diff --git a/aigw/api-reference/inference-api/config-object.mdx b/aigw/api-reference/inference-api/config-object.mdx index 24c5a452c..cc5d28cfe 100644 --- a/aigw/api-reference/inference-api/config-object.mdx +++ b/aigw/api-reference/inference-api/config-object.mdx @@ -735,13 +735,13 @@ You can find more examples of schemas [below](/aigw/api-reference/inference-api/ | Example | Description | |---------|-------------| | [Single Provider](#single-provider-with-provider-slug) | Basic setup with provider slug (recommended) | -| [With Hyperparameters](#provider-slug-with-model--hyperparameters) | Override model and parameters | +| [With Hyperparameters](#provider-slug-with-model-&-hyperparameters) | Override model and parameters | | [Cache + Retry](#provider-slug-with-cache-and-retry) | Enable caching and retry logic | | [Load Balancing](#load-balancing-with-provider-slugs) | Distribute traffic across providers | | [Fallback](#fallback-across-providers) | Automatic failover between providers | | [Combined Strategies](#load-balancing-and-fallback-combination) | Nested load balancing with fallback | | [Passthrough Target](#passthrough-target) | Defer provider resolution to the request | -| [Legacy: API Key](#legacy-single-provider-with-api-key) | Direct API key usage | +| [Legacy: API Key](#legacy-single-provider-with-virtual-key) | Direct API key usage | | [Legacy: Virtual Key](#legacy-single-provider-with-virtual-key) | Virtual key usage | --- diff --git a/aigw/api-reference/inference-api/headers.mdx b/aigw/api-reference/inference-api/headers.mdx index 50e8d0bee..bfd102898 100644 --- a/aigw/api-reference/inference-api/headers.mdx +++ b/aigw/api-reference/inference-api/headers.mdx @@ -20,7 +20,7 @@ Authenticate your requests with your AI Gateway API key, passed as `Bearer $PORT Environment variable: `PORTKEY_API_KEY` -The `x-portkey-api-key` header remains active and continues to authenticate requests. `Authorization` is the standard way to authenticate into the gateway; use `x-portkey-api-key` when `Authorization` is already carrying provider credentials, as in [Provider Slug + Auth](#1-provider-slug-auth) below. +The `x-portkey-api-key` header remains active and continues to authenticate requests. `Authorization` is the standard way to authenticate into the gateway; use `x-portkey-api-key` when `Authorization` is already carrying provider credentials, as in [Provider Slug + Auth](#1-provider-slug-+-auth) below. diff --git a/aigw/help-center/mcp-gateway-troubleshooting.mdx b/aigw/help-center/mcp-gateway-troubleshooting.mdx index 9286f636f..b8653bd44 100644 --- a/aigw/help-center/mcp-gateway-troubleshooting.mdx +++ b/aigw/help-center/mcp-gateway-troubleshooting.mdx @@ -35,7 +35,7 @@ MCP Gateway authenticates in two places: your client → Prisma AIRS AI Gateway | `401` | Missing/expired token, or the MCP server needs you to sign in | Re-authenticate; if prompted, complete the server's sign-in | | `403` | You're authenticated but not allowed | Wrong workspace/server in the URL, or you don't have access to that server | | `404` | Server not found | The slug in your URL is wrong, or the server isn't registered in this workspace | -| `500` "Unable to verify user access" | The gateway couldn't confirm your access | See [API key type](#can-t-connect-or-access-denied) below | +| `500` "Unable to verify user access" | The gateway couldn't confirm your access | See [API key type](#can’t-connect-or-access-denied) below | --- diff --git a/aigw/integrations/llms/azure-openai/batches.mdx b/aigw/integrations/llms/azure-openai/batches.mdx index aebd6ab59..fdd7eba6d 100644 --- a/aigw/integrations/llms/azure-openai/batches.mdx +++ b/aigw/integrations/llms/azure-openai/batches.mdx @@ -12,7 +12,7 @@ This is the most efficient way to The AI Gateway supports **two modes** on Azure OpenAI: * **[Provider Batch API](#using-azure-openai-batch-api-through-the-ai-gateway)** (cheapest, completion_window: `24h`, `48h`, etc.) -* **[AI Gateway Batch API](/aigw/product/ai-gateway/batches#portkey-batch-api-mode)** (fast, provider-agnostic, completion_window: `immediate`) +* **[AI Gateway Batch API](/aigw/product/ai-gateway/batches#provider-batch-api-mode)** (fast, provider-agnostic, completion_window: `immediate`) ## Using Azure OpenAI Batch API through the AI Gateway diff --git a/aigw/integrations/llms/bedrock/aws-bedrock.mdx b/aigw/integrations/llms/bedrock/aws-bedrock.mdx index 060de0c7a..166e59339 100644 --- a/aigw/integrations/llms/bedrock/aws-bedrock.mdx +++ b/aigw/integrations/llms/bedrock/aws-bedrock.mdx @@ -57,7 +57,7 @@ If you're using [AWS Security Token Service](https://docs.aws.amazon.com/STS/lat #### Not using Bedrock Provider from Model Catalog? -[Check out this example on how you can directly use your AWS details to make a Bedrock request through the AI Gateway.](/aigw/integrations/llms/bedrock/aws-bedrock#making-requests-without-using-portkey%E2%80%99s-model-catalog) +[Check out this example on how you can directly use your AWS details to make a Bedrock request through the AI Gateway.](/aigw/integrations/llms/bedrock/aws-bedrock#making-requests-without-using-the-ai-gateway’s-model-catalog) ### **3\. Invoke Chat Completions with AWS bedrock** diff --git a/aigw/integrations/llms/bedrock/batches.mdx b/aigw/integrations/llms/bedrock/batches.mdx index 9df47026a..a4420c08e 100644 --- a/aigw/integrations/llms/bedrock/batches.mdx +++ b/aigw/integrations/llms/bedrock/batches.mdx @@ -17,7 +17,7 @@ This is the most efficient way to The AI Gateway supports **two modes** on Bedrock: * **[Provider Batch API](#using-bedrock-batch-api-through-the-ai-gateway)** (cheapest, completion_window: `24h`, `48h`, etc.) -* **[AI Gateway Batch API ⭐️](/aigw/product/ai-gateway/batches#portkey-batch-api-mode)** (fast, provider-agnostic, completion_window: `immediate`) +* **[AI Gateway Batch API ⭐️](/aigw/product/ai-gateway/batches#provider-batch-api-mode)** (fast, provider-agnostic, completion_window: `immediate`) ## Before You Start diff --git a/aigw/integrations/llms/vertex-ai/batches.mdx b/aigw/integrations/llms/vertex-ai/batches.mdx index 1b6f0e32a..fabb180b3 100644 --- a/aigw/integrations/llms/vertex-ai/batches.mdx +++ b/aigw/integrations/llms/vertex-ai/batches.mdx @@ -17,7 +17,7 @@ With Prisma AIRS AI Gateway, you can perform batch inference operations with Ver The AI Gateway supports **two modes** on Vertex: * **[Provider Batch API](#using-vertex-batch-api-through-the-ai-gateway)** (cheapest, completion_window: `24h`, `48h`, etc.) -* **[AI Gateway Batch API](/aigw/product/ai-gateway/batches#portkey-batch-api-mode)** (fast, provider-agnostic, completion_window: `immediate`) +* **[AI Gateway Batch API](/aigw/product/ai-gateway/batches#provider-batch-api-mode)** (fast, provider-agnostic, completion_window: `immediate`) ## Using Vertex Batch API through the AI Gateway diff --git a/aigw/product/enterprise-offering/security.mdx b/aigw/product/enterprise-offering/security.mdx index 1de88240a..e58be5fb5 100644 --- a/aigw/product/enterprise-offering/security.mdx +++ b/aigw/product/enterprise-offering/security.mdx @@ -26,7 +26,7 @@ These encryption standards are part of our commitment to maintaining secure data Our access control measures are designed with granularity to offer precise control over who can see and manage data. -We provide [Role-Based Access Control (RBAC)](/aigw/product/enterprise-offering/access-control-management#id-2.-fine-grained-user-roles-and-permissions), allowing for stringent governance suited to complex organisational needs. +We provide [Role-Based Access Control (RBAC)](/aigw/product/enterprise-offering/access-control-management#2-fine-grained-user-roles-and-permissions), allowing for stringent governance suited to complex organisational needs. This system is pivotal for enforcing security policies and ensuring that only authorized personnel have access to sensitive operations and data. diff --git a/api-reference/inference-api/config-object.mdx b/api-reference/inference-api/config-object.mdx index 49100409a..1b3e04fa9 100644 --- a/api-reference/inference-api/config-object.mdx +++ b/api-reference/inference-api/config-object.mdx @@ -737,13 +737,13 @@ You can find more examples of schemas [below](/api-reference/inference-api/confi | Example | Description | |---------|-------------| | [Single Provider](#single-provider-with-provider-slug) | Basic setup with provider slug (recommended) | -| [With Hyperparameters](#provider-slug-with-model--hyperparameters) | Override model and parameters | +| [With Hyperparameters](#provider-slug-with-model-&-hyperparameters) | Override model and parameters | | [Cache + Retry](#provider-slug-with-cache-and-retry) | Enable caching and retry logic | | [Load Balancing](#load-balancing-with-provider-slugs) | Distribute traffic across providers | | [Fallback](#fallback-across-providers) | Automatic failover between providers | | [Combined Strategies](#load-balancing-and-fallback-combination) | Nested load balancing with fallback | | [Passthrough Target](#passthrough-target) | Defer provider resolution to the request | -| [Legacy: API Key](#legacy-single-provider-with-api-key) | Direct API key usage | +| [Legacy: API Key](#legacy-single-provider-with-virtual-key) | Direct API key usage | | [Legacy: Virtual Key](#legacy-single-provider-with-virtual-key) | Virtual key usage | --- diff --git a/changelog/enterprise.mdx b/changelog/enterprise.mdx index e5d1e23c1..630f4f80c 100644 --- a/changelog/enterprise.mdx +++ b/changelog/enterprise.mdx @@ -1279,7 +1279,7 @@ New `x-portkey-sensitive-headers` header (SDK aliases: `sensitive_headers` / `se `reasoning_effort` (`minimal` / `low` / `medium` / `high` / `none`) now works for Bedrock Claude reasoning models — mapped to adaptive thinking on Claude 4.6, and to `thinking.budget_tokens` on earlier reasoning models. -[Bedrock `reasoning_effort` Documentation](/integrations/llms/bedrock/aws-bedrock#using-reasoning-effort-parameter) +[Bedrock `reasoning_effort` Documentation](/integrations/llms/bedrock/aws-bedrock#using-reasoning_effort-parameter) ### Agent Gateway (Preview) @@ -1706,7 +1706,7 @@ Added support for Databricks Model Serving as a new provider with support for ch Together AI now supports reasoning/thinking models with `reasoning_effort` parameter and `content_blocks` in the response. When `strictOpenAiCompliance` is set to `false`, the response includes structured `content_blocks` with both thinking content and the final text response. Both streaming and non-streaming modes are supported. -[Together AI Documentation](/integrations/llms/together-ai#reasoning--thinking-support) +[Together AI Documentation](/integrations/llms/together-ai#reasoning-/-thinking-support) ### Fixes and Improvements - **Unified Messages & Responses API**: Fixed issues when a request config had a combination of native and non-native providers (e.g., load balancing across Anthropic and OpenAI). The adapter decision is now made per-provider, ensuring correct behavior for mixed configs. @@ -3158,7 +3158,7 @@ We are redacting this release and will be releasing a patch with out Workspace B - Updated the unified API signature for Extended thinking which was introduced in v1.10.12 to ensure that OpenAI compliant field of the response remain untouched regardless of strict_open_ai_compliance flag. - More Details: - [Anthropic](/integrations/llms/anthropic#extended-thinking-reasoning-models) - - [AWS Bedrock](/integrations/llms/bedrock/aws-bedrock#extended-thinking-reasoning-models) + - [AWS Bedrock](/integrations/llms/bedrock/aws-bedrock#extended-thinking-reasoning-models-beta) - [VertexAI](/integrations/llms/vertex-ai#extended-thinking-reasoning-models) ### Unified Batches API Improvements @@ -3210,7 +3210,7 @@ We are redacting this release and will be releasing a patch with out Workspace B - Introduced a unified API signature to support single-turn and multi-turn conversations with Anthropic Extended Reasoning across Anthropic, AWS Bedrock and VertexAI. - More Details: - [Anthropic](/integrations/llms/anthropic#extended-thinking-reasoning-models) - - [AWS Bedrock](/integrations/llms/bedrock/aws-bedrock#extended-thinking-reasoning-models) + - [AWS Bedrock](/integrations/llms/bedrock/aws-bedrock#extended-thinking-reasoning-models-beta) - [VertexAI](/integrations/llms/vertex-ai#extended-thinking-reasoning-models) ### Prometheus Metric Updates diff --git a/guides/use-cases/few-shot-prompting.mdx b/guides/use-cases/few-shot-prompting.mdx index e089e492e..1a780d4b5 100644 --- a/guides/use-cases/few-shot-prompting.mdx +++ b/guides/use-cases/few-shot-prompting.mdx @@ -65,7 +65,7 @@ In this configuration, `{{few_shot_examples}}` is a placeholder for the few-shot -1. Click on it and paste the [raw prompt code from above](/guides/use-cases/few-shot-prompting#this-is-how-our-raw-prompt-would-look). And that's it! You have your **dynamically updatable** few shot prompt template ready to deploy. +1. Click on it and paste the [raw prompt code from above](/guides/use-cases/few-shot-prompting#this-is-how-our-raw-prompt-looks). And that's it! You have your **dynamically updatable** few shot prompt template ready to deploy. ## Deploying the Prompt with Portkey diff --git a/help-center/mcp-gateway-troubleshooting.mdx b/help-center/mcp-gateway-troubleshooting.mdx index 62118c70d..d35cbffa5 100644 --- a/help-center/mcp-gateway-troubleshooting.mdx +++ b/help-center/mcp-gateway-troubleshooting.mdx @@ -35,7 +35,7 @@ MCP Gateway authenticates in two places: your client → Portkey (using your API | `401` | Missing/expired token, or the MCP server needs you to sign in | Re-authenticate; if prompted, complete the server's sign-in | | `403` | You're authenticated but not allowed | Wrong workspace/server in the URL, or you don't have access to that server | | `404` | Server not found | The slug in your URL is wrong, or the server isn't registered in this workspace | -| `500` "Unable to verify user access" | The gateway couldn't confirm your access | See [API key type](#can-t-connect-or-access-denied) below | +| `500` "Unable to verify user access" | The gateway couldn't confirm your access | See [API key type](#can’t-connect-or-access-denied) below | --- diff --git a/integrations/libraries/android-studio.mdx b/integrations/libraries/android-studio.mdx index ea79917ba..3218f7eca 100644 --- a/integrations/libraries/android-studio.mdx +++ b/integrations/libraries/android-studio.mdx @@ -13,7 +13,7 @@ description: 'Add observability, governance, and reliability to Android Studio w This guide shows how to add Portkey as a **Third-Party Remote Provider** in Android Studio in a few minutes. -For enterprise deployments across teams, see [Enterprise Governance](#3-enterprise-governance). +For enterprise deployments across teams, see [Enterprise Governance](#3-set-up-enterprise-governance). ## 1. Setup @@ -80,7 +80,7 @@ After adding Portkey as a provider: The models shown are the ones you added in Portkey (e.g. `@openai-prod/gpt-4o`, `@anthropic-prod/claude-3-5-sonnet-20241022`). All traffic is routed through Portkey automatically. -**Fallbacks, load balancing, or caching?** Create a [Portkey Config](/product/ai-gateway/configs), attach it to your API key, and use the config’s virtual model in Android Studio. See [Enterprise Governance](#3-enterprise-governance) for examples. +**Fallbacks, load balancing, or caching?** Create a [Portkey Config](/product/ai-gateway/configs), attach it to your API key, and use the config’s virtual model in Android Studio. See [Enterprise Governance](#3-set-up-enterprise-governance) for examples. import AdvancedFeatures from '/snippets/portkey-advanced-features.mdx'; diff --git a/integrations/libraries/anythingllm.mdx b/integrations/libraries/anythingllm.mdx index 085867a36..9b97dc27a 100644 --- a/integrations/libraries/anythingllm.mdx +++ b/integrations/libraries/anythingllm.mdx @@ -13,7 +13,7 @@ AnythingLLM is an all-in-one Desktop & Docker AI application with built-in RAG a This guide shows how to configure AnythingLLM with Portkey in under 5 minutes. - For enterprise deployments across teams, see [Enterprise Governance](#3-enterprise-governance). + For enterprise deployments across teams, see [Enterprise Governance](#3-set-up-enterprise-governance). # 1. Setup @@ -73,7 +73,7 @@ Change models by updating the **Chat Model** field: All requests route through Portkey automatically. -**Want fallbacks, load balancing, or caching?** Create a [Portkey Config](/product/ai-gateway/configs), attach it to your API key, and set Chat Model to `dummy`. See [Enterprise Governance](#3-enterprise-governance) for examples. +**Want fallbacks, load balancing, or caching?** Create a [Portkey Config](/product/ai-gateway/configs), attach it to your API key, and set Chat Model to `dummy`. See [Enterprise Governance](#3-set-up-enterprise-governance) for examples. import AdvancedFeatures from '/snippets/portkey-advanced-features.mdx'; diff --git a/integrations/libraries/cline.mdx b/integrations/libraries/cline.mdx index ac90fee84..8f3ad1591 100644 --- a/integrations/libraries/cline.mdx +++ b/integrations/libraries/cline.mdx @@ -14,7 +14,7 @@ Cline is an AI coding assistant for VS Code. Add Portkey to get: This guide shows how to configure Cline with Portkey in under 5 minutes. - For enterprise deployments across teams, see [Enterprise Governance](#3-enterprise-governance). + For enterprise deployments across teams, see [Enterprise Governance](#3-set-up-enterprise-governance). # 1. Setup @@ -82,7 +82,7 @@ Change models by updating the **Model ID** field: All requests route through Portkey automatically. -**Want fallbacks, load balancing, or caching?** Create a [Portkey Config](/product/ai-gateway/configs), attach it to your API key, and set Model ID to `dummy`. See [Enterprise Governance](#3-enterprise-governance) for examples. +**Want fallbacks, load balancing, or caching?** Create a [Portkey Config](/product/ai-gateway/configs), attach it to your API key, and set Model ID to `dummy`. See [Enterprise Governance](#3-set-up-enterprise-governance) for examples. import AdvancedFeatures from '/snippets/portkey-advanced-features.mdx'; diff --git a/integrations/libraries/codex.mdx b/integrations/libraries/codex.mdx index ba7b25717..4c6417527 100644 --- a/integrations/libraries/codex.mdx +++ b/integrations/libraries/codex.mdx @@ -13,7 +13,7 @@ description: 'Add usage tracking, cost controls, and security guardrails to Code Configure Codex with Portkey in a few minutes. - For enterprise deployments across teams, see [Enterprise Governance](#3-enterprise-governance). + For enterprise deployments across teams, see [Enterprise Governance](#3-set-up-enterprise-governance). ## Quick setup with CLI @@ -185,7 +185,7 @@ wire_api = "chat" -**Fallbacks, load balancing, or caching?** Create a [Portkey Config](/product/ai-gateway/configs), attach it to your API key, and set `model` to the config’s virtual model. See [Enterprise Governance](#3-enterprise-governance) for examples. +**Fallbacks, load balancing, or caching?** Create a [Portkey Config](/product/ai-gateway/configs), attach it to your API key, and set `model` to the config’s virtual model. See [Enterprise Governance](#3-set-up-enterprise-governance) for examples. import AdvancedFeatures from '/snippets/portkey-advanced-features.mdx'; diff --git a/integrations/libraries/conductor.mdx b/integrations/libraries/conductor.mdx index 75967e8d6..191575d19 100644 --- a/integrations/libraries/conductor.mdx +++ b/integrations/libraries/conductor.mdx @@ -11,7 +11,7 @@ description: 'Add usage tracking, cost controls, and security guardrails to Cond - **Governance** — budget limits, usage tracking, and team access controls - For enterprise deployments across teams, see [Enterprise Governance](#3-enterprise-governance). + For enterprise deployments across teams, see [Enterprise Governance](#3-set-up-enterprise-governance). ## 1. Setup diff --git a/integrations/libraries/continue-dev.mdx b/integrations/libraries/continue-dev.mdx index 9a5976b61..4574bc363 100644 --- a/integrations/libraries/continue-dev.mdx +++ b/integrations/libraries/continue-dev.mdx @@ -13,7 +13,7 @@ Continue.dev is an open-source AI coding assistant for VS Code and JetBrains. Ad This guide shows how to configure Continue.dev with Portkey in under 5 minutes. - For enterprise deployments across teams, see [Enterprise Governance](#3-enterprise-governance). + For enterprise deployments across teams, see [Enterprise Governance](#3-set-up-enterprise-governance). --- @@ -258,7 +258,7 @@ models: ``` -**Want fallbacks, load balancing, or caching?** Create a [Portkey Config](/product/ai-gateway/configs), attach it to your API key, and set `x-portkey-config` to your Config ID in `requestOptions.headers`. See [Enterprise Governance](#3-enterprise-governance) for examples. +**Want fallbacks, load balancing, or caching?** Create a [Portkey Config](/product/ai-gateway/configs), attach it to your API key, and set `x-portkey-config` to your Config ID in `requestOptions.headers`. See [Enterprise Governance](#3-set-up-enterprise-governance) for examples. --- diff --git a/integrations/libraries/cursor.mdx b/integrations/libraries/cursor.mdx index 2f04ab62c..c527d210b 100644 --- a/integrations/libraries/cursor.mdx +++ b/integrations/libraries/cursor.mdx @@ -15,7 +15,7 @@ description: "Add observability, governance, and reliability to Cursor with Port - For enterprise governance, see [Enterprise Governance](#enterprise-governance). + For enterprise governance, see [Enterprise Governance](#3-set-up-enterprise-governance). ## 1. Setup diff --git a/integrations/libraries/goose.mdx b/integrations/libraries/goose.mdx index 064ddadf4..ea7672915 100644 --- a/integrations/libraries/goose.mdx +++ b/integrations/libraries/goose.mdx @@ -13,7 +13,7 @@ Goose is an open source AI agent that automates engineering tasks. Add Portkey t This guide shows how to configure Goose with Portkey in under 5 minutes. - For enterprise deployments across teams, see [Enterprise Governance](#3-enterprise-governance). + For enterprise deployments across teams, see [Enterprise Governance](#3-set-up-enterprise-governance). # 1. Setup @@ -72,7 +72,7 @@ Change models by updating the model field: All requests route through Portkey automatically. -**Want fallbacks, load balancing, or caching?** Create a [Portkey Config](/product/ai-gateway/configs), attach it to your API key, and set Model to `dummy`. See [Enterprise Governance](#3-enterprise-governance) for examples. +**Want fallbacks, load balancing, or caching?** Create a [Portkey Config](/product/ai-gateway/configs), attach it to your API key, and set Model to `dummy`. See [Enterprise Governance](#3-set-up-enterprise-governance) for examples. import AdvancedFeatures from '/snippets/portkey-advanced-features.mdx'; diff --git a/integrations/libraries/janhq.mdx b/integrations/libraries/janhq.mdx index f95b994db..3403c4eb3 100644 --- a/integrations/libraries/janhq.mdx +++ b/integrations/libraries/janhq.mdx @@ -13,7 +13,7 @@ Jan is an open source alternative to ChatGPT that runs 100% offline on your comp This guide shows how to configure Jan with Portkey in under 5 minutes. - For enterprise deployments across teams, see [Enterprise Governance](#3-enterprise-governance). + For enterprise deployments across teams, see [Enterprise Governance](#3-set-up-enterprise-governance). # 1. Setup @@ -69,7 +69,7 @@ Change models by updating the model selection: All requests route through Portkey automatically. -**Want fallbacks, load balancing, or caching?** Create a [Portkey Config](/product/ai-gateway/configs), attach it to your API key, and set Model to `dummy`. See [Enterprise Governance](#3-enterprise-governance) for examples. +**Want fallbacks, load balancing, or caching?** Create a [Portkey Config](/product/ai-gateway/configs), attach it to your API key, and set Model to `dummy`. See [Enterprise Governance](#3-set-up-enterprise-governance) for examples. import AdvancedFeatures from '/snippets/portkey-advanced-features.mdx'; diff --git a/integrations/libraries/langflow.mdx b/integrations/libraries/langflow.mdx index 7e9c21925..c2ca79b90 100644 --- a/integrations/libraries/langflow.mdx +++ b/integrations/libraries/langflow.mdx @@ -11,7 +11,7 @@ Langflow is an open-source visual framework for building multi-agent and RAG app - **Guardrails** — PII detection, content filtering, compliance controls -For enterprise governance setup, see [Enterprise Governance](#enterprise-governance). +For enterprise governance setup, see [Enterprise Governance](#3-set-up-enterprise-governance). ## Quick Start diff --git a/integrations/libraries/librechat.mdx b/integrations/libraries/librechat.mdx index 963e5cb8b..25c2df003 100644 --- a/integrations/libraries/librechat.mdx +++ b/integrations/libraries/librechat.mdx @@ -10,7 +10,7 @@ Add Portkey to LibreChat to get: - **Security guardrails** for PII detection and content filtering -For enterprise governance setup, see [Enterprise Governance](#3-enterprise-governance). +For enterprise governance setup, see [Enterprise Governance](#3-set-up-enterprise-governance). ## 1. Setup Portkey diff --git a/integrations/libraries/n8n.mdx b/integrations/libraries/n8n.mdx index af0e682ea..da1c1c926 100644 --- a/integrations/libraries/n8n.mdx +++ b/integrations/libraries/n8n.mdx @@ -11,7 +11,7 @@ n8n is a workflow automation platform. Portkey adds enterprise controls for prod - **Guardrails** — PII detection, content filtering, compliance controls -For enterprise governance setup, see [Enterprise Governance](#enterprise-governance). +For enterprise governance setup, see [Enterprise Governance](#3-set-up-enterprise-governance). ## Quick Start diff --git a/integrations/libraries/roo-code.mdx b/integrations/libraries/roo-code.mdx index 2c6413f6f..3a821270b 100644 --- a/integrations/libraries/roo-code.mdx +++ b/integrations/libraries/roo-code.mdx @@ -13,7 +13,7 @@ Roo is an AI coding assistant for VS Code. Add Portkey to get: This guide shows how to configure Roo with Portkey in under 5 minutes. - For enterprise deployments across teams, see [Enterprise Governance](#3-enterprise-governance). + For enterprise deployments across teams, see [Enterprise Governance](#3-set-up-enterprise-governance). # 1. Setup @@ -83,7 +83,7 @@ Change models by updating the **Model** field: All requests route through Portkey automatically. -**Want fallbacks, load balancing, or caching?** Create a [Portkey Config](/product/ai-gateway/configs), attach it to your API key, and set Model to `dummy`. See [Enterprise Governance](#3-enterprise-governance) for examples. +**Want fallbacks, load balancing, or caching?** Create a [Portkey Config](/product/ai-gateway/configs), attach it to your API key, and set Model to `dummy`. See [Enterprise Governance](#3-set-up-enterprise-governance) for examples. diff --git a/integrations/libraries/zed.mdx b/integrations/libraries/zed.mdx index ed4b417e0..6ef313dae 100644 --- a/integrations/libraries/zed.mdx +++ b/integrations/libraries/zed.mdx @@ -13,7 +13,7 @@ Zed is a next-generation code editor built for AI-powered development. Add Portk This guide shows how to configure Zed with Portkey in under 5 minutes. - For enterprise deployments across teams, see [Enterprise Governance](#3-enterprise-governance). + For enterprise deployments across teams, see [Enterprise Governance](#3-set-up-enterprise-governance). # 1. Setup @@ -87,7 +87,7 @@ Add more models to your `available_models` array: All requests route through Portkey automatically. -**Want fallbacks, load balancing, or caching?** Create a [Portkey Config](/product/ai-gateway/configs), attach it to your API key, and set model name to `dummy`. See [Enterprise Governance](#3-enterprise-governance) for examples. +**Want fallbacks, load balancing, or caching?** Create a [Portkey Config](/product/ai-gateway/configs), attach it to your API key, and set model name to `dummy`. See [Enterprise Governance](#3-set-up-enterprise-governance) for examples. import AdvancedFeatures from '/snippets/portkey-advanced-features.mdx'; diff --git a/integrations/llms/azure-openai/batches.mdx b/integrations/llms/azure-openai/batches.mdx index 9f922fa1d..1a970d157 100644 --- a/integrations/llms/azure-openai/batches.mdx +++ b/integrations/llms/azure-openai/batches.mdx @@ -13,7 +13,7 @@ This is the most efficient way to Portkey supports **two modes** on Azure OpenAI: * **[Provider Batch API](#using-azure-openai-batch-api-through-portkey)** (cheapest, completion_window: `24h`, `48h`, etc.) -* **[Portkey Batch API](/product/ai-gateway/batches#portkey-batch-api-mode)** (fast, provider-agnostic, completion_window: `immediate`) +* **[Portkey Batch API](/product/ai-gateway/batches#provider-batch-api-mode)** (fast, provider-agnostic, completion_window: `immediate`) ## Using Azure OpenAI Batch API through Portkey diff --git a/integrations/llms/bedrock/batches.mdx b/integrations/llms/bedrock/batches.mdx index c58853f0f..367d3ac20 100644 --- a/integrations/llms/bedrock/batches.mdx +++ b/integrations/llms/bedrock/batches.mdx @@ -17,7 +17,7 @@ This is the most efficient way to Portkey supports **two modes** on Bedrock: * **[Provider Batch API](#using-bedrock-batch-api-through-portkey)** (cheapest, completion_window: `24h`, `48h`, etc.) -* **[Portkey Batch API ⭐️](/product/ai-gateway/batches#portkey-batch-api-mode)** (fast, provider-agnostic, completion_window: `immediate`) +* **[Portkey Batch API ⭐️](/product/ai-gateway/batches#provider-batch-api-mode)** (fast, provider-agnostic, completion_window: `immediate`) ## Before You Start diff --git a/integrations/llms/openai3.mdx b/integrations/llms/openai3.mdx index 7c511dfa2..b06a1ffba 100644 --- a/integrations/llms/openai3.mdx +++ b/integrations/llms/openai3.mdx @@ -17,8 +17,8 @@ Your OpenAI personal or service account API keys can be saved to Portkey. Additi Optional -- Add your OpenAI organization and project ID details: ([Docs](#openai-projects-and-organizations)) -- Directly use OpenAI API key without Model Catalog: ([Docs](/api-reference/inference-api/headers#1-provider-slug-auth)) +- Add your OpenAI organization and project ID details: ([Docs](#openai-projects-&-organizations)) +- Directly use OpenAI API key without Model Catalog: ([Docs](/api-reference/inference-api/headers#1-provider-slug-+-auth)) - Set budget & rate limits per AI Provider: ([Docs](/product/model-catalog)) diff --git a/integrations/llms/vertex-ai/batches.mdx b/integrations/llms/vertex-ai/batches.mdx index 49c6400bb..0e0165c26 100644 --- a/integrations/llms/vertex-ai/batches.mdx +++ b/integrations/llms/vertex-ai/batches.mdx @@ -17,7 +17,7 @@ With Portkey, you can perform batch inference operations with Vertex AI models. Portkey supports **two modes** on Vertex: * **[Provider Batch API](#using-vertex-batch-api-through-portkey)** (cheapest, completion_window: `24h`, `48h`, etc.) -* **[Portkey Batch API](/product/ai-gateway/batches#portkey-batch-api-mode)** (fast, provider-agnostic, completion_window: `immediate`) +* **[Portkey Batch API](/product/ai-gateway/batches#provider-batch-api-mode)** (fast, provider-agnostic, completion_window: `immediate`) ## Using Vertex Batch API through Portkey diff --git a/product/ai-gateway/batches.mdx b/product/ai-gateway/batches.mdx index 5030a4d6e..bc5d71e02 100644 --- a/product/ai-gateway/batches.mdx +++ b/product/ai-gateway/batches.mdx @@ -14,7 +14,7 @@ Portkey's AI Gateway lets you send a single request that fan‑outs to hundreds | Mode | When to pick it | Works with | | ---------------------- | -------------------------- | ------------ | | **[Provider Batch API](#provider-batch-api-mode)** | *Cheapest* for overnight or offline jobs. Uses the provider's native batch endpoint & limits.| `OpenAI`, `Azure OpenAI`, `Bedrock`, `Vertex` | -| **[Portkey Batch API](#portkey-batch-api-mode)** | *Fastest* and provider‑agnostic. Batches at the Gateway layer; ideal when a provider has no native batch support or you need cross‑provider jobs. | Any provider supported by Portkey Gateway | +| **[Portkey Batch API](#provider-batch-api-mode)** | *Fastest* and provider‑agnostic. Batches at the Gateway layer; ideal when a provider has no native batch support or you need cross‑provider jobs. | Any provider supported by Portkey Gateway | Quick rule of thumb →
Need low latency or multi‑provider batching? **Portkey Batch API**. Otherwise, stick with the provider's native batch for cost savings. diff --git a/product/enterprise-offering/security-portkey.mdx b/product/enterprise-offering/security-portkey.mdx index 903e92c4e..1e0941352 100644 --- a/product/enterprise-offering/security-portkey.mdx +++ b/product/enterprise-offering/security-portkey.mdx @@ -26,7 +26,7 @@ These encryption standards are part of our commitment to maintaining secure data Our access control measures are designed with granularity to offer precise control over who can see and manage data. -For enterprise clients, we provide enhanced [Role-Based Access Control (RBAC)](/product/enterprise-offering/access-control-management#id-2.-fine-grained-user-roles-and-permissions), allowing for stringent governance suited to complex organizational needs. +For enterprise clients, we provide enhanced [Role-Based Access Control (RBAC)](/product/enterprise-offering/access-control-management#2-fine-grained-user-roles-and-permissions), allowing for stringent governance suited to complex organizational needs. This system is pivotal for enforcing security policies and ensuring that only authorized personnel have access to sensitive operations and data. diff --git a/support/portkeys-december-migration.mdx b/support/portkeys-december-migration.mdx index 14f3b1e2b..3a5409d6b 100644 --- a/support/portkeys-december-migration.mdx +++ b/support/portkeys-december-migration.mdx @@ -17,7 +17,7 @@ This is a **Breaking Change** that **Requires Migration**. - [**Configs**](/support/portkeys-december-migration#configs-2.0) are upgraded to _**version**_ _**2.0**_, bringing nested gateway strategies with granular handling. For Configs saved in the Portkey dashboard, this is **NOT a Breaking Change** and we will **Auto Migrate** your old Configs. For Configs directly defined at the time of making a call, through the old SDKs or old APIS, they **will fail** on the new APIs & SDKs and **require migration**. + [**Configs**](/support/portkeys-december-migration#configs-2-0) are upgraded to _**version**_ _**2.0**_, bringing nested gateway strategies with granular handling. For Configs saved in the Portkey dashboard, this is **NOT a Breaking Change** and we will **Auto Migrate** your old Configs. For Configs directly defined at the time of making a call, through the old SDKs or old APIS, they **will fail** on the new APIs & SDKs and **require migration**. diff --git a/virtual_key_old/integrations/libraries/n8n.mdx b/virtual_key_old/integrations/libraries/n8n.mdx index 6c6ae54c5..9f3f71b6b 100644 --- a/virtual_key_old/integrations/libraries/n8n.mdx +++ b/virtual_key_old/integrations/libraries/n8n.mdx @@ -89,7 +89,7 @@ Save your API key securely - you'll need it for n8n integration. Now that you have your Portkey components set up, let's connect them to n8n. Since Portkey provides OpenAI API compatibility, integration is straightforward and requires just a few configuration steps in your n8n workflow. -You need your Portkey API Key from [Step 1](#Setting-up-portkey) before going further. +You need your Portkey API Key from [Step 1](#1-setting-up-portkey) before going further. 1. In your n8n workflow, add the OpenAI node where you want to use an LLM diff --git a/virtual_key_old/integrations/libraries/zed.mdx b/virtual_key_old/integrations/libraries/zed.mdx index 75e27b4e2..914320716 100644 --- a/virtual_key_old/integrations/libraries/zed.mdx +++ b/virtual_key_old/integrations/libraries/zed.mdx @@ -83,7 +83,7 @@ Save your API key securely - you'll need it for Zed integration. ## 2. Integrated Portkey with Zed - You will need your Portkey API key created in [Step 1](#Setting-up-portkey) for this integration + You will need your Portkey API key created in [Step 1](#1-setting-up-portkey) for this integration Portkey is an OpenAI compatible API, which means it can be easily integrated with zed without any changes to your setup. Here's how you do it diff --git a/virtual_key_old/integrations/llms/openai3.mdx b/virtual_key_old/integrations/llms/openai3.mdx index 43513f499..4a065f2b1 100644 --- a/virtual_key_old/integrations/llms/openai3.mdx +++ b/virtual_key_old/integrations/llms/openai3.mdx @@ -19,8 +19,8 @@ Your OpenAI personal or service account API keys can be saved to Portkey. Additi Optional -- Add your OpenAI organization and project ID details: ([Docs](#openai-projects-and-organizations)) -- Directly use OpenAI API key without the Virtual Key: ([Docs](/api-reference/inference-api/headers#1-provider-slug-auth)) +- Add your OpenAI organization and project ID details: ([Docs](#openai-projects-&-organizations)) +- Directly use OpenAI API key without the Virtual Key: ([Docs](/api-reference/inference-api/headers#1-provider-slug-+-auth)) - Create a short-lived virtual key OR one with usage/rate limits: ([Docs](/product/ai-gateway/virtual-keys)) diff --git a/virtual_key_old/product/enterprise-offering/security-portkey.mdx b/virtual_key_old/product/enterprise-offering/security-portkey.mdx index 69adf0ba9..28f097ca8 100644 --- a/virtual_key_old/product/enterprise-offering/security-portkey.mdx +++ b/virtual_key_old/product/enterprise-offering/security-portkey.mdx @@ -26,7 +26,7 @@ These encryption standards are part of our commitment to maintaining secure data Our access control measures are designed with granularity to offer precise control over who can see and manage data. -For enterprise clients, we provide enhanced [Role-Based Access Control (RBAC)](/product/enterprise-offering/access-control-management#id-2.-fine-grained-user-roles-and-permissions), allowing for stringent governance suited to complex organizational needs. +For enterprise clients, we provide enhanced [Role-Based Access Control (RBAC)](/product/enterprise-offering/access-control-management#2-fine-grained-user-roles-and-permissions), allowing for stringent governance suited to complex organizational needs. This system is pivotal for enforcing security policies and ensuring that only authorized personnel have access to sensitive operations and data.