# Swytcho

## Docs

- [Swytcho: Unified AI API for Developers — Overview](https://developer.swytcho.com/introduction.md): Swytcho gives developers a single, OpenAI-compatible API to access multiple AI models — build faster without managing separate integrations.
- [Quickstart Guide: Send Your First Swytcho API Request](https://developer.swytcho.com/quickstart.md): Make your first Swytcho API call in minutes — create an account, grab your API key, and send a chat completion request using curl, Python, or Node.js.
- [Swytcho API Authentication: Keys, Scopes & Security](https://developer.swytcho.com/authentication.md): Learn how to generate API keys, pass them as Bearer tokens, apply the right scopes, and follow security best practices to keep your integration safe.
- [Swytcho AI Models: Capabilities and Selection](https://developer.swytcho.com/concepts/models.md): Explore the AI models available on Swytcho, understand their capabilities and trade-offs, and choose the right model for your use case and budget.
- [Swytcho API Requests: Headers, Body, and Parameters](https://developer.swytcho.com/concepts/requests.md): Learn the base URL, required headers, request body schema, and key parameters needed to send well-formed requests to the Swytcho API.
- [Swytcho API Response Format: Fields and Finish Reasons](https://developer.swytcho.com/concepts/responses.md): Decode every field in a Swytcho API response — the envelope, choices array, usage object, finish reasons, and what each tells you about your completion.
- [Swytcho API Rate Limits: Tiers, Headers, and Retries](https://developer.swytcho.com/concepts/rate-limits.md): Understand Swytcho's rate limit tiers, read the limit headers in every response, handle 429 errors gracefully, and learn how to request a quota increase.
- [Swytcho Completions API: Generate Text from a Prompt](https://developer.swytcho.com/guides/text-generation.md): Use the Swytcho completions endpoint to generate text from a prompt. Control output length, creativity, and stopping behavior for any generation task.
- [Build Multi-Turn Conversations with Chat Completions](https://developer.swytcho.com/guides/chat-completions.md): Send a messages array to build multi-turn AI conversations. Manage roles, history, and context windows for production chatbots and AI assistants.
- [Stream AI Responses in Real Time with the Swytcho API](https://developer.swytcho.com/guides/streaming.md): Enable token-by-token streaming via server-sent events. Reduce latency and build chat interfaces that display AI output as it is generated in real time.
- [Function Calling: Connect AI to Your Tools with Swytcho](https://developer.swytcho.com/guides/function-calling.md): Define tools as JSON schemas so the model chooses when to call them. Build agents that fetch live data, run calculations, and interact with external APIs.
- [Generate Embeddings for Semantic Search with Swytcho](https://developer.swytcho.com/guides/embeddings.md): Convert text into dense vectors with the Swytcho embeddings endpoint. Power semantic search, RAG pipelines, clustering, and content recommendation systems.
- [Swytcho Integrations: Connect to Your Existing Stack](https://developer.swytcho.com/integrations/overview.md): Swytcho works with the tools you already use — from the OpenAI SDK to LangChain, LlamaIndex, and custom webhook integrations — with no code rewrites.
- [OpenAI SDK Compatibility: Use Swytcho as a Drop-In](https://developer.swytcho.com/integrations/openai-compatibility.md): Swytcho's API is fully OpenAI-compatible — swap your base URL and API key to access every Swytcho model through the SDK you already use.
- [Swytcho Webhooks: Receive Real-Time Event Notifications](https://developer.swytcho.com/integrations/webhooks.md): Configure Swytcho webhooks to receive real-time event notifications on your server, then verify HMAC signatures to process deliveries safely.
- [Swytcho SDKs, Client Libraries, and REST API Guide](https://developer.swytcho.com/resources/sdks.md): Access Swytcho's unified AI API using official Python and Node.js SDKs, the OpenAI SDK, or plain HTTP requests from any language or framework.
- [Swytcho API Error Codes and Troubleshooting Reference](https://developer.swytcho.com/resources/error-codes.md): Understand every HTTP status code and error object the Swytcho API returns, and learn how to handle failures gracefully in your application.
- [Swytcho API Frequently Asked Questions and Answers](https://developer.swytcho.com/resources/faq.md): Find quick answers to the most common questions about Swytcho's API, pricing, models, rate limits, data privacy, and production readiness.
- [Swytcho API Reference: Endpoints, SDKs & Conventions](https://developer.swytcho.com/api-reference/overview.md): Explore Swytcho's unified REST API for chat, completions, embeddings, and models — one base URL, one auth scheme, and full OpenAI SDK compatibility.
- [Swytcho API Authentication: Keys, Headers & Security](https://developer.swytcho.com/api-reference/authentication.md): Authenticate Swytcho API requests with a Bearer token, obtain and rotate API keys from the dashboard, and follow best practices to protect credentials.
- [POST /v1/chat/completions — Swytcho Chat API Reference](https://developer.swytcho.com/api-reference/chat.md): Send a list of messages and receive a model-generated reply. Supports multi-turn conversations, streaming, tool calls, and fine-grained sampling controls.
- [POST /v1/completions — Swytcho Text Completions API](https://developer.swytcho.com/api-reference/completions.md): Generate text by continuing a raw prompt string. Best for single-turn tasks: summarization, classification, code generation, and template-based workflows.
- [POST /v1/embeddings — Swytcho Text Embeddings API](https://developer.swytcho.com/api-reference/embeddings.md): Convert text into dense vector representations for semantic search, clustering, classification, and retrieval-augmented generation (RAG) pipelines.
- [GET /v1/models — List and Retrieve Models on Swytcho](https://developer.swytcho.com/api-reference/models.md): List all AI models your API key can access or retrieve details for a specific model ID, including ownership metadata and when it was added to the platform.