wtf is deepseek r1? v3? v3.1????

R1 as a reasoning powerhouse || what's a reasoning model? || wtf is the difference?

"The study of reasoning model draws its inspiration from the observation that reasoning is one of the main intelligent activities of human beings, and of the ways by which human thinking comes from one idea to a related idea." – Science Direct

ty, smart person.

‼️ DEEPSEEK V3.1 is now a hybrid model.

• find the huggingface page right here

• and the official news page on deepseek docs here

• tl;dr: R1 has now become v3.1 thinking. similar, faster (model name on official api: deepseek-reasoner)

• v3 non-thinking is your usual v3 but improved (model name on official api: deepseek-chat)

• if you're using official api, the model you'll be using is only v3.1 only. you can switch between reasoning or non-reasoning, but you don't have access to v3 0324 or r1 0528

Differences between R1 and V3? (old, but relevant)

i'll leave you with this from datacamp.com, link to article here

DeepSeek-V3 doesn’t have reasoning ability. As we mentioned, it works as a next-word predictor. This means that it can answer questions whose answers are encoded in the training data.

Because the amount of data used to train these models is so huge, it is capable of answering questions on almost any topic. Like other LLMs, it excels in natural-sounding conversation and creativity. It's the model we want for creating writing, content creation, or answering generic questions that are likely to have been solved already numerous times.

DeepSeek-R1, on the other hand, shines when it comes to complex problem-solving, logic, and step-by-step reasoning tasks. It's designed to tackle challenging queries that require thorough analysis and structured solutions. When faced with complex coding challenges or detailed logical puzzles, R1 is the tool to rely on.

source: datacamp.com

so now you know!

---

🧀 For more troubleshooting tips, find jem's guide here!

---

HOW TO USE DEEPSEEK MODELS AS A PROXY || JANITOR.AI SPECIFIC (paid + free)

1. Official DeepSeek API (paid)

1

Make an account on the Deepseek Platform

2

Generate a key

3

Add credits (top up your account)

4

Go back to Janitor

Go here:

CHOOSE Proxy, then paste the key here:

5

Add the model + proxy URL

V3.1 (thinking): deepseek-reasoner

V3.1 (non-thinking): deepseek-chat

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

6

Save, refresh and done!

THE TEMP ISSUE (OFFICIAL API)

‼️ With this method, TEMP doesn't affect R1. find the official docs here

⬆️ more info needed for v3.1 reasoning.

FOR V3.: this is how temp works for this model (info can be found here)

IF set temp = 1, THEN actual temp = 0.3

1. OpenRouter method (free****‼️)

1

Make an account on Openrouter.ai

2

Generate a key (Menu > Keys > Create Key)

COPY THE KEY INTO YOUR NOTES || looks something like sk-v1-xxxxxxx

3

Go back to Janitor

Go here:

CHOOSE Proxy, then paste the key here:

4

Add the model and proxy URL

edit (26 Aug 25): V3 0324 and R1 0528 remain free on openrouter, whilst v3.1 isn't.

V3.1: deepseek/deepseek-chat-v3.1

V3 0324 (free): deepseek/deepseek-chat-v3-0324:free

R1 0528 (free): deepseek/deepseek-r1-0528:free

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

5

Save, refresh and done!

****—previously, OpenRouter provided 200 free messages. Nowadays, you get 50.

to get more, you must add $10 in credits ONCE to get 1000 free messages/day forever.

edit (26 Aug 25): Chutes is now strictly a paid service.