FAQ
Answers to the questions people ask most. Can't find yours? Search the docs (Ctrl+K), check the errors page, or ask in the Discord.
Free tier
Is FreeTheAI really free?
Yes. Every account with a confirmed email gets 50 free requests a day with no credit card, plus 50 more a day for linking Discord. The free tier has limits, and it needs a short check-in once a day. Paid models and plans are coming soon and will be optional.
How does the free tier work?
Create an account, confirm your email, create an API key, and do the daily check-in on freetheai.org. Free models then work until 00:00 UTC, when the daily requests and the check-in reset. Free accounts run one request at a time. See Limits and the daily reset.
How do I get more free requests?
Link your Discord account on the Free usage page in your dashboard for +50 requests a day. That page also shows how much you have left and when it resets.
Do failed requests count against my daily limit?
No. A request only counts when it gets a real answer. Errors, busy models, and requests turned away are given back right away. A reply that breaks off partway counts only if a real amount of text already reached you.
Does FreeTheAI store my prompts?
No. FreeTheAI does not store prompts or replies. It keeps what it needs to run the service and stop abuse, such as request counts, timing, and IP addresses, as described in the privacy policy.
Using the API
Which URL and key do I put in my app?
Use the base URL https://api.freetheai.org/v1 and an API key from Dashboard > API keys. Apps that ask for the full URL, like JanitorAI, need https://api.freetheai.org/v1/chat/completions. Claude Code and the Anthropic SDK use https://api.freetheai.org. Copy model IDs exactly as they appear on the Models page. There are step-by-step guides for 24 apps.
Does it work with the OpenAI and Anthropic SDKs?
Yes. Set the base URL (base_url in Python, baseURL in JavaScript) to https://api.freetheai.org/v1 for the OpenAI SDKs, or https://api.freetheai.org for the Anthropic SDK, and use your FreeTheAI key. There are also official SDKs for Python, JavaScript and TypeScript, and Go.
Does it support streaming and tool calls?
Yes, on Chat Completions, Responses, and Anthropic Messages, for every free model. See Streaming and Tool calls.
Why are my replies cut off, or why does my app say "No response"?
Raise your app's max tokens (response length), or set it to 0 to use the model's full output length, and turn on streaming. Some models think before they answer, so long chats can take a while; if your app gives up waiting, retry, turn thinking off, or pick a faster model.
SillyTavern shows "Bad Request". How do I fix it?
On the API connection screen, set Prompt Post-Processing to Semi-strict and try again. Some models need at least one message from you in every request, and that setting makes sure there is one.
What are the dog/ models good for?
The fta/dog/ models are for everyday work that is not roleplay or coding: questions, writing and editing, summaries, research, translation, and reading images you attach. They reply in plain text only. They do not play characters, so roleplay apps such as JanitorAI usually get a content filter error, and they cannot make tool or function calls, so coding agents and tool-based apps do not work with them. For roleplay or coding, pick a GLM, Kimi, or MiniMax model instead.
How do I turn the model's thinking off?
On Dashboard > API keys, open scope & settings under your key, turn on Turn thinking off, and save. Models that think first then answer straight away, with nothing to change in your app. In code you can also send "reasoning_effort": "none" or "thinking": {"type": "disabled"}. If you see a second "thinking" part inside the reply text, your app's preset is asking the model to write its thoughts; turn that option off in the preset.
Which model should I use for roleplay?
Start with fta/zai/glm-5.3. On the Models page, pick Roleplay under Good for to see the models that suit roleplay, ranked by what roleplay apps use most. The dog/ and lion/ models are for general questions and writing, not roleplay.
Which model should I use for coding?
Start with fta/zai/glm-5.3. Use fta/kimi/k3 for harder reasoning and fta/zai/glm-5.3-flash for small, quick tasks.
What happened to freetheai.xyz?
FreeTheAI moved to freetheai.org and api.freetheai.org. Old freetheai.xyz pages redirect to the new site. Use https://api.freetheai.org/v1 and current fta/ model IDs; old addresses and model IDs no longer work.
Errors and limits
Why do I get "daily check-in required"?
Free models unlock after a quick daily check-in at freetheai.org/checkin. Your dashboard shows when the next check-in opens. Daily free requests reset at 00:00 UTC.
It says the model is busy or I am rate limited. What should I do?
Free models can get busy at peak times. Wait a minute and retry, or switch to another model. Requests turned away because a model was busy do not count toward your daily free requests. If the message says a reply is still running, wait for it to finish: free accounts run one request at a time.
My message was blocked or "rejected". Is my setup wrong?
Usually not. Some models have a content filter that can block a message or its reply. Retry, rephrase a little, or switch to another model.
Where is every error explained?
On the errors page: every message the API sends, word for word, with what it means and how to fix it.
Account and support
Which email can I sign up with?
Use an address from a major provider: Gmail, Outlook, Yahoo, or iCloud. Some privacy-focused and temporary email services are not accepted. Confirm your email from the link we send before using the API.
My API access is on hold. What now?
Open an appeal from Dashboard > Support and choose the appeal category. Staff review every appeal in order and you get a notification with the result. The decision on an appeal is final, and creating another account to get around a hold gets that account closed too. Appeals are handled on the site only, not in Discord.
What should I include when I ask for help?
Your signup email, a screenshot of the error, a screenshot of your app's connection settings with the API key hidden, the error ID if there is one, and roughly when it happened. That lets us find the problem without back and forth. Open a ticket from Dashboard > Support, or ask in the Discord.
I forgot my password or got logged out. What do I do?
Use Forgot password? on the login page to get a reset link by email. Don't make a new account to get back in: FreeTheAI allows one account per person, and extra accounts are put on hold.
The security check or check-in doesn't work for me.
Open freetheai.org in Chrome, Edge, or Safari with ad blockers and other extensions turned off for the site (or in a private window), turn off any VPN, and stay on one connection until you finish. If it still fails, try another browser or device.
Can people in my household have their own accounts?
Yes. Each person signs up with their own email and uses only their own account and API key. Don't share accounts or keys. If an account is put on hold, its owner appeals from that account.
Can an AI agent sign up or check in for me?
No. Accounts are for people, and sign-up, sign-in, and the check-in each include a human check. Do them yourself on freetheai.org, then give your app or agent the API key through its settings or an environment variable.