--- title: "FreeTheAI API errors: every message and how to fix it" description: "Every error the FreeTheAI API returns, word for word: what it means and how to fix it, from check-in and limits to busy models and content filters." url: https://freetheai.org/docs/errors language: en updated: 2026-11-11 --- # FreeTheAI API errors Every message the FreeTheAI API answers with, word for word, with what it means and how to fix it. Messages that end with an error id: keep the id for a support ticket. Live model status: https://freetheai.org/status ## Your key and account The request reached FreeTheAI, but the key or account cannot use it yet. ### 401 Unauthorized Message: `unauthorized` The request has no API key, or the key is wrong, revoked, or expired. 1. Send the key as `Authorization: Bearer ftai_...` (in most apps: paste it into the API key field). 2. Check the key is active at https://freetheai.org/dashboard/api-keys. If it was revoked or you lost it, create a new one. ### 401 Not a complete key Message: `This is not a complete FreeTheAI API key. A key starts with ftai_ and is 53 characters long` Only part of a key was pasted, usually the short start the API keys page shows. 1. The full key is shown only once, when you create it. If you no longer have it, create a new key and paste the whole key into your app. ### 401 Seller MCP token used as an API key Message: `This is a seller MCP token. It works only with the FreeTheAI Seller MCP server at https://mcp.freetheai.org/seller` A token that starts with `ftsm_` was sent to the model API. Those tokens let an AI agent manage a seller account; they cannot call models. 1. To call models, use an API key that starts with `ftai_` from https://freetheai.org/dashboard/api-keys. 2. To manage your seller account from an agent, add the token to the agent as an MCP server; https://freetheai.org/sell shows how. ### 403 Daily check-in required Message: `Daily check-in required for free models. Visit https://freetheai.org to solve the captcha.` Free models need a quick check-in once a day. It resets at 00:00 UTC. 1. Sign in on freetheai.org and do the check-in, then send the request again. Your key does not change. 2. Paid models never need a check-in. ### 403 Email not confirmed Message: `Confirm your email address to use the API.` The account has not confirmed its email address yet. 1. Sign in on freetheai.org, send the confirmation link, and open it from your inbox (check spam). ### 403 Account on hold Message: `This account's API access is on hold pending an abuse review.` API access for this account is paused while it is reviewed. 1. Open Support in your dashboard and send an appeal. Holds are reviewed by people; one account per person. ### 403 Address not on the key’s allowlist Message: `This API key only accepts requests from the IP addresses on its allowlist` The key has an IP allowlist and the request came from another address (home addresses change often). 1. Add your current address to the key, or clear its IP allowlist, at https://freetheai.org/dashboard/api-keys. ### 403 Model not allowed on this key Message: `This API key's model list does not include this model.` The key is limited to certain models, and this is not one of them. 1. Add the model to the key, or clear the key’s model list, at https://freetheai.org/dashboard/api-keys. ### 403 Relayed request Message: `Requests relayed through a Cloudflare Worker are not accepted.` The request came through another service instead of from your app or device. 1. Call the API directly. In RisuAI on the web, turn on Settings > Advanced Settings > Force Plain Fetch. ### 403 App not supported Message: `LoreBary is not supported on FreeTheAI. Use your API key directly in another app.` Requests from this app are not accepted. 1. Use your key in another app; the setup guides at https://freetheai.org/setup cover 24 of them. ## The request itself The request was refused before any reply, because of what it asks for. ### 404 Model not found Message: `was not found. Use a model ID from https://api.freetheai.org/v1/models` No model has that ID. Model IDs look like `glm-5.3`, or `/glm-5.3` for one provider; old IDs from freetheai.xyz no longer work. 1. Copy an ID exactly as https://freetheai.org/models or `GET https://api.freetheai.org/v1/models` lists it. ### 404 Provider does not offer this model Message: `See its models at https://freetheai.org/providers/` The model ID names one provider (`/`), and that provider does not list this model. 1. Open the provider's page from the message and copy one of its model IDs, or drop the `/` part to use any provider you follow. ### 400 Model accepts text only Message: `This model accepts text only. Remove the images, or pick a model that accepts images` The request has images, and this model cannot read them. 1. Remove the images, or pick a model marked for images on https://freetheai.org/models. ### 400 Key set to tool-capable models only Message: `This API key is set to tool-capable models only, and this model cannot take tool calls.` The key has the "Tool-capable models only" switch on, and this model cannot use tools. 1. Pick a model from `/v1/models` (the key only lists tool-capable ones), or turn the switch off on the API keys page. ### 400 Media model on a chat endpoint Message: `This model generates media. Create a task with POST /v1/videos or POST /v1/images/generations` Image and video models run as tasks, not chat. 1. Create a task with the endpoint named in the message and poll it until it completes (see https://freetheai.org/docs). ### 400 Audio length unreadable Message: `the audio length could not be read; send wav, mp3, flac, ogg, m4a, or mp4` Transcription is charged by the recording’s length, and it could not be read from this file. Nothing was charged. 1. Send the recording as WAV, MP3, FLAC, Ogg, M4A, or MP4 (see https://docs.freetheai.org/api/audio-transcriptions). ### 400 Speech text too long Message: `input must be at most` One speech request takes at most 4,096 characters. 1. Split the text into several requests (see https://docs.freetheai.org/api/audio-speech). ### 410 Images already fetched Message: `these images were already fetched or have expired` Images from provider models are handed out once, or kept for one hour if never read. 1. Save the images the first time you read the task. 2. To get new ones, create a new task (see https://docs.freetheai.org/api/images). ### 400 Content filtered Message: `Content filtered: the model's content filter blocked this request or its reply.` The model’s own safety filter refused the message or its reply. It is not a fault with your key. 1. Rephrase the message, or use another model. ### 400 Content filtered on dog/ or lion/ models Message: `Content filtered: dog/ models are for general questions, writing, and images.` The fta/dog/ and fta/lion/ models are for general questions, writing, images, and research. Their filter often refuses coding, roleplay, and character chats. 1. For coding or roleplay, use an fta/zai or fta/kimi model. ### 400 Settings the model does not accept Message: `the model rejected one of the request's settings` A generation setting (temperature, top_p, penalties, max tokens) has a value this model refuses. 1. Reset your app’s generation settings to their defaults and try again. ### 400 No message from you Message: `the model needs at least one message from you in the request` The request only had system or character messages. Some apps send that by default. 1. In SillyTavern: API Connections > Prompt Post-Processing > Semi-strict. In other apps, set role handling to semi-strict or strict. ### 400 Conversation too long Message: `the conversation is too long for this model` The chat is longer than this model can read at once. 1. Lower your app’s context size, or start a new chat. ### 400 Request rejected as invalid Message: `the provider rejected this request as invalid; check the messages and parameters.` The model refused the request’s shape: an empty message, an unusual role order, or a parameter it does not take. 1. Reset your app’s generation settings, and turn on semi-strict prompt processing if your app has it. 2. If it keeps happening, open a ticket with the error id from the message. ### 400 Invalid JSON Message: `invalid json payload` The request body is not valid JSON for this endpoint. 1. Check the body, and that the URL matches the format you send (for example `/v1/chat/completions` for OpenAI chat). ### 400 Missing model Message: `missing model` The request does not name a model. 1. Set the model field to an ID from https://freetheai.org/models. ### 413 Request too large Message: `request body is too large` The request is over the size limit, usually a long chat with many images. 1. Shorten the chat history or lower your app’s context size, and send fewer or smaller images. ## Your limits Free accounts have daily limits. These reset on their own; the Free usage page in your dashboard shows how much you have used. ### 429 Too many requests at once Message: `concurrency limit reached: your account already has as many requests running as its plan allows.` A reply is still running, and free accounts run one request at a time. Coding tools often send several at once. 1. Wait for the current reply to finish (or stop it), then send again. Most coding tools retry these on their own. ### 429 Daily free requests used Message: `You've used today's free requests. They reset at 00:00 UTC` The account has used today’s free requests. Failed requests do not count. Accounts without Discord linked are told that linking it gives more free requests every day. 1. Wait for 00:00 UTC, or raise the limit: link your Discord account on the Free usage page, or see the other ways listed there. ### 413 Request too large for the free tier Message: `This request is too large for the free tier.` One request is bigger than the free tier allows. Accounts without Discord linked have a smaller per-request size. 1. Lower your app’s context size or start a new chat, then retry. 2. Link your Discord account on the Free usage page to send larger requests. ### 429 Daily budget for these models used Message: `Daily token budget for this provider is used up.` Some model families have a daily token budget per account, and yours is used for today. 1. Use another model until 00:00 UTC; every other model still works. The Free usage page shows each budget. ### 429 Rate limit Message: `rate limit reached` Too many requests in a short time. 1. Slow down and retry after a short wait. ## Busy or paused models The request was fine, but the model cannot take it right now. These are not your limits, and other models keep working. ### 503 Model busy Message: `this model is busy right now; try again in a minute or pick another model.` The model has no free capacity this minute. These refusals do not count against your limits. 1. Retry in a minute, or pick another model. ### 503 Model paused Message: `is paused by that provider right now` The model exists, but the provider you named, or every provider that offers it, has paused it for now. Paused models come back on their own; these refusals do not count against your limits. 1. Use the same model from another provider you follow (drop the `/` part to let FreeTheAI pick one), or pick another model on https://freetheai.org/models. ### 503 Shared daily limit reached Message: `has hit its shared daily limit (for everyone, not your own usage).` Some models share one daily limit across everyone so they last all week. When it is used up, the model is paused for everyone until the time in the message, even if your own allowance still has room. The status page shows which models are paused. 1. Use another model until then; for coding, fta/zai/glm-5.3 is a good switch. 2. Check https://freetheai.org/status for when it is back. ### 503 Paused while capacity refills Message: `this model is paused for everyone while its shared capacity refills` The model is paused for everyone for a few hours while its capacity refills. 1. Use another model meanwhile, and check https://freetheai.org/status. ### 503 Free capacity used up Message: `this model's free capacity is used up right now` The model’s free capacity is used for now. 1. Try again later, or pick another model. ### 503 Model temporarily unavailable Message: `this model is temporarily unavailable` The model is offline for now. 1. Try again later, or pick another model. ### 502 Upstream temporarily unavailable Message: `upstream provider temporarily unavailable.` The model did not answer this time. These do not count against your limits. 1. Retry. For long replies, turn on streaming in your app: very long replies without streaming can time out. 2. If it keeps happening, open a ticket with the error id from the message. ### 502 Upstream rate limited Message: `upstream provider is rate limited.` The model is getting too many requests this minute. 1. Retry in a minute, or pick another model. ### 502 Model server error Message: `the model's server hit an error; try again in a moment.` The model’s server failed this time. 1. Try again in a moment. ### 502 Stream interrupted Message: `stream interrupted. Error id:` The reply stopped partway. A cut-off that delivered almost nothing is not counted. 1. Regenerate the reply. If it keeps happening, open a ticket with the error id. ### 503 Free request check unavailable Message: `the free request check is temporarily unavailable; try again in a moment.` A short hiccup on our side while counting the request. 1. Try again in a moment. ### 400 Request failed Message: `request failed` Something went wrong that has no more specific message. 1. Check the model ID and the request body. If it keeps happening, open a ticket with the time, the model, and your app’s name. ## Paid usage Paid models from providers, including every embedding, speech, transcription, image, and video model they list, spend wallet balance. The free tier never spends money. ### 402 Insufficient wallet balance Message: `insufficient wallet balance` The wallet does not have enough balance for this paid request. 1. Add credits on the Credits page, or use a free model. ### 402 Key budget used Message: `api key budget exhausted` The key reached the spending budget set on it. 1. Raise or clear the key’s budget at https://freetheai.org/dashboard/api-keys. ## Messages from your app Common messages your app shows that do not come from the API itself. ### App Claude Code: two keys set Message: `Both ANTHROPIC_AUTH_TOKEN and ANTHROPIC_API_KEY set` Claude Code found two keys in your environment and may use the wrong one. 1. Keep only `ANTHROPIC_AUTH_TOKEN` set to your FreeTheAI key, and unset `ANTHROPIC_API_KEY`. The Claude Code guide is at https://freetheai.org/setup/claude-code. ### App Failed to fetch / NetworkError Message: `Failed to fetch` The browser did not send the request at all. The usual cause is a key pasted only partly, or with a stray character. 1. Create a new key, paste the whole key, and reload the app. Check the base URL is `https://api.freetheai.org/v1`. ### App No response from bot Message: `No response from bot` The app gave up waiting while the model was still thinking. Long chats on thinking models take longer to start. 1. Retry, turn the model’s thinking off on your key (API keys page), or use a faster model.