# Portrix docs

## Docs

- [Introduction to Portrix: Unified AI Gateway Platform](https://docs.portix.ai/introduction.md): Portrix is a unified AI gateway that routes requests to 400+ LLMs through a single OpenAI-compatible endpoint. Learn what Portrix is and how it works.
- [Portrix Quickstart: Make Your First AI API Request](https://docs.portix.ai/quickstart.md): Learn how to send your first AI request through Portrix. Get an API key, install the SDK, and call 400+ models in under 5 minutes.
- [Authenticate with Portrix: API Keys and Best Practices](https://docs.portix.ai/authentication.md): Learn how to create and manage API keys for Portrix. Send your key as a Bearer token in the Authorization header on every request.
- [Portrix Gateway: One Endpoint for 400+ AI Providers](https://docs.portix.ai/concepts/gateway.md): The Portrix gateway is a single API endpoint that proxies requests to 400+ AI providers. Understand how it sits between your app and every LLM provider.
- [Portrix Model Catalog: 400+ AI Models from Every Provider](https://docs.portix.ai/concepts/models.md): Portrix provides access to 400+ models from OpenAI, Anthropic, Google, Mistral, and more. Learn how models are identified and how to choose the right one.
- [Request Routing, Fallbacks, and Load Balancing in Portrix](https://docs.portix.ai/concepts/routing.md): Portrix automatically routes your requests to the right provider and handles fallbacks when a provider is unavailable. Learn how routing works.
- [Protocol Translation: OpenAI Format Across All AI Providers](https://docs.portix.ai/concepts/protocols.md): Portrix automatically converts your OpenAI-format requests to each provider's native API format. No per-provider SDK needed — one protocol for all models.
- [Send Your First AI Request via the Portrix Gateway](https://docs.portix.ai/guides/first-request.md): Walk through making your first AI model request using the Portrix gateway. Includes cURL, Python, and JavaScript examples you can run immediately.
- [Choosing the Right Model for Your Portrix Workload](https://docs.portix.ai/guides/model-selection.md): Compare speed, cost, and capability across 400+ models on Portrix. Learn how to pick the right model for chat, reasoning, embeddings, and vision tasks.
- [Configure AI Fallbacks and Load Balancing in Portrix](https://docs.portix.ai/guides/fallbacks-and-load-balancing.md): Set up automatic fallbacks and load balancing in Portrix to keep your AI application resilient when a provider experiences downtime or rate limits.
- [Portrix Managed Web Search for Grounded AI Answers](https://docs.portix.ai/guides/web-search.md): Use Portrix managed web search to ground AI responses in up-to-date information. Enable search with a single header — no external search API needed.
- [How to Stream AI Responses Using Server-Sent Events](https://docs.portix.ai/guides/streaming.md): Enable token-by-token streaming from any Portrix-connected model using the standard OpenAI streaming API. Works with all 400+ models and providers.
- [Use the OpenAI SDK with Portrix to Access 400+ Models](https://docs.portix.ai/integrations/openai-sdk.md): Portrix is a drop-in replacement for the OpenAI API. Change two lines of code to route all OpenAI SDK calls through Portrix and access 400+ models.
- [Connect to Portrix from Python Using the OpenAI Library](https://docs.portix.ai/integrations/python.md): Integrate Portrix into Python applications using the openai library or raw HTTP requests. Access 400+ models with minimal code changes.
- [Integrate Portrix into JavaScript and TypeScript Apps](https://docs.portix.ai/integrations/javascript.md): Integrate Portrix into Node.js and browser applications with the openai npm package. Includes TypeScript types, streaming, and async/await patterns.
- [Connect LangChain Chains and Agents to Portrix Gateway](https://docs.portix.ai/integrations/langchain.md): Connect LangChain to Portrix to access 400+ models in your chains and agents. Configure ChatOpenAI to point at the Portrix gateway.
- [Use the Vercel AI SDK to Stream Portrix Model Responses](https://docs.portix.ai/integrations/vercel-ai.md): Integrate Portrix into Next.js and Vercel applications using the Vercel AI SDK. Stream responses with useChat and access all 400+ models.
- [Configure AI Provider API Keys in Your Portrix Account](https://docs.portix.ai/configuration/providers.md): Connect your own API keys from OpenAI, Anthropic, Google, and other providers to Portrix. Route requests through your accounts for billing and control.
- [Portrix API Rate Limits, Quotas, and Usage Controls](https://docs.portix.ai/configuration/rate-limits.md): Learn about rate limits in Portrix — requests per minute, tokens per minute, and per-model quotas. See how to handle 429 errors and increase your limits.
- [Environment Variables for Portrix API Configuration](https://docs.portix.ai/configuration/environment-variables.md): Reference for the environment variables used to configure Portrix API access. Set PORTRIX_API_KEY and PORTRIX_BASE_URL in your application environment.
- [Common Questions About Using the Portrix AI Gateway](https://docs.portix.ai/help/faq.md): Answers to common questions about Portrix — model access, pricing, compatibility, API keys, and migrating from OpenAI or other providers.
- [Troubleshooting Common Portrix API Errors and Issues](https://docs.portix.ai/help/troubleshooting.md): Diagnose and fix the most common errors with the Portrix API: 401 auth failures, 429 rate limits, 404 model not found, and connection timeouts.
- [Supported AI Models and Providers Available in Portrix](https://docs.portix.ai/help/supported-models.md): Browse all 400+ AI models available through Portrix, organized by provider. Includes model IDs, context windows, and supported capabilities.
- [Portrix API Reference: Endpoints and Authentication](https://docs.portix.ai/api-reference/overview.md): Complete reference for the Portrix REST API. OpenAI-compatible endpoints for chat, completions, embeddings, and model listing at api.portrix.ai/v1.
- [Portrix API Authentication: Keys and Bearer Tokens](https://docs.portix.ai/api-reference/authentication.md): Authenticate Portrix API requests using Bearer tokens in the Authorization header. Get your API key from the dashboard at app.portrix.ai.
- [Portrix API Error Codes, Status Codes, and Retries](https://docs.portix.ai/api-reference/errors.md): Complete reference for Portrix API HTTP status codes and error response format. Covers 4xx client errors, 5xx server/provider errors, and retry guidance.
- [POST /v1/chat/completions — Chat Completions API](https://docs.portix.ai/api-reference/chat-completions.md): POST /v1/chat/completions — generate chat responses from 400+ models. Accepts messages array, model ID, temperature, max_tokens, and streaming flag.
- [POST /v1/completions — Legacy Text Completions API](https://docs.portix.ai/api-reference/completions.md): POST /v1/completions — legacy text completion endpoint for prompt-based models. Accepts a prompt string and returns generated text continuation.
- [POST /v1/embeddings — Generate Text Embeddings API](https://docs.portix.ai/api-reference/embeddings.md): POST /v1/embeddings — generate vector embeddings for text. Use openai/text-embedding-3-small or text-embedding-3-large for semantic search and retrieval.
- [GET /v1/models — List and Retrieve Available Models](https://docs.portix.ai/api-reference/models.md): GET /v1/models — retrieve a list of all AI models available through Portrix. Returns model IDs, owned_by provider, and capability metadata.