# LLM.kiwi documentation

> Beginner-friendly documentation for the free OpenAI-compatible LLM.kiwi API, with secure setup, working examples, reference material, and troubleshooting.

## Docs

- [API reference](https://docs.llm.kiwi/api-reference.md): Reference for the LLM.kiwi REST API: authentication, chat completion endpoints, request and response fields, headers, and HTTP status codes.
- [Best practices](https://docs.llm.kiwi/best-practices.md): Production tips for LLM.kiwi: secure API key storage, environment variables, timeouts, retries with backoff, output validation, and safe deployment.
- [Core concepts](https://docs.llm.kiwi/concepts.md): Beginner-friendly explanations of core LLM.kiwi concepts: APIs, HTTP requests, chat messages, roles, models, tokens, context windows, and streaming.
- [Error reference](https://docs.llm.kiwi/errors.md): Complete list of LLM.kiwi API error codes, their causes, safe retry strategies, and fixes for 400, 401, 403, 404, 429, and 5xx HTTP status responses.
- [Code examples](https://docs.llm.kiwi/examples.md): Copy-paste LLM.kiwi code examples in cURL, Python, and Node.js for chat completions, streaming responses, system prompts, and structured JSON output.
- [Frequently asked questions](https://docs.llm.kiwi/faq.md): Answers to common LLM.kiwi questions on free access, API keys, available models, rate limits, data privacy, OpenAI compatibility, and integration options.
- [Glossary](https://docs.llm.kiwi/glossary.md): Glossary of LLM and API terms used in the LLM.kiwi docs, including tokens, prompts, completions, context windows, streaming, roles, and rate limits.
- [LLM.kiwi documentation](https://docs.llm.kiwi/index.md): Get started with LLM.kiwi, the free OpenAI-compatible chat completion API. Learn to create a key, send your first request, and build real applications.
- [Limits and pricing](https://docs.llm.kiwi/limits.md): LLM.kiwi pricing and usage limits: free-tier access, per-minute rate limits, token quotas, request size caps, and fair-use throttling behavior explained.
- [Models](https://docs.llm.kiwi/models.md): Compare LLM.kiwi models: the automatic router that selects the best model per request and the Croatian-focused model tuned for local language tasks.
- [Quickstart](https://docs.llm.kiwi/quickstart.md): Step-by-step quickstart for LLM.kiwi: sign up for a free API key, store it safely in an environment variable, and send your first chat completion request.
- [SDKs and libraries](https://docs.llm.kiwi/sdks.md): Use LLM.kiwi from the official OpenAI Python and JavaScript SDKs by pointing the base URL at LLM.kiwi, or call the API directly over plain HTTP requests.
- [Troubleshooting](https://docs.llm.kiwi/troubleshooting.md): Fix common LLM.kiwi issues: 401 authentication failures, malformed requests, connection timeouts, SDK configuration errors, and broken streaming responses.
- [Use cases](https://docs.llm.kiwi/use-cases.md): Real-world LLM.kiwi use cases with prompts and patterns for chatbots, text summarization, data extraction, translation, and AI-assisted content generation.