Proxies Options
Tired of the Jllm shenanigans? This is a total beginner's guide on what alternatives are there. Probably there are many more, but these are some I found and tried. Remember all these are based on pers
Trying to make this guide ADHD and dyslexia friendly, feel free to let me know if I can improve the presentation for that!
Here is a simplified version, read below for more details!
Basic AI Lingo:
Tokens = A token is a unit of text used by AI models. A single word can be 1-3 tokens depending on its length and complexity.
Memory Context= How much the AI remembers of your RP, measured in Tokens. Always includes the bot permanent tokens and your persona's, any remaining free space will use temporary tokens(first message, dialog examples and Rp chatlog). the longer you go on the chat the older temporary tokens will be forgotten)
B= Usually shows on a model in front of a number, it basically means how smart a model is, usually they go like 12B, 32B, 70B etc. The higher the number the smarter the model is.
What I look for in an AI model(coming from the JLLM):
Good memory Jllm only has 3k-7k context nowadays, times of high traffic like Christmas lowers it a lot. I usually look for something with 16K+ of context.
Avoiding cliche behaviors and phrases Examples: "maybe...just maybe", "jolts of electricity", "I'll ruin you for everyone else", etc., you know what I mean
Avoid overly horny behavior triggered for nothing So you can have slow burn Rps, and/or Rps with plots that don't focus on NSFW.
More intelligence, be more in character, more knowledgeable ( for my case, more knowledgeable about the One piece lore).
Better special awareness + more logic
FREE PROXIES OPTIONS:
Kobold proxy collab
Pros:
Has a lot of variety of small models from 7 to 22B, mostly 12 B's
24K memory context on 12B models even 16K on 14Bs
Fast generation
Medium easy integration on jai
Cons:
A hassle to setup: Every time you want to use any chat, you have to manually set up the url at the proxies settings. Additionally, whenever you want to activate the proxy, it takes about about 5 min to boot it, then you have to set it up and only then you can chat. Also, if you close the collab browser page, it will kill your API key and you'll have to set it up again(wait the 5 min loading time again) so you can use it again. I don't recommend this if your wifi fails a lot
I'm not sure on this one, but I heard there is a time limit for every day, I think 3 hrs, but I don't remember. I didn't use it much due to the hassle to set up
Feel free to explore, but these are just some cool model recommendations, I enjoyed!:
EVA-Tissint(14b) | personal fav from there
Starcannon(12b) | Personally, I liked it
Magnum(12b) | people say it's good
Mag-Mell(12b) | people say it's good
Here is the google collab link(done by Hibikiass)
Kobold Local Host
You can run your own llm on your own pc
Pros:
You don't have to share the machine with anyone, I heard this gives you better response even with the same model
You can choose any model you want and it will be free, there are thousands of options
Cons:
Hard to install and setup at first
Like the Kobold Collab, You'll have to boot it every time you want to use it
You need a powerful PC with at least 6GB of VRAM to run even a small 7B model.
Arli AI
They have free small 12B models!
Pros:
Easy to set up. Once you have it set up, you don't need to do anything else no more. Plug and play experience!
Cons:
Slow response times. In my previous experience, I was as waiting 30s to 1 min per generation before the first word was generated.
I liked the models, but I still felt like it lacked what I looked for for long term/complex RP, especially when it came to have knowledge of canon characters, however this bullet point is totally personal preference and you might find a model that you really like!
Open Router
Pros:
Has some different free models, Most of them are not entirely made for RP, they do a pretty good job!
Most models have an extremely huge context
Easy to set up. Once you do it, you don't have to touch it anymore
Cons:
A lot of the free models aren't tailored to RP, so you will probably have to make a custom prompt to tailor it to your taste and play with the temp(at least from my experience)
As of April 2025, you only get 50 free messages per account.
Model recs:
Deepseek R1 (free) | Read more about it below at the paid Open router section.
Deepseek V3 (free) | Read more about it below at the paid Open router section.
PAID PROXIES OPTIONS
There are usually 2 general options within paid proxies. Subscriptions or pay per token(basically you paid as much as you use)
SUBSCRIPTIONS
Arli ai:
Pricing:
10$/m = Access Up to 32B Models
15$/m = all models up to 72B
Pros:
Unlimited messages
Multiple diverse models up to 72B with high context!
They keep adding more models!
Easy to set up. Once it's done you don't need to touch it anymore unless you want to change models. Plug and play experience.
Cons:
Slow replies, expect 30 to 1 min for the message to start generating the first word
Personal fav models from what I tried with my bots as of January 2025:
Llama-3.3-70B-DeepSeek-R1-Distill
Qwen2.5-72B-Evathene-v1.3
Llama-3.3+3.1-70B-Euryale-v2.2
Qwen2.5-72B-EVA-v0.2
Other subs I'm aware they exist but I didn't try
Infermatic: Link Essential= $9/month Plus= $20/month
Featherless: Link Feather Basic= $10/month | Max. 15B models, Unlimited messages Feather Premium= $25/month | All models up to 72B models, Unlimited messages
PAY PER TOKEN:
You pay as much as you use. Price depends on each model
Open router
Pros:
Extreme variety of models with extreme variety of price ranges, intelligence, most have huge context memory
Cons:
If you are a reroll maniac, you can end up with a huge bill, fortunately you can put a limit to how much I wanna spend!
Personal fav models:
DeepSeek V3 0324
DeepSeek R1
Nemotron Ultra
DeepSeek
You can Choose in between the V3 and R1 (read about them at the open router section!) Their models are a lot more stable here than on Open router and cheaper(normal price but you don't compete with other provider's overpriced prices)
Pros:
Lowest R1 or V3 prices! no errors like in open router even on the paid version. Some hours offer 75% of discount on R1!(good for Europeans)>
Really cheap
Faster and more stable than on Open router>
Cons:
More or Same issues as the models on OR, as the issues are from the models themselves, However, I THINK the models perform better here>
Guide on how to Set up deekseek
MODEL OVERVIEW PROS AND CONS
This is my personal model overview. Other people might have different experiences and opinions!
Prices "Cheap" or "Expensive" are in comparison to having a subscription of about 10$/m
Flow = RP adaptability. How well it flows from message to message with a natural feel
Aggressiveness = How cruel/harsh a model is, tendency for cruelty
Chaoticness = How creative or out of rails a model is likely to be, more stars mean more chaotic
JLLM
FREE
DeepSeek R1
FREE or cheap
Deepseek V3 0324
FREE or Very cheap
Claude Sonnet
Expensive
Nemotron Ultra
FREE
Claude sonnet 3.5 | Best quality | Expensive
Available on Open Router and via their official API
Pros:
For me, Sonnet is king
Has a lot of general lore for canon characters
Characters feel in character a lot
Stable
Good plot and creativity
Best one regarding not being repetitive
Cons:
Expensive if you use Jai a lot. Using it with 16k of memory context, messages can go from 1~6 cents per message(from my experience), only use this on the regular if ur an oil prince/ess!
Censored. There are ways around it with prompts and prefill but if you want to use it uncensored, you need to boot the collab page every time and run it every time you want to chat(like in kobolt collab)
Extra notes: Wanna go bankrupt? You can also use Claude Opus, I heard it's really good!
DeepSeek R1 | Good For Price
Available on Open Router, Chutes and DeepSeek's Platform
Pros:
Characters feel in character very accurately
Good body language and Mannerisms
Good spacial awareness, really good brain, especially with powers that require some logic and some LLms struggle to grasp the concept
As good as sonnet but for a much much smaller fraction of the price(in my personal experience, but needs a good custom advanced prompt)
A lot of canon character lore
Uncensored, no need for prefils/jailbreaks
Cons:
Slow to generate(because it's a reasoning model, hence it's smartness). Faster than Arli's(from the time when I tested arli)
Issues with text formatting, but it's possible to mostly get rid of it with a good prompt, however its hard to get it consistent
Struggles with character development. It it will stick to characters too much not allowing much room for different behaviors, this can be improved with prompts, but it's still a high maintenance model that needs to be hand holded. It makes characters feel static reacting almost always in the same way
Not sure if it's a con, but it's really aggressive compared to other LLMS and WILL be mean and cruel if needed sometimes without reason
Deepseek V3 0324 | Best quality for Price
Available on Open Router, Chutes and DeepSeek's Platform
Pros:
Good at being in character
Good price
Good character development and good prose
Wide canon characters knowledge
Cons:
While it's uncensored, it does feel like anything that would typically be censored happens off screen and it doesn't focus on anything graphics like NSFW o violence, however if you have a good prompt you can bypass that
I think it has a little of positive bias
It feels insane with harsh topics, like its loosing it mind in a lot of cases
Nemotron Ultra
Available on Open Router
Pros:
Has a good flow from text to text
FREE
Feels smarter than other models in smaller things, like understanding what it means being unconscious, understanding that in a multi bot, some characters don't participate in the response and such things
Feels sane compared to deepseek models
Adheres consistently really well to advanced prompts without "fighting with it"
You can trigger reasoning with OOC, making it analyze better the situation
Cons:
Despite stable, it feels a little lacking in chaos/creativity
Notes:
You will need a prompt to enable NSFW stuff, but one you have it there are no drawbacks
Last updated