# Portkey AI Gateway

## Docs

- [Create Speech](https://mintlify.wiki/portkey-AI/gateway/api/audio/speech.md): POST /v1/audio/speech - Convert text to speech
- [Create Transcription](https://mintlify.wiki/portkey-AI/gateway/api/audio/transcriptions.md): POST /v1/audio/transcriptions - Convert speech to text
- [Create Translation](https://mintlify.wiki/portkey-AI/gateway/api/audio/translations.md): POST /v1/audio/translations - Translate speech to English text
- [Authentication](https://mintlify.wiki/portkey-AI/gateway/api/authentication.md): Authenticate requests to the Portkey AI Gateway
- [Cancel Batch](https://mintlify.wiki/portkey-AI/gateway/api/batches/cancel.md): Cancel a batch that is in progress
- [Create Batch](https://mintlify.wiki/portkey-AI/gateway/api/batches/create.md): Create a large batch of API requests for asynchronous processing
- [List Batches](https://mintlify.wiki/portkey-AI/gateway/api/batches/list.md): List all batches for your organization
- [Retrieve Batch](https://mintlify.wiki/portkey-AI/gateway/api/batches/retrieve.md): Retrieve the status and results of a batch request
- [Create Chat Completion](https://mintlify.wiki/portkey-AI/gateway/api/chat/completions.md): POST /v1/chat/completions - Generate chat completions
- [Streaming Chat Completions](https://mintlify.wiki/portkey-AI/gateway/api/chat/streaming.md): Stream chat completion responses in real-time
- [Create Completion](https://mintlify.wiki/portkey-AI/gateway/api/completions/create.md): POST /v1/completions - Generate text completions
- [Create Embeddings](https://mintlify.wiki/portkey-AI/gateway/api/embeddings/create.md): POST /v1/embeddings - Generate embeddings for text
- [Error Handling](https://mintlify.wiki/portkey-AI/gateway/api/errors.md): Error codes and responses from the Portkey AI Gateway
- [Delete File](https://mintlify.wiki/portkey-AI/gateway/api/files/delete.md): Delete a file
- [List Files](https://mintlify.wiki/portkey-AI/gateway/api/files/list.md): Returns a list of files that belong to the user's organization
- [Retrieve File](https://mintlify.wiki/portkey-AI/gateway/api/files/retrieve.md): Returns information about a specific file
- [Upload File](https://mintlify.wiki/portkey-AI/gateway/api/files/upload.md): Upload a file for use with fine-tuning or other operations
- [Fine-tuning Jobs](https://mintlify.wiki/portkey-AI/gateway/api/fine-tuning/jobs.md): Create and manage fine-tuning jobs for custom model training
- [Edit Images](https://mintlify.wiki/portkey-AI/gateway/api/images/edits.md): POST /v1/images/edits - Edit images with text prompts
- [Generate Images](https://mintlify.wiki/portkey-AI/gateway/api/images/generations.md): POST /v1/images/generations - Generate images from text prompts
- [Count Message Tokens](https://mintlify.wiki/portkey-AI/gateway/api/messages/count-tokens.md): Count the number of tokens in a message for Anthropic models
- [List Models](https://mintlify.wiki/portkey-AI/gateway/api/models/list.md): Retrieve a list of available models from the AI Gateway
- [API Overview](https://mintlify.wiki/portkey-AI/gateway/api/overview.md): Introduction to the Portkey AI Gateway API
- [Realtime WebSocket API](https://mintlify.wiki/portkey-AI/gateway/api/realtime/websocket.md): Bidirectional streaming communication with AI models via WebSocket
- [Caching](https://mintlify.wiki/portkey-AI/gateway/concepts/caching.md): Response caching mechanisms for performance and cost optimization
- [Configs](https://mintlify.wiki/portkey-AI/gateway/concepts/configs.md): Gateway configuration system for routing, retries, and guardrails
- [Guardrails](https://mintlify.wiki/portkey-AI/gateway/concepts/guardrails.md): Input and output validation with hooks and guardrails
- [Load Balancing](https://mintlify.wiki/portkey-AI/gateway/concepts/load-balancing.md): Distribute requests across providers and API keys with weighted load balancing
- [Providers](https://mintlify.wiki/portkey-AI/gateway/concepts/providers.md): Provider system architecture and integration patterns
- [Routing](https://mintlify.wiki/portkey-AI/gateway/concepts/routing.md): How the AI Gateway routes requests to LLM providers
- [Cloudflare Workers Deployment](https://mintlify.wiki/portkey-AI/gateway/deployment/cloudflare.md): Deploy Portkey AI Gateway to Cloudflare's edge network
- [Docker Deployment](https://mintlify.wiki/portkey-AI/gateway/deployment/docker.md): Deploy Portkey AI Gateway using Docker or Docker Compose
- [Enterprise Deployment](https://mintlify.wiki/portkey-AI/gateway/deployment/enterprise.md): Private cloud deployments with advanced features and dedicated support
- [Kubernetes Deployment](https://mintlify.wiki/portkey-AI/gateway/deployment/kubernetes.md): Deploy Portkey AI Gateway to Kubernetes clusters
- [Node.js Deployment](https://mintlify.wiki/portkey-AI/gateway/deployment/nodejs.md): Deploy Portkey AI Gateway as a standalone Node.js server
- [Deployment Options](https://mintlify.wiki/portkey-AI/gateway/deployment/overview.md): Choose the best deployment method for your Portkey AI Gateway
- [Fallbacks](https://mintlify.wiki/portkey-AI/gateway/features/fallbacks.md): Automatically fallback to backup providers when requests fail
- [Multi-Modal Support](https://mintlify.wiki/portkey-AI/gateway/features/multi-modal.md): Vision, audio, and image generation capabilities across 250+ LLMs
- [Realtime APIs (WebSocket)](https://mintlify.wiki/portkey-AI/gateway/features/realtime.md): Low-latency bidirectional communication with LLMs over WebSocket
- [Automatic Retries](https://mintlify.wiki/portkey-AI/gateway/features/retries.md): Automatically retry failed requests with exponential backoff
- [Streaming Responses](https://mintlify.wiki/portkey-AI/gateway/features/streaming.md): Stream responses from LLMs in real-time for better user experience
- [Request Timeouts](https://mintlify.wiki/portkey-AI/gateway/features/timeouts.md): Manage request duration and prevent hanging requests
- [Installation](https://mintlify.wiki/portkey-AI/gateway/installation.md): Deploy Portkey AI Gateway with your preferred method
- [Autogen Integration](https://mintlify.wiki/portkey-AI/gateway/integrations/autogen.md): Use Portkey AI Gateway with Microsoft Autogen for multi-agent conversations
- [CrewAI Integration](https://mintlify.wiki/portkey-AI/gateway/integrations/crewai.md): Use Portkey AI Gateway with CrewAI for orchestrated multi-agent systems
- [JavaScript/TypeScript SDK](https://mintlify.wiki/portkey-AI/gateway/integrations/javascript.md): Use Portkey's JavaScript SDK for production-ready LLM applications in Node.js and browsers
- [LangChain Integration](https://mintlify.wiki/portkey-AI/gateway/integrations/langchain.md): Use Portkey AI Gateway with LangChain for production-ready LLM applications
- [LlamaIndex Integration](https://mintlify.wiki/portkey-AI/gateway/integrations/llamaindex.md): Use Portkey AI Gateway with LlamaIndex for production-ready RAG applications
- [OpenAI SDK Integration](https://mintlify.wiki/portkey-AI/gateway/integrations/openai-sdk.md): Use Portkey AI Gateway as a drop-in replacement for OpenAI SDK
- [Integration Overview](https://mintlify.wiki/portkey-AI/gateway/integrations/overview.md): Connect Portkey AI Gateway with popular agent frameworks and SDKs
- [Phidata Integration](https://mintlify.wiki/portkey-AI/gateway/integrations/phidata.md): Use Portkey AI Gateway with Phidata for AI assistants with memory and knowledge
- [Python SDK](https://mintlify.wiki/portkey-AI/gateway/integrations/python.md): Use Portkey's native Python SDK for production-ready LLM applications
- [REST API](https://mintlify.wiki/portkey-AI/gateway/integrations/rest-api.md): Use Portkey AI Gateway directly via HTTP REST API for any programming language
- [Welcome to Portkey AI Gateway](https://mintlify.wiki/portkey-AI/gateway/introduction.md): A blazing fast AI Gateway routing to 250+ LLMs with sub-1ms latency
- [MCP Gateway Access Control](https://mintlify.wiki/portkey-AI/gateway/mcp/access-control.md): Configure granular team and user permissions for MCP servers and tools
- [MCP Gateway Authentication](https://mintlify.wiki/portkey-AI/gateway/mcp/authentication.md): Configure single authentication layer for all MCP servers at the gateway level
- [MCP Gateway Overview](https://mintlify.wiki/portkey-AI/gateway/mcp/overview.md): Centralized control plane for managing Model Context Protocol servers across your organization
- [MCP Gateway Quickstart](https://mintlify.wiki/portkey-AI/gateway/mcp/quickstart.md): Get started with MCP Gateway in under 10 minutes
- [Anthropic](https://mintlify.wiki/portkey-AI/gateway/providers/anthropic.md): Integrate Claude models from Anthropic including Claude 3.5 Sonnet, Claude 3 Opus, and Claude 3 Haiku
- [Anyscale](https://mintlify.wiki/portkey-AI/gateway/providers/anyscale.md): Access open-source models including Llama, Mixtral, and Mistral through Anyscale Endpoints
- [Azure OpenAI](https://mintlify.wiki/portkey-AI/gateway/providers/azure-openai.md): Integrate OpenAI models through Microsoft Azure with enterprise-grade security and compliance
- [AWS Bedrock](https://mintlify.wiki/portkey-AI/gateway/providers/bedrock.md): Integrate Claude, Llama, Mistral, and more through Amazon Bedrock with enterprise security
- [Cohere](https://mintlify.wiki/portkey-AI/gateway/providers/cohere.md): Integrate Cohere models including Command R, Command R+, and embeddings for enterprise NLP
- [DeepInfra](https://mintlify.wiki/portkey-AI/gateway/providers/deepinfra.md): Access 100+ models with cost-effective inference and fast deployment
- [Google Gemini](https://mintlify.wiki/portkey-AI/gateway/providers/google-gemini.md): Integrate Google Gemini models including Gemini 2.0 Flash, Gemini 1.5 Pro, and Gemini 1.5 Flash
- [Groq](https://mintlify.wiki/portkey-AI/gateway/providers/groq.md): Access ultra-fast LLM inference with Groq LPU technology - 500+ tokens/second
- [Mistral AI](https://mintlify.wiki/portkey-AI/gateway/providers/mistral.md): Integrate Mistral models including Mistral Large, Medium, and Small with function calling support
- [Ollama](https://mintlify.wiki/portkey-AI/gateway/providers/ollama.md): Run LLMs locally with Ollama - private, fast, and free
- [OpenAI](https://mintlify.wiki/portkey-AI/gateway/providers/openai.md): Integrate OpenAI models including GPT-4, GPT-3.5, o1, DALL-E, and Whisper through Portkey
- [Providers Overview](https://mintlify.wiki/portkey-AI/gateway/providers/overview.md): Learn how Portkey AI Gateway routes to 250+ LLMs from 78+ providers
- [Perplexity](https://mintlify.wiki/portkey-AI/gateway/providers/perplexity.md): Access Perplexity Sonar models with built-in web search and real-time information
- [Supported Providers](https://mintlify.wiki/portkey-AI/gateway/providers/supported-providers.md): Complete list of 78+ AI providers supported by Portkey AI Gateway
- [Together AI](https://mintlify.wiki/portkey-AI/gateway/providers/together-ai.md): Access 100+ open-source models including Llama, Mixtral, and Qwen with fast inference
- [Quickstart](https://mintlify.wiki/portkey-AI/gateway/quickstart.md): Get started with Portkey AI Gateway in under 5 minutes