-specification.mdx
@@ -1,4 +1,4 @@
 ---
 title: "OpenAPI Specification"
-url: "https://github.com/Portkey-AI/openapi"
+url: "https://github.com/PaloAltoNetworks/openapi"
 ---
diff --git a/aigw/changelog/data-service.mdx b/aigw/changelog/data-service.mdx
@@ -291,7 +291,7 @@ rss: true
 ---
 
 ### Data exports
-- Added support for [Data exports](/api-reference/admin-api/data-plane/logs/log-exports-beta/start-a-log-export) for hybrid deployments.
+- Added support for Data exports for hybrid deployments.
 
 ### Fixes and Improvements
 - Fixed issue with custom batches for small batch files

diff --git a/aigw/changelog/enterprise.mdx b/aigw/changelog/enterprise.mdx
@@ -2662,7 +2662,7 @@ Added new condition keys for fine-grained budget and rate limit policies:
 
 ### Log Exports available on Data Plane
 - Log exports are now available on Data Plane
-- Export logs without them being sent to Management Plane [Docs Link](/api-reference/admin-api/data-plane/logs/log-exports-beta)
+- Export logs without them being sent to Management Plane
 - Please note that, `Dataservice` is required for log exports to work via Data Plane.
 
 ### Fixes And Improvements

diff --git a/aigw/integrations/cloud/azure.mdx b/aigw/integrations/cloud/azure.mdx
@@ -34,7 +34,7 @@ Bring any model deployed via Azure AI Studio (formerly AI Foundry) under the AI
 <Card title="Azure Content Safety Guardrails" icon="shield-check" href="/product/guardrails/azure-guardrails">
 Apply robust, configurable content moderation and PII detection to every AI request—no code changes required in your applications.
 </Card>
-<Card title="Full Support for OpenAI C# SDK & Semantic Kernel" icon="code" href="/api-reference/sdk/c-sharp">
+<Card title="Full Support for OpenAI C# SDK & Semantic Kernel" icon="code">
 Developers can continue using familiar Microsoft tooling. The AI Gateway transparently adds value by handling routing, cost attribution, observability, and guardrails.
 </Card>
 <Card title="Native Azure API Management (APIM) Integration" icon="plug">

diff --git a/aigw/integrations/libraries.mdx b/aigw/integrations/libraries.mdx
@@ -45,7 +45,7 @@ title: "Overview"
 
   <Card title="Mongo DB" href="/aigw/integrations/libraries/mongodb" />
 
-  <Card title="Microsoft Seamntic Kernel" href="/api-reference/inference-api/sdks/c-sharp#microsoft-semantic-kernel-example" />
+  <Card title="Microsoft Semantic Kernel" href="/aigw/integrations/libraries/microsoft-semantic-kernel" />
 
   <Card title="Tooljet" href="/aigw/integrations/libraries/tooljet"/>
 

diff --git a/aigw/integrations/libraries/vercel.mdx b/aigw/integrations/libraries/vercel.mdx
@@ -410,7 +410,7 @@ const openai = createOpenAI({
 
 </CodeGroup>
 
-<Card title="Learn more about AI Gateway Headers" href="/api-reference/inference-api/request-headers" />
+<Card title="Learn more about AI Gateway Headers" href="/aigw/api-reference/inference-api/headers" />
 
 ## Using AI Providers & Model Catalog
 

diff --git a/aigw/integrations/llms/aws-sagemaker.mdx b/aigw/integrations/llms/aws-sagemaker.mdx
@@ -133,10 +133,6 @@ curl https://aigw.portkey.ai/v1/endpoints/{endpoint_name}/invocations \
 
 <CardGroup cols={2}>
 
-<Card title="SDK Reference" icon="code" href="/api-reference/sdk/list">
-Complete SDK documentation and API reference
-</Card>
-
 <Card title="Add Metadata" icon="tag" href="/aigw/product/observability/metadata">
 Add metadata to your Sagemaker requests
 </Card>

diff --git a/aigw/integrations/llms/azure-foundry.mdx b/aigw/integrations/llms/azure-foundry.mdx
@@ -607,10 +607,6 @@ The native `/v1/ocr` endpoint requires gateway version **2.18.0** or higher for
 
 <CardGroup cols={2}>
 
-<Card title="SDK Reference" icon="code" href="/api-reference/sdk/list">
-  Complete SDK documentation and API reference
-</Card>
-
 <Card
   title="Azure OpenAI"
   icon="microsoft"

diff --git a/aigw/integrations/llms/azure-openai/azure-openai.mdx b/aigw/integrations/llms/azure-openai/azure-openai.mdx
@@ -210,11 +210,6 @@ For further questions on custom Azure deployments or fine-grained access tokens,
 
 ## Next Steps
 
-The complete list of features supported in the SDK are available on the link below.
-
-<Card title="SDK" href="/api-reference/sdk">
-</Card>
-
 You'll find more information in the relevant sections:
 
 1. [Add metadata to your requests](/aigw/product/observability/metadata)

diff --git a/aigw/integrations/llms/bedrock/aws-bedrock.mdx b/aigw/integrations/llms/bedrock/aws-bedrock.mdx
@@ -581,10 +581,6 @@ Integration is identical to standard Bedrock. Only the endpoint changes — set
 
 ## Next Steps
 
-The complete list of features supported in the SDK are available on the link below.
-<Card title="SDK" href="/api-reference/sdk">
-</Card>
-
 You'll find more information in the relevant sections:
 
 1. [Add metadata to your requests](/aigw/product/observability/metadata)

diff --git a/aigw/integrations/llms/gemini.mdx b/aigw/integrations/llms/gemini.mdx
@@ -1395,10 +1395,6 @@ You can edit generated images by continuing the conversation. Pass the image dat
 
 <CardGroup cols={2}>
 
-<Card title="SDK Reference" icon="code" href="/api-reference/sdk/list">
-Complete SDK documentation and API reference
-</Card>
-
 <Card title="Add Metadata" icon="tag" href="/aigw/product/observability/metadata">
 Add metadata to your Gemini requests
 </Card>

diff --git a/aigw/integrations/llms/oracle.mdx b/aigw/integrations/llms/oracle.mdx
@@ -80,11 +80,6 @@ You can specify the API version using the `oracleApiVersion` parameter (defaults
 
 ## Next Steps
 
-The complete list of features supported in the SDK are available on the link below.
-
-<Card title="SDK" href="/api-reference/sdk">
-</Card>
-
 You'll find more information in the relevant sections:
 
 1. [Add metadata to your requests](/aigw/product/observability/metadata)

diff --git a/aigw/integrations/llms/vertex-ai.mdx b/aigw/integrations/llms/vertex-ai.mdx
@@ -2344,10 +2344,6 @@ environment:
 
 <CardGroup cols={2}>
 
-<Card title="SDK Reference" icon="code" href="/api-reference/sdk/list">
-Complete SDK documentation and API reference
-</Card>
-
 <Card title="Add Metadata" icon="tag" href="/aigw/product/observability/metadata">
 Add metadata to your Vertex AI requests
 </Card>

diff --git a/aigw/integrations/tracing-providers/honeyhive.mdx b/aigw/integrations/tracing-providers/honeyhive.mdx
@@ -281,7 +281,6 @@ def call_openai():
 
 - [HoneyHive Documentation](https://docs.honeyhive.ai)
 - [AI Gateway Guide](/aigw/product/ai-gateway)
-- [AI Gateway Python SDK Reference](/api-reference/sdk)
 
 <Note>
 For enterprise support and custom features, contact our [enterprise team](https://www.paloaltonetworks.com/ai-security/ai-gateway#:~:text=See%20Prisma%20AIRS%20AI%20Gateway%20in%20Action

diff --git a/aigw/integrations/tracing-providers/langfuse.mdx b/aigw/integrations/tracing-providers/langfuse.mdx
@@ -226,7 +226,6 @@ client = OpenAI(
 
 - [Langfuse Documentation](https://langfuse.com/docs)
 - [AI Gateway Guide](/aigw/product/ai-gateway)
-- [AI Gateway Python SDK Reference](/api-reference/sdk)
 
 <Note>
 For enterprise support and custom features, contact our [enterprise team](https://www.paloaltonetworks.com/ai-security/ai-gateway#:~:text=See%20Prisma%20AIRS%20AI%20Gateway%20in%20Action

diff --git a/aigw/integrations/tracing-providers/langsmith.mdx b/aigw/integrations/tracing-providers/langsmith.mdx
@@ -182,7 +182,6 @@ If you're already using LangSmith with OpenAI, migrating to use the AI Gateway i
 
 * [LangSmith Documentation](https://docs.smith.langchain.com/)
 * [AI Gateway Guide](/aigw/product/ai-gateway)
-* [AI Gateway Python SDK Reference](/api-reference/sdk)
 
 <Note>
   For enterprise support and custom features, contact our [enterprise team](https://www.paloaltonetworks.com/ai-security/ai-gateway#:~:text=See%20Prisma%20AIRS%20AI%20Gateway%20in%20Action

diff --git a/aigw/product/administration/enforce-workspace-budget-limts-and-rate-limits.mdx b/aigw/product/administration/enforce-workspace-budget-limts-and-rate-limits.mdx
@@ -113,12 +113,6 @@ Use the Admin API to programmatically manage workspace budgets and rate limits.
 - Rate limits support request- or token-based throttling with units `rpm` (per minute), `rph` (per hour), or `rpd` (per day).
 
 
-Learn more here:
-
-<Card title="AI Gateway Admin API" href="/api-reference/admin-api/control-plane/workspaces/update-workspace">
-AI Gateway Workspace API documentation
-</Card>
-
 ## Availability
 
 Workspace Budget Limits are available to AI Gateway Enterprise customers and select Pro users. To enable these features for your account, please contact [support@portkey.ai](mailto:support@portkey.ai).
diff --git a/aigw/product/ai-gateway.mdx b/aigw/product/ai-gateway.mdx
@@ -68,7 +68,7 @@ description: The world's fastest AI Gateway with advanced routing & integrated G
     Route requests to privately hosted or local models using custom host URLs
   </Card>
 
-  <Card title="Gateway to other APIs" href="/api-reference/inference-api/gateway-for-other-apis">
+  <Card title="Gateway to other APIs">
     Call rerank, video, listen, and other provider paths through https://aigw.portkey.ai/v1/... with the same configs and logging as unified routes
   </Card>
 </CardGroup>

diff --git a/aigw/product/ai-gateway/cache-simple-and-semantic.mdx b/aigw/product/ai-gateway/cache-simple-and-semantic.mdx
@@ -21,7 +21,7 @@ Cache LLM responses to serve requests up to **20x faster** and cheaper.
 
 ## Enable Cache
 
-Add `cache` to your [config object](/api-reference/config-object#cache-object-details):
+Add `cache` to your [config object](/aigw/api-reference/inference-api/config-object#cache-object-details):
 
 <CodeGroup>
 
@@ -162,7 +162,7 @@ To enable semantic caching on a self-hosted AI Gateway, configure the embedding
 
   </Step>
   <Step title="Enable semantic caching per request">
-    Set the cache mode to `semantic` in your [config object](/api-reference/config-object#cache-object-details) for each LLM request:
+    Set the cache mode to `semantic` in your [config object](/aigw/api-reference/inference-api/config-object#cache-object-details) for each LLM request:
 
     ```json
     { "cache": { "mode": "semantic" } }

diff --git a/aigw/product/ai-gateway/messages-api.mdx b/aigw/product/ai-gateway/messages-api.mdx
@@ -849,7 +849,7 @@ curl https://aigw.portkey.ai/v1/messages \
 
 ## API Reference
 
-- [Messages](/api-reference/inference-api/anthropic-transform) — `POST /v1/messages`
+- Messages — `POST /v1/messages`
 
 <CardGroup cols={2}>
   <Card
@@ -859,13 +859,6 @@ curl https://aigw.portkey.ai/v1/messages \
   >
     Anthropic specification
   </Card>
-  <Card
-    title="API Reference"
-    icon="code"
-    href="/api-reference/inference-api/anthropic-transform"
-  >
-    AI Gateway Messages API reference
-  </Card>
   <Card
     title="Universal API"
     icon="arrows-rotate"

diff --git a/aigw/product/ai-gateway/universal-api.mdx b/aigw/product/ai-gateway/universal-api.mdx
@@ -397,7 +397,7 @@ The AI Gateway blocks requests to private and reserved IP ranges by default to p
 
 ### Additional Endpoints
 
-- **[Gateway to Other APIs](/api-reference/inference-api/gateway-for-other-apis)** — Proxy requests to any provider endpoint
+- **Gateway to Other APIs** — Proxy requests to any provider endpoint
 - **[Assistants API](/api-reference/inference-api/assistants-api/assistants/create-assistant)** — OpenAI Assistants with persistent threads
 - **[Completions](/api-reference/inference-api/completions)** — Legacy text completion endpoint
 

diff --git a/aigw/product/enterprise-offering/org-management/api-keys-authn-and-authz.mdx b/aigw/product/enterprise-offering/org-management/api-keys-authn-and-authz.mdx
@@ -5,7 +5,7 @@ description: "Discover how Admin and Workspace API Keys are used to manage acces
 
 ## API Keys
 
-The AI Gateway uses two types of API keys to manage access to resources and operations: **Admin API Keys** and **Workspace API Keys**. These keys play crucial roles in authenticating and authorizing various operations within your [organisation](/aigw/product/enterprise-offering/org-management/organizations) and [workspaces](/api-reference/admin-api/control-plane/workspaces/create-workspace).
+The AI Gateway uses two types of API keys to manage access to resources and operations: **Admin API Keys** and **Workspace API Keys**. These keys play crucial roles in authenticating and authorizing various operations within your [organisation](/aigw/product/enterprise-offering/org-management/organizations) and [workspaces](/aigw/product/enterprise-offering/org-management/workspaces).
 
 ### Admin API Keys
 
@@ -458,5 +458,5 @@ Both types of API keys play important roles in the AI Gateway's security model,
 ### Related Topics
 
 <Card title="Organisations" href="/aigw/product/enterprise-offering/org-management/organizations"/>
-<Card title="Workspaces" href="/api-reference/admin-api/control-plane/workspaces/create-workspace"/>
+<Card title="Workspaces" href="/aigw/product/enterprise-offering/org-management/workspaces"/>
 <Card title="User Roles & Permissions" href="/aigw/product/enterprise-offering/org-management/user-roles-and-permissions"/>
diff --git a/aigw/product/enterprise-offering/org-management/user-roles-and-permissions.mdx b/aigw/product/enterprise-offering/org-management/user-roles-and-permissions.mdx
@@ -98,6 +98,6 @@ Organisation Owners and Admins can configure access permissions for various reso
 ## Related Topics
 
 <Card title="Organisations" href="/aigw/product/enterprise-offering/org-management/organizations"/>
-<Card title="Workspaces" href="/api-reference/admin-api/control-plane/workspaces/create-workspace"/>
+<Card title="Workspaces" href="/aigw/product/enterprise-offering/org-management/workspaces"/>
 <Card title="API Keys (AuthN and AuthZ)" href="/aigw/product/enterprise-offering/org-management/api-keys-authn-and-authz"/>
 <Card title="Access Control Management" href="/aigw/product/enterprise-offering/access-control-management"/>
diff --git a/aigw/product/enterprise-offering/org-management/workspaces.mdx b/aigw/product/enterprise-offering/org-management/workspaces.mdx
@@ -65,10 +65,6 @@ Once all resources have been removed, enter the workspace name in the confirmati
   Workspace deletion is permanent and cannot be undone
 </Warning>
 
-Alternatively you can also delete workspaces using the Admin API:
-
-<Card title="Delete a Workspace API" href="/api-reference/admin-api/control-plane/workspaces/delete-a-workspace"/>
-
 ### Related Topics
 
 <Card title="Organisations" href="/aigw/product/enterprise-offering/org-management/organizations"/>

diff --git a/aigw/product/observability/logs-export.mdx b/aigw/product/observability/logs-export.mdx
@@ -288,8 +288,6 @@ Here's a complete script that creates, starts, monitors, and downloads a log exp
 
 ### API reference
 
-For detailed API specifications, see the [Log Exports API reference](/api-reference/admin-api/data-plane/logs/log-exports-beta/create-a-log-export).
-
 | Endpoint | Description |
 |----------|-------------|
 | `POST /v1/logs/exports` | Create a new export job |