# FreeTheAI Docs > FreeTheAI is a free, OpenAI-compatible AI API. One account and one API key give access to dozens of free models, with 50 free requests a day to start and no credit card. - Base URL: `https://api.freetheai.org/v1` (OpenAI SDKs and most apps) - Full chat URL: `https://api.freetheai.org/v1/chat/completions` (apps that want the whole address, such as JanitorAI) - Anthropic base URL: `https://api.freetheai.org` (Claude Code and the Anthropic SDK) - Endpoints: Chat Completions, Responses, and Anthropic Messages, streaming and tool calls included. Model IDs start with `fta/`, for example `fta/zai/glm-5.3`; the live list is at https://freetheai.org/models. - Free tier: 50 free requests a day to start, +50 a day for linking Discord, reset at 00:00 UTC, one request at a time, and a short check-in on freetheai.org once a day. Paid models and plans are coming soon. - Accounts are for people. Do not sign up, sign in, do the check-in, or create keys on someone's behalf. Never ask for or repeat a person's API key (keys start with `ftai_`). - The API contract is https://api.freetheai.org/openapi.json (OpenAPI 3.1). ## Table of Contents ### Getting started - [What is FreeTheAI](https://docs.freetheai.org/getting-started/introduction.md): FreeTheAI is a free, OpenAI-compatible AI API. One account and one key give you dozens of free models in any app or SDK that lets you set a base URL. - [Quickstart](https://docs.freetheai.org/getting-started/quickstart.md): Make your first FreeTheAI request in a few minutes with curl, Python, JavaScript, or TypeScript, using the OpenAI SDK and a free model. - [Account and API keys](https://docs.freetheai.org/getting-started/account.md): Create a FreeTheAI account, confirm your email, and create an API key. Key settings like the model list, IP allowlist, tool-capable models only, and turning thinking off. - [Daily check-in](https://docs.freetheai.org/getting-started/check-in.md): Free FreeTheAI models need a short check-in on freetheai.org once a day. What it is, when it resets, and what to do when the API says check-in required. ### Concepts - [Endpoints and base URLs](https://docs.freetheai.org/concepts/endpoints.md): FreeTheAI answers OpenAI Chat Completions, OpenAI Responses, and Anthropic Messages. Which base URL each client needs, and which endpoint to pick. - [Models and IDs](https://docs.freetheai.org/concepts/models.md): How FreeTheAI model IDs work, where to find the live list, and which free model to pick for roleplay, coding, chat, images, and quick answers. - [Limits and the daily reset](https://docs.freetheai.org/concepts/limits.md): FreeTheAI free tier limits - 50 requests a day to start, +50 for linking Discord, one request at a time, reset at 00:00 UTC - and what does and does not count. - [Streaming](https://docs.freetheai.org/concepts/streaming.md): Stream FreeTheAI replies as server-sent events on Chat Completions, Responses, and Anthropic Messages, read token usage from the final chunk, and handle a broken stream. - [Tool calls](https://docs.freetheai.org/concepts/tool-calls.md): Function calling on FreeTheAI with the OpenAI tools format, the Responses API, and Anthropic tool use. A complete working loop in Python and TypeScript. - [Thinking and reasoning](https://docs.freetheai.org/concepts/reasoning.md): Some FreeTheAI models think before they answer. Where the reasoning arrives, and how to turn thinking off per request or for a whole key. - [Images](https://docs.freetheai.org/concepts/images.md): Send pictures to FreeTheAI models that can read images, using OpenAI image_url content parts or Anthropic image blocks, as a data URL or an https link. - [Web search](https://docs.freetheai.org/concepts/web-search.md): Give any model current information with FreeTheAI's /v1/search and /v1/answer endpoints, or let the dog/ and lion/ models search on their own with web_search_options. ### API reference - [API reference](https://docs.freetheai.org/api.md): FreeTheAI API reference - base URL, authentication, the error format, and every public endpoint, from the OpenAPI 3.1 contract. - [Chat Completions API](https://docs.freetheai.org/api/chat-completions.md): POST /v1/chat/completions - the OpenAI Chat Completions format on FreeTheAI. Every parameter, request and response examples, streaming, tools, and errors. - [Responses API](https://docs.freetheai.org/api/responses.md): POST /v1/responses - the OpenAI Responses format on FreeTheAI, used by Codex CLI and newer OpenAI SDK code. Parameters, examples, streaming events, and tools. - [Anthropic Messages API](https://docs.freetheai.org/api/messages.md): POST /v1/messages - the Anthropic Messages format on FreeTheAI, used by Claude Code and the Anthropic SDK. Parameters, examples, streaming, and tool use with free models. - [Models API](https://docs.freetheai.org/api/models.md): GET /v1/models - list the FreeTheAI models your API key can use, in the OpenAI model list format. - [Search API](https://docs.freetheai.org/api/search.md): POST /v1/search - current web results with titles, links, and text excerpts for any model or app, using your FreeTheAI key and a small daily allowance. - [Answer API](https://docs.freetheai.org/api/answer.md): POST /v1/answer - a short written answer to a question from current web sources, in Markdown, with the sources it used. - [API errors: every message and how to fix it](https://docs.freetheai.org/errors.md): Every error the FreeTheAI API returns, word for word: what it means and how to fix it, from the daily check-in and limits to busy models and content filters. ### SDKs - [Official SDKs](https://docs.freetheai.org/sdks.md): The official FreeTheAI SDKs for Python, JavaScript and TypeScript, and Go - install, first request, streaming, web search, fallback models, and typed errors. - [OpenAI Python SDK](https://docs.freetheai.org/sdks/openai-python.md): Use the official OpenAI Python SDK with FreeTheAI - set base_url and your key, then use chat completions, streaming, tools, Responses, async, and error handling. - [OpenAI JavaScript and TypeScript SDK](https://docs.freetheai.org/sdks/openai-javascript.md): Use the official OpenAI Node.js SDK with FreeTheAI from JavaScript or TypeScript - baseURL, chat completions, streaming, Responses, and error handling. - [Anthropic SDK](https://docs.freetheai.org/sdks/anthropic.md): Use the official Anthropic Python and TypeScript SDKs with FreeTheAI's Messages endpoint and free models like GLM 5.3 and Kimi K3, including streaming and tool use. - [LangChain](https://docs.freetheai.org/sdks/langchain.md): Use FreeTheAI models in LangChain through the OpenAI-compatible ChatOpenAI class in Python and JavaScript, with streaming and tool binding. - [Plain HTTP and fetch](https://docs.freetheai.org/sdks/http.md): Call the FreeTheAI API without an SDK - fetch in JavaScript, requests and httpx in Python, and curl - including reading a server-sent event stream by hand. ### App guides - [App setup guides](https://docs.freetheai.org/guides.md): Step-by-step FreeTheAI setup for 24 apps - JanitorAI, SillyTavern, Chub AI, Open WebUI, LibreChat, Claude Code, Codex, Cline, Aider, Zed, and more - with the exact base URL, key, and model. #### Roleplay apps - [JanitorAI Free API: FreeTheAI Proxy Setup](https://docs.freetheai.org/guides/janitor-ai.md): Use free models like GLM 5.3, Kimi K3, and MiniMax M3 on JanitorAI. The exact proxy URL, API key, and model name for FreeTheAI, plus fixes for common errors. - [SillyTavern Free API: Connect FreeTheAI (Custom OpenAI)](https://docs.freetheai.org/guides/sillytavern.md): Connect SillyTavern to free models with FreeTheAI. Chat Completion, Custom (OpenAI-compatible) source, base URL, key, and model ID, step by step. - [Chub AI Free API: FreeTheAI Reverse Proxy Setup](https://docs.freetheai.org/guides/chub-ai.md): Use free AI models on chub.ai (Venus) with FreeTheAI. Where the OpenAI reverse proxy lives in Secrets, the base URL to use, and how to pick the model. - [RisuAI Free API: FreeTheAI Custom API Setup](https://docs.freetheai.org/guides/risuai.md): Set up FreeTheAI in RisuAI with the Custom API model: URL, key, request model, and the Force Plain Fetch setting the web version needs. - [Tavo App Free API: Connect FreeTheAI](https://docs.freetheai.org/guides/tavo.md): Use free AI models in the Tavo roleplay app on Android and iPhone. Add FreeTheAI as a Custom (OpenAI Protocol) connection with the right base URL. #### Chat apps - [Open WebUI Free API: Add FreeTheAI as an OpenAI Connection](https://docs.freetheai.org/guides/open-webui.md): Add FreeTheAI to Open WebUI as an OpenAI-compatible connection and chat with free models like GLM 5.3, Kimi K3, and MiniMax M3. - [LibreChat Free API: FreeTheAI Custom Endpoint (librechat.yaml)](https://docs.freetheai.org/guides/librechat.md): Add FreeTheAI to LibreChat as a custom endpoint in librechat.yaml, with model fetching, titles, and the API key kept in your .env file. - [LobeChat Free API: Add FreeTheAI as a Custom Provider](https://docs.freetheai.org/guides/lobechat.md): Add FreeTheAI to LobeHub (LobeChat) as a custom AI provider with the OpenAI request format and use free models in your chats. - [Chatbox Free API: Add FreeTheAI as a Custom Provider](https://docs.freetheai.org/guides/chatbox.md): Use free AI models in Chatbox on Windows, Mac, Linux, Android, and iOS. Add FreeTheAI with the OpenAI API Compatible mode. - [Cherry Studio Free API: Add FreeTheAI as a Provider](https://docs.freetheai.org/guides/cherry-studio.md): Add FreeTheAI to Cherry Studio as an OpenAI-type provider. The API address to enter, how Cherry adds /v1, and how to enable free models. - [NextChat Free API: Use FreeTheAI as a Custom Endpoint](https://docs.freetheai.org/guides/nextchat.md): Point NextChat (ChatGPT-Next-Web) at FreeTheAI with a custom OpenAI endpoint and custom model list to chat with free models. - [TypingMind Free API: Add FreeTheAI as a Custom Model](https://docs.freetheai.org/guides/typingmind.md): Add FreeTheAI models to TypingMind as custom models with the chat completions endpoint and an Authorization header. - [AnythingLLM Free API: FreeTheAI with Generic OpenAI](https://docs.freetheai.org/guides/anythingllm.md): Use FreeTheAI as the LLM in AnythingLLM with the Generic OpenAI provider: base URL, key, model, context window, and max tokens. - [Page Assist Free API: Add FreeTheAI to the Browser Extension](https://docs.freetheai.org/guides/page-assist.md): Use free AI models in the Page Assist browser extension. Add FreeTheAI as an OpenAI compatible provider and pick your models. #### Coding tools - [Claude Code Free API: Run It on FreeTheAI Models](https://docs.freetheai.org/guides/claude-code.md): Run Claude Code with free models like GLM 5.3 and Kimi K3 through FreeTheAI. Tested settings.json and environment variables. - [Codex CLI Free API: Use FreeTheAI Models in Codex](https://docs.freetheai.org/guides/codex.md): Configure OpenAI Codex CLI to use free models through FreeTheAI's Responses API. A tested config.toml with a custom model provider. - [OpenCode Free API: Add FreeTheAI as a Custom Provider](https://docs.freetheai.org/guides/opencode.md): Use free models in OpenCode with FreeTheAI. Store the key with /connect and add the provider to opencode.json with context limits. - [Kilo Code Free API: Add FreeTheAI as a Custom Provider](https://docs.freetheai.org/guides/kilo-code.md): Use free models in the Kilo Code VS Code extension and CLI with FreeTheAI as an OpenAI Compatible custom provider. - [Cline Free API: Use FreeTheAI as an OpenAI Compatible Provider](https://docs.freetheai.org/guides/cline.md): Set up Cline in VS Code with free models from FreeTheAI: OpenAI Compatible provider, base URL, key, model ID, and context window. - [Continue.dev Free API: FreeTheAI in config.yaml](https://docs.freetheai.org/guides/continue-dev.md): Add FreeTheAI models to the Continue extension for VS Code and JetBrains with a config.yaml model entry using the openai provider. - [Aider Free API: Use FreeTheAI Models](https://docs.freetheai.org/guides/aider.md): Run the Aider AI pair programmer on free models with FreeTheAI: OPENAI_API_BASE, OPENAI_API_KEY, and the openai/ model prefix. - [Zed Editor Free API: Add FreeTheAI as an OpenAI Compatible Provider](https://docs.freetheai.org/guides/zed.md): Use free models in Zed's agent panel with FreeTheAI. Add an OpenAI compatible provider from Agent Settings or settings.json. - [VS Code Copilot Free API: Add FreeTheAI Models (BYOK)](https://docs.freetheai.org/guides/github-copilot.md): Use free FreeTheAI models in VS Code chat and Copilot agent mode with bring your own key: the Custom Endpoint provider and chatLanguageModels.json. - [Hermes Agent Free API: Use FreeTheAI as a Custom Endpoint](https://docs.freetheai.org/guides/hermes-agent.md): Run Nous Research's Hermes Agent on free models through FreeTheAI, with hermes model or config.yaml. ### Help - [FAQ](https://docs.freetheai.org/faq.md): Answers to common FreeTheAI questions - which URL and key to use, the daily check-in, limits, cut-off replies, Bad Request in SillyTavern, busy models, thinking, and account help.