built by recursal.ai

Compatible Applications

These are some of the applications that support our API, if you would like to add your application to this list, please contact us.

WyvernChat

An AI Character Card Repository and Chat platform.

SillyTavern

LLM Frontend for Power Users.

novelcrafter

A platform that allows users to utilize AI to help them craft stories.

KoboldAI Lite

A lightweight web interface for chatting and prompting LLMs.

Agnaistic

A lightweight web interface for chatting with LLMs.

Venus AI

Chatbot roleplay.

Janitor AI

Chatbot repository and chatting site.

RisuAI

Make your own story. User-friendly software for LLM roleplaying

Model Types

Our ever-growing list of supported model types, including LLaMA-3, Mistral, and more.

RWKV
rwkv5-7b
8 models
Minimum Subscription Basic
Context Size 16,384
Parameters 7B
Max Output 4,096
Mistral v0.2 7B
mistral-v02-7b-std-lc
680 models
Minimum Subscription Basic
Context Size 8,192
Parameters 7B
Max Output 4,096
Llama 3 8B
llama3-8b-8k
673 models
Minimum Subscription Basic
Context Size 8,192
Parameters 8B
Max Output 4,096
Llama 3.1 8B
llama31-8b-16k
143 models
Minimum Subscription Basic
Context Size 16,384
Parameters 8B
Max Output 4,096
Llama 2 Solar 10B
llama2-solar-10b7-4k
222 models
Minimum Subscription Basic
Context Size 4,096
Parameters 10.7B
Max Output 4,096
Mistral Nemo 12B
mistral-nemo-12b-lc
80 models
Minimum Subscription Basic
Context Size 16,384
Parameters 12B
Max Output 4,096
Llama 2 13B
llama2-13b-4k
212 models
Minimum Subscription Basic
Context Size 4,096
Parameters 13B
Max Output 4,096
Llama 3 15B
llama3-15b-8k
12 models
Minimum Subscription Basic
Context Size 8,192
Parameters 15B
Max Output 4,096
Qwen 2 32B
qwen2-32b-lc
15 models
Minimum Subscription Premium
Context Size 16,384
Parameters 32B
Max Output 4,096
Yi 1.5 34B
yi1.5-34b-lc
1 models
Minimum Subscription Basic
Context Size 16,384
Parameters 34B
Max Output 4,096
Llama 3 70B
llama3-70b-8k
90 models
Minimum Subscription Premium
Context Size 8,192
Parameters 70B
Max Output 4,096
Llama 3.1 70B
llama31-70b-16k
34 models
Minimum Subscription Premium
Context Size 16,384
Parameters 70B
Max Output 4,096
Qwen 2 72B
qwen2-72b-lc
25 models
Minimum Subscription Premium
Context Size 16,384
Parameters 72B
Max Output 4,096
Mixtral 8x22B
mixtral-8x22b-lc
1 models
Minimum Subscription Premium
Context Size 16,384
Parameters 141B
Max Output 4,096
Llama 3 405B
llama3-405b-lc
2 models
Minimum Subscription Premium
Context Size 4,096
Parameters 405B
Max Output 4,096