Guide

Janitor AI 'No Endpoints Found': The Three OpenRouter Settings Behind It, and the Fix for Each

Janitor AI 'no endpoints found' comes from OpenRouter: provider restrictions, a retired model id, or the privacy setting.

HProxy Team··Updated September 28, 2026·5 min read
HProxy.Guide

Skip the dead lists.

Our free proxy list re-checks every exit every few minutes across 100+ countries, with a live last-checked time, so you copy IPs that worked moments ago, not a stale text dump.

Open the free proxy list→

"No endpoints found" is the Janitor AI error that convinces people their setup is broken when it is not. The proxy URL is right, the key is right, and the chat still refuses. The message comes from OpenRouter, which Janitor passes through unchanged, and it means one thing: at this moment, no provider is available to serve the model id you typed, either because none exists, or because your own OpenRouter settings rule out the ones that do.

Janitor AI's OpenRouter error guide files it under 404 and names three causes. This page takes them in the order that fixes the most cases fastest, gives the exact setting for each, and ends with the current list of free model ids, because a retired id is the cause more often than anything else.

Cause one: the model id is retired or misspelled

OpenRouter's free models change. Providers add them, rename them, and retire them, and the id that worked in a guide from spring is often gone by autumn. Janitor's guide gives its own example of the pattern: deepseek-chat-v3:free was replaced by deepseek-chat-v3-0324:free, and neither is on the list now: on 28 September 2026 no DeepSeek id ended in :free. Type a retired id and OpenRouter has, literally, no endpoint for it.

The fix is mechanical. Open OpenRouter's models page, filter for :free, and copy the id character for character, suffix included. Ids are case sensitive. On 28 September 2026, OpenRouter's public list carried 16 free ids; the ones with the most context:

  • thinkingmachines/inkling:free and thinkingmachines/inkling-small:free
  • nvidia/nemotron-3.5-lightning:free
  • nvidia/nemotron-3-ultra-550b-a55b:free
  • dots-studio/dots-3-note-preview:free
  • qwen/qwen3.8-27b:free
  • inclusionai/ling-3.0-flash-sante:free
  • poolside/laguna-s-2.1:free and poolside/laguna-xs-2.1:free
  • google/gemma-4-31b-it:free and google/gemma-4-26b-a4b-it:free
  • nvidia/nemotron-3-super-120b-a12b:free

Two ids from the August list, z-ai/glm-5.2:free and nvidia/nemotron-3-nano-30b-a3b:free, were gone by then. That is cause one in action.

The full list, and the limits that come with it, are in our OpenRouter guide for Janitor AI. If the id you have is on the current list and the error persists, move to cause two.

Cause two: the privacy setting

Many free models are served by providers that may train on your prompts. OpenRouter's docs say that if you opt out of training, "OpenRouter will not route to providers that train." With the setting off, every provider for that model is excluded and the answer is no endpoints found. Janitor's guide gives the fix in one line: enable Model Training under Privacy Settings on OpenRouter. Save, refresh Janitor, and retry.

This is the cause worth a pause rather than a reflex. Enabling it means the providers behind the free models may train on your roleplay. The free route is priced in exactly that, and OpenRouter documents it, with separate settings for paid and free models. If it is not acceptable, the alternatives are a paid model on OpenRouter with training left off for paid models (the same key, a small balance), or a paid API such as DeepSeek's, under that provider's own terms. Google's Gemini free tier is no way out of the trade: Google says free-tier content is used to improve its products. Each route is covered in best free Janitor AI proxy. Make the choice on purpose.

Cause three: provider restrictions

OpenRouter lets you block providers you do not want and allow only the ones you do. Set that too tightly and a free model that is only served by a blocked provider has no endpoint left. Janitor's guide states the fix: unblock all Ignored Providers and clear Allowed Providers, then save. Most people never touched these settings; if you did, or followed a guide that did, this is the cause.

Working through 'no endpoints found' in the order that fixes it fastest
  1. Check the model id

    current :free spelling from OpenRouter's list

  2. Enable Model Training

    Privacy Settings on OpenRouter, if the trade is acceptable

  3. Clear provider restrictions

    unblock Ignored, clear Allowed, save

  4. Still failing?

    the model is down; check its uptime tab

  5. Switch model

    another :free id for tonight

Source: Janitor AI OpenRouter error guide and OpenRouter docs, read 28 September 2026

When all three are fine: the model is down

If the id is current, privacy is enabled and providers are unrestricted, the model is simply not being served right now. Janitor's guide recommends the same check for a 502: open the model's uptime tab on OpenRouter, which shows whether its providers are up. Pick another free model for the evening and come back to the first one later. Nothing in your Janitor settings is wrong.

What it is not

It is not a rate limit; that is a 429, with its own causes and fixes in Janitor AI error 429. It is not a wrong URL; that produces a network error, and Janitor's rule is that the OpenRouter URL must be exactly https://openrouter.ai/api/v1/chat/completions. It is not a bad key; that is a 401. And it is not a Janitor outage: the message is OpenRouter's answer about your model and your account.

It is also not anything your IP address touches. We run a proxy network of the IP-changing kind, and there is no version of this error a network proxy fixes, because the decision is made by the model id you typed and the settings inside your OpenRouter account. If openrouter.ai or janitorai.com cannot be reached from your network or country at all, that shows up as a network error, not this one, and we give no steps around it. The one Janitor rule that follows the address is its age check for users connecting from Australia, Brazil or the UK, where "Detection is IP-based only." That is not this error either. Where our lines do fit is a network that needs a known exit, such as a company network, with a static residential or ISP address in the country where you are, from $0.44 per GB on a usage meter.

Check the id, flip the setting if you accept the trade, clear the provider lists, and the endpoints come back.

Sources

Frequently asked questions

What does 'no endpoints found' mean on Janitor AI?
It is an OpenRouter message, forwarded by Janitor, meaning that no provider is currently available to serve the model you typed. Janitor AI's own OpenRouter error guide lists it as a 404 with three causes: your provider settings are restricted too far, the model id no longer exists, or your privacy settings block the free model. Each has a one-line fix on OpenRouter's side.
How do I fix 'no endpoints found' on Janitor AI?
Check three things on OpenRouter in this order. First, the model id: open OpenRouter's models page and copy the current spelling, because free ids rotate and retired ones return this error. Second, privacy: enable Model Training under Privacy Settings, which Janitor's guide names as the fix for free models blocked by data policy. Third, providers: unblock all Ignored Providers and clear Allowed Providers, then save. Retry after each step.
Why does 'no endpoints found' appear only on free models?
Because many free models are served by providers that may train on your prompts, and OpenRouter says that if you opt out of training, it will not route to providers that train. It keeps separate settings for paid and free models. The free route works once the free-model setting allows training, which is a trade about your data that you should make on purpose.
Which Janitor AI model ids are current on OpenRouter?
On 28 September 2026 OpenRouter's public models list carried 16 ids ending in :free, including nvidia/nemotron-3-ultra-550b-a55b:free, nvidia/nemotron-3.5-lightning:free, google/gemma-4-31b-it:free and qwen/qwen3.8-27b:free. z-ai/glm-5.2:free, on the list in August, was gone. No DeepSeek id ended in :free, so any guide still listing deepseek/deepseek-chat:free is describing a model that returns this exact error.
Is 'no endpoints found' a Janitor AI outage?
No. Janitor is passing on an answer from OpenRouter, and the answer is about your model choice and your OpenRouter settings. If the id is current, privacy is enabled and providers are unrestricted, the model itself is down, which OpenRouter's uptime tab for that model shows; pick another :free model for the evening.
Can a proxy or VPN fix 'no endpoints found'?
No. Nothing about this error involves your IP address. It is decided by the model id you typed and by settings inside your OpenRouter account. If openrouter.ai or janitorai.com cannot be reached from your network or country at all, that shows as a network error rather than this one, and we give no steps around it.

Get proxies that are alive right now

Our free proxy list re-checks every exit every few minutes across 100+ countries, with a live last-checked time, so you copy IPs that worked moments ago, not a stale text dump. When the location has to survive a real check, the paid network holds up.

129M+ proxy checks run · 100+ countries · HTTP / HTTPS / SOCKS · re-checked every few minutes · no signup

HProxy.

Honest guides and comparisons on proxies, scraping and staying unblocked, from the team that runs the network.

RSS feed