JanitorAI Proxy (Openrouter + Deepseek + Gemini) Setup [Updated 7-21]

[YOU CAN REUSE/REPOST THIS AS LONG AS IT LINKS BACK TO THIS PASTEBIN OR GIVES CREDIT]

UPDATE 7-21: Removed Chutes (It is no longer free to use, so 90% of you won't use it. Because of this, I've removed it. If you want to pay for Proxy, either use the official deepseek platform or pay 10 dollars for openrouter as mentioned below.)

Added a way to use Google Gemini on JanitorAI

Added a way to use the official deepseek platform onto JanitorAI

Put important sections separate to make readability more easier


UPDATE 7-22 (Thank you SonicSpeed for the clarification)

Gemini/google has a free tier that is available to use at a lower rate limit. It's the same process, you just have to select a weaker model in the workspace to do so.

Clarified that Openrouter's tokens do expire after a year. I am uncertain if this prevents you from accessing the 1000 requests per day, but since the 10 dollar limit is tied to account purchase history, not how many credits you currently have, it's likely that you'd still get 1000 per day. Still, you should use those 10 dollar credits before the year ends, if applicable.


--------------------


  			Setting up an Open router account for AI chat: Deepseek V3 JanitorAI Version

1. Go to https://openrouter.ai/

2. Sign in to your email in the top right corner

3. Hover over profile picture (top right) and select the "keys" dropdown

4. Select the "create key" button

5. Name it to whatever you want, for this example I will call it Deepseek V3 to keep track of my keys and to remember which model goes with which key
- Credit limit is optional and, if you plan to not use paid models and use a free one like deepseek V3, you can leave it alone

6. SAVE THE ENTIRE KEY TO SOMEWHERE SAVE AND EASILY RETRIEVEABLE! (For example, a notepad on your desktop) You will NOT be able to copy your key again from the site.

7. Before you leave the settings/key page, go to the menu on the left side and select the "privacy" tab. Make sure that, under "Free Models", that the "Enable training and logging (chatroom and API)" Option is turned ON. You need this on for Janitor AI to get endpoints and send data back and forth. You will not be able to chat with a proxy otherwise

8. Go to models and find a model for you. For this example, we will be using my favorite and recommended model, DeepSeek V3 0324 (FREE), which can be found here: https://openrouter.ai/deepseek/deepseek-chat-v3-0324:free

9. That link is what you'll want to copy, but you can also click the clipboard button under the main name. This name of the model is important, keep it.

--


Alternatively, you can use Deepseek R1 0528 over Deepseek v3. While R1 gives more in-depth answers (at the cost of being a bit much/flowery sometimes) and tending to eat up tokens with fluff. However, I would HIGHLY recommend R1 for extremely long roleplays or for high token/simulator bots, as it handles it marginally better than v3.



Deepseek V3: General use/Lighter roleplay

Deepseek R1: Much more detailed/heavy roleplay, more niche but powerful use.



			To use deepseek R1 on openrouter, follow the steps above, but put these in instead:


Model: deepseek/deepseek-r1-0528:free

Proxy URL: https://openrouter.ai/api/v1/chat/completions

Key: Your personal key (make sure to make this its own key to avoid issues!

You should always try and have one free model per key, to avoid any potential issues.

--

###


				OPTIONAL STEP: Increasing daily limit through money

Many people don't wish to pay. However, if you have 10 credits stored in your account, which I BELIEVE to be $10 USD but I am uncertain, the daily limit goes from around 50 to 1000 requests per day for all free models. If you really want an option for daily limits, you can. MAKE SURE to set your key to not use any credits so you don't use up your paid credits.



					Setting up the Official Deepseek Platform

Do not that, while you do need to pay for this, it is extremely cheap, is quite fast, and provides responses that are moderately more impressive than other providers. If you are willing to pay for a proxy, then I'd recommend this option. However, if you use a proxy a TON, and aren't willing to wait for the discount hours (more on that below) it may be a better investment to give Openrouter the $10 to get 1000 free each day instead, as you only need to do it once and will safe you slightly more in the long run.

If you wish to know how efficient deepseek platform is, I've used around 600 api requests and 3 million tokens during the discount period, and I have only used 45 cents so far.

1. Go to this platform here: https://platform.deepseek.com

2. Sign in/sign up for an account

3. Once you are in, make sure you are on the 'Usage' page and click the 'Top Up' Button. Alternatively, you can select the 'Top up' button on the left side of the page.

4. Put in your credit card info here. I would recommend just doing 2 dollars, but any amount is good.

5. Once you have completed that, on the top left click 'API keys'

6. Create a new API key. MAKE SURE TO SAVE THE WHOLE API KEY ID SOMEWHERE SAFE, AS YOU WILL NOT BE ABLE TO GET IT BACK ON THIS PAGE!

7. Now you should be ready. For setting up in JanitorAI, follow the steps down below


Model (Deepseek V3 Chat): deepseek-chat

Model (Deepseek R1): deepseek-reasoner

Proxy URL: https://api.deepseek.com/v1/chat/completions


				Deepseek Platform Discount Hours (When you should use it)

From around 16:30-00:30 UTC, or 8:30PM to 11:30AM for EST, is the time where both of the models for deepseek are 50%/75% off. I would recommend only using the official platform during these hours, and when you want to chat during these off-discount hours, use openrouter instead for free daily uses.


###


					 Using Gemini in JanitorAI

YOU NEED TO PUT IN YOUR CREDIT CARD TO USE THIS! HOWEVER, THERE IS A 'FREE TRIAL' THAT YOU CAN USE. Additionally, there are lower tier models that are available for free. To do so, just skip the payment part and simply get the name of the tier, your key, and put it into J.AI

I CANNOT PERSONALLY VERIFY IF THIS WORKS AT THIS TIME!

DO NOTE THAT I HAVE NOT TESTED THIS! I mostly wanted to update this guide and get this announcement out for the J.AI UK situation hits. I have used Gemini before, however, for helping to get some information on certain ideas and characters, and it works quite well! According to others, it works better than deepseek, ESPECIALLY with pre-existing characters.

Please don't use your actual account to set this up, use a burner/alt account



1. Go to this link: https://aistudio.google.com and sign in

2. When you sign in, go to 'Dashboard' on the top right. Then, click Usage and Billing.

3. When you set up billing, you will get $300 dollars in free credit for 90 days.

4. Going back to the studio, go to the top right and click 'Dashboard'. Then, in the top right, click 'Create API Key'

5. When you create the key, MAKE SURE TO SAVE IT SECURELY LOCALY, AS YOU WILL NOT BE ABLE TO ACCESS IT AGAIN ON THIS PAGE!

6. Go into JanitorAI, and follow the steps below

Model: gemini-2.5-pro

Proxy URL:  https://generativelanguage.googleapis.com/v1beta/openai/chat/completions

Do note that Gemini is censored! You will need a bypass/jailbreak for more ERP elements.

While I cannot verify how good these are, you can use the prompts to help here: https://rentry.co/pddvz4oo




						SETTING UP IN JANITORAI

1. Go into JanitorAI and go to a proxy enabled character

2. Click the 3 bars on the top left, and go to API settings, then Proxy

3. From top to bottom, the first text field you want to put in the name of the model you're going to be using. For deepseek v3, it is the link from above. (deepseek/deepseek-chat-v3-0324:free)

4. The 2nd field for the Proxy URL. You need to get the url from the site that is hosting the proxy, and each WEBSITE has a different one. For example, No matter what model you use, if you get it from openrouter, it will use this: https://openrouter.ai/api/v1/chat/completions

14. Finally, the 3rd field is for the API key you saved locally or in a secure location. After putting it in, all you have to do is save [Press the Save settings button], reload, and it should be applied! (Make sure to do this BEFORE selecting the check API button)


POSSIBLE ISSUES
If you are getting a networking error, or it simply is not working, some possible solutions can be:
Copy and pasting the model name and Proxy URL, since typing it can cause issues
Closing and Reopening JanitorAI tabs
Make sure you Save Settings and reload the page BEFORE checking the API.


Personal notes as of 7-21:
To get your best worth out of it, I would recommend using Deepseek as a starter and when JLLM can't get the scenario right or doesn't have correct knowledge. Otherwise, use JLLM for general use and conversation. Despite it being slow and not as complex, it does roleplay the best, and has the best dialogue (from my experience)

For almost all applications, deepseek is easier to set up and use than Gemini. Unless you REALLY want something special, stick with Deepseek



Thank you for your time.

Made by NullSeu