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.

anime.gf

moemoemoemoemoemoe

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.

tts-standard
0 models
Minimum Subscription Basic
Context Size
Parameters 0B
Max Output
audio-music
0 models
Minimum Subscription Basic
Context Size
Parameters 0B
Max Output
tts-f5-tts
1 models
Minimum Subscription Basic
Context Size
Parameters 0B
Max Output
tts-chatterbox-turbo
1 models
Minimum Subscription Basic
Context Size
Parameters 0B
Max Output
tts-chatterbox
1 models
Minimum Subscription Basic
Context Size
Parameters 0B
Max Output
bge-m3
0 models
Minimum Subscription Basic
Context Size 32,768
Parameters 0.027B
Max Output
tts-kokoro-82m
1 models
Minimum Subscription Basic
Context Size
Parameters 0.082B
Max Output
nomic-v15
2 models
Minimum Subscription Basic
Context Size 32,768
Parameters 0.1B
Max Output
gpt-sw3-126m
2 models
Minimum Subscription Basic
Context Size 2,048
Parameters 0.2B
Max Output
gpt2-sw3-126m
2 models
Minimum Subscription Basic
Context Size 2,048
Parameters 0.2B
Max Output
gemma3-270m
1 models
Minimum Subscription Basic
Context Size 32,768
Parameters 0.27B
Max Output
bge-large-en
5 models
Minimum Subscription Basic
Context Size 32,768
Parameters 0.3B
Max Output
ernie4_5-0b3
5 models
Minimum Subscription Basic
Context Size 32,768
Parameters 0.3B
Max Output
gemma3-0b2
193 models
Minimum Subscription Basic
Context Size 32,768
Parameters 0.3B
Max Output
lfm2-0b3
103 models
Minimum Subscription Basic
Context Size 32,768
Parameters 0.35B
Max Output
qwen2-0b5
3884 models
Minimum Subscription Basic
Context Size 32,768
Parameters 0.5B
Max Output
qwen25-0b5
147 models
Minimum Subscription Basic
Context Size 32,768
Parameters 0.5B
Max Output
gpt-sw3-356m
8 models
Minimum Subscription Basic
Context Size 2,048
Parameters 0.5B
Max Output
qwen15-0b5
42 models
Minimum Subscription Basic
Context Size 32,768
Parameters 0.6B
Max Output
qwen3-600m
0 models
Minimum Subscription Basic
Context Size 32,768
Parameters 0.6B
Max Output
qwen3-embedding-0b6
1 models
Minimum Subscription Basic
Context Size 32,768
Parameters 0.6B
Max Output
laya-0b6
0 models
Minimum Subscription Basic
Context Size 4,096
Parameters 0.6B
Max Output
lfm2-0b7
7 models
Minimum Subscription Basic
Context Size 32,768
Parameters 0.7B
Max Output
surya2-ocr
1 models
Minimum Subscription Basic
Context Size 262,144
Parameters 0.7B
Max Output
mamba-0b7
3 models
Minimum Subscription Basic
Context Size 32,768
Parameters 0.79B
Max Output
qwen3-0b6
1311 models
Minimum Subscription Basic
Context Size 32,768
Parameters 0.8B
Max Output
gemma3-1b
0 models
Minimum Subscription Basic
Context Size 32,768
Parameters 1B
Max Output
llama32-1b
2819 models
Minimum Subscription Basic
Context Size 32,768
Parameters 1B
Max Output
gemma3t-1b
403 models
Minimum Subscription Basic
Context Size 32,768
Parameters 1B
Max Output
granitemoe-1b
7 models
Minimum Subscription Basic
Context Size 32,768
Parameters 1B
Max Output
olmo-1b
11 models
Minimum Subscription Basic
Context Size 32,768
Parameters 1B
Max Output
tts-csm-1b
1 models
Minimum Subscription Basic
Context Size
Parameters 1B
Max Output
ovisocr-2
1 models
Minimum Subscription Basic
Context Size 262,144
Parameters 1B
Max Output
lightonocr-2
1 models
Minimum Subscription Basic
Context Size 16,384
Parameters 1B
Max Output
tinyllama-1b1
1338 models
Minimum Subscription Basic
Context Size 2,048
Parameters 1.1B
Max Output
gptbigcode-1b
2 models
Minimum Subscription Basic
Context Size 32,768
Parameters 1.1B
Max Output
k2-horizon-1b1
1 models
Minimum Subscription Basic
Context Size 32,768
Parameters 1.1B
Max Output
lfm2-1b2
1 models
Minimum Subscription Basic
Context Size 32,768
Parameters 1.2B
Max Output
lfm2-1b
154 models
Minimum Subscription Basic
Context Size 32,768
Parameters 1.2B
Max Output
gpt-sw3-1b3
5 models
Minimum Subscription Basic
Context Size 2,048
Parameters 1.4B
Max Output
phi-1b4
45 models
Minimum Subscription Basic
Context Size 2,048
Parameters 1.4B
Max Output
ouro-1b
12 models
Minimum Subscription Basic
Context Size 32,768
Parameters 1.4B
Max Output
qwen2-1b5
2383 models
Minimum Subscription Basic
Context Size 32,768
Parameters 1.5B
Max Output
qwen25-1b5
87 models
Minimum Subscription Basic
Context Size 32,768
Parameters 1.5B
Max Output
tts-dia-1b6
1 models
Minimum Subscription Basic
Context Size
Parameters 1.6B
Max Output
tts-zonos-1b6
0 models
Minimum Subscription Basic
Context Size
Parameters 1.6B
Max Output
tts-qwen3-tts-1b7
1 models
Minimum Subscription Basic
Context Size
Parameters 1.7B
Max Output
tts-zonos-1b7
0 models
Minimum Subscription Basic
Context Size
Parameters 1.7B
Max Output
qwen15-1b8
64 models
Minimum Subscription Basic
Context Size 32,768
Parameters 1.8B
Max Output
qwen3-1b7
1738 models
Minimum Subscription Basic
Context Size 32,768
Parameters 2B
Max Output
qwen3.5-2b
1 models
Minimum Subscription Basic
Context Size 32,768
Parameters 2B
Max Output
gemma4-e2b
2 models
Minimum Subscription Basic
Context Size 32,768
Parameters 2B
Max Output
qwen3vl-2b
52 models
Minimum Subscription Basic
Context Size 32,768
Parameters 2B
Max Output
Gemma-2b
15 models
Minimum Subscription Basic
Context Size 32,768
Parameters 2B
Max Output
granite-2b
23 models
Minimum Subscription Basic
Context Size 32,768
Parameters 2B
Max Output
stablelm-2b
18 models
Minimum Subscription Basic
Context Size 32,768
Parameters 2.2B
Max Output
qwen3_5-2b
134 models
Minimum Subscription Basic
Context Size 32,768
Parameters 2.3B
Max Output
gemma-2b
180 models
Minimum Subscription Basic
Context Size 8,192
Parameters 2.5B
Max Output
gemma2-2b
956 models
Minimum Subscription Basic
Context Size 8,192
Parameters 2.6B
Max Output
ouro-2b
10 models
Minimum Subscription Basic
Context Size 32,768
Parameters 2.6B
Max Output
rwkv7-2b9
1 models
Minimum Subscription Basic
Context Size 32,768
Parameters 2.9B
Max Output
phi2-3b
99 models
Minimum Subscription Basic
Context Size 2,048
Parameters 3B
Max Output
qwen25vl-3b
26 models
Minimum Subscription Basic
Context Size 32,768
Parameters 3B
Max Output
mistral3-3b
1 models
Minimum Subscription Basic
Context Size 32,768
Parameters 3B
Max Output
granitemoe-3b
6 models
Minimum Subscription Basic
Context Size 32,768
Parameters 3B
Max Output
tts-llama3-3b
1 models
Minimum Subscription Basic
Context Size
Parameters 3B
Max Output
qwen25-3b
1355 models
Minimum Subscription Basic
Context Size 32,768
Parameters 3.1B
Max Output
llama32-3b
906 models
Minimum Subscription Basic
Context Size 32,768
Parameters 3.2B
Max Output
music-ace-step-3b5
0 models
Minimum Subscription Basic
Context Size
Parameters 3.5B
Max Output
hcxvision-3b
2 models
Minimum Subscription Basic
Context Size 32,768
Parameters 3.7B
Max Output
phi4-3b8
54 models
Minimum Subscription Basic
Context Size 32,768
Parameters 3.8B
Max Output
qwen15-4b
15 models
Minimum Subscription Basic
Context Size 32,768
Parameters 4B
Max Output
qwen3-4b
3111 models
Minimum Subscription Basic
Context Size 32,768
Parameters 4B
Max Output
phi3-4b
123 models
Minimum Subscription Basic
Context Size 4,096
Parameters 4B
Max Output
mellum-4b
8 models
Minimum Subscription Basic
Context Size 32,768
Parameters 4B
Max Output
qwen3.5-4b
2 models
Minimum Subscription Basic
Context Size 32,768
Parameters 4B
Max Output
gemma4-e4b
2 models
Minimum Subscription Basic
Context Size 32,768
Parameters 4B
Max Output
qwen3-embedding-4b
1 models
Minimum Subscription Basic
Context Size 32,768
Parameters 4B
Max Output
qwen3vl-4b
94 models
Minimum Subscription Basic
Context Size 32,768
Parameters 4B
Max Output
nanbeige41-3b
1 models
Minimum Subscription Basic
Context Size 32,768
Parameters 4.1B
Max Output
phi3v-4b
8 models
Minimum Subscription Basic
Context Size 32,768
Parameters 4.1B
Max Output
gemma3-4b
355 models
Minimum Subscription Basic
Context Size 32,768
Parameters 4.3B
Max Output
qwen3_5-4b
428 models
Minimum Subscription Basic
Context Size 32,768
Parameters 4.5B
Max Output
arcee-4b5
1 models
Minimum Subscription Basic
Context Size 32,768
Parameters 4.5B
Max Output
gemma4-5b
232 models
Minimum Subscription Basic
Context Size 32,768
Parameters 5.1B
Max Output
k2-horizon-5b1
1 models
Minimum Subscription Basic
Context Size 32,768
Parameters 5.1B
Max Output
RWKV
rwkv5-7b
7 models
Minimum Subscription Basic
Context Size 16,384
Parameters 7B
Max Output
Mistral v0.2 7B
mistral-v02-7b-std-lc
0 models
Minimum Subscription Basic
Context Size 8,192
Parameters 7B
Max Output
rwkv6-7b-16k
0 models
Minimum Subscription Basic
Context Size 16,384
Parameters 7B
Max Output
qwen25-7b-lc
0 models
Minimum Subscription Basic
Context Size 32,768
Parameters 7B
Max Output
qwen2-7b-lc
0 models
Minimum Subscription Basic
Context Size 32,768
Parameters 7B
Max Output
llama2-7b
3688 models
Minimum Subscription Basic
Context Size 4,096
Parameters 7B
Max Output
mistral-v01-7b
1997 models
Minimum Subscription Basic
Context Size 4,096
Parameters 7B
Max Output
rwkv6-7b
1 models
Minimum Subscription Basic
Context Size 16,384
Parameters 7B
Max Output
mistral-v02-7b
616 models
Minimum Subscription Basic
Context Size 8,192
Parameters 7B
Max Output
olmo3-7b
1 models
Minimum Subscription Basic
Context Size 32,768
Parameters 7B
Max Output
qwen25vl-7b
47 models
Minimum Subscription Basic
Context Size 32,768
Parameters 7B
Max Output
mimo-7b
5 models
Minimum Subscription Basic
Context Size 32,768
Parameters 7B
Max Output
falcon-7b2
23 models
Minimum Subscription Basic
Context Size 32,768
Parameters 7B
Max Output
qwenlmheadmodel-7b
15 models
Minimum Subscription Basic
Context Size 32,768
Parameters 7B
Max Output
panguembedded-8b
4 models
Minimum Subscription Basic
Context Size 32,768
Parameters 7B
Max Output
zamba2-7b
1 models
Minimum Subscription Basic
Context Size 32,768
Parameters 7B
Max Output
gpt-sw3-6b7
4 models
Minimum Subscription Basic
Context Size 2,048
Parameters 7.1B
Max Output
gpt2-sw3-6b7
3 models
Minimum Subscription Basic
Context Size 2,048
Parameters 7.1B
Max Output
rwkv7-7b2
1 models
Minimum Subscription Basic
Context Size 32,768
Parameters 7.2B
Max Output
qwen2-7b
2585 models
Minimum Subscription Basic
Context Size 32,768
Parameters 7.6B
Max Output
qwen25-7b
239 models
Minimum Subscription Basic
Context Size 32,768
Parameters 7.6B
Max Output
qwen3-7b6
0 models
Minimum Subscription Basic
Context Size 32,768
Parameters 7.6B
Max Output
qwen15-7b
19 models
Minimum Subscription Basic
Context Size 32,768
Parameters 7.7B
Max Output
falcon-7b7
1 models
Minimum Subscription Basic
Context Size 32,768
Parameters 7.8B
Max Output
gemma4-7b
225 models
Minimum Subscription Basic
Context Size 32,768
Parameters 7.9B
Max Output
Llama 3.1 8B
llama31-8b-16k
0 models
Minimum Subscription Basic
Context Size 32,768
Parameters 8B
Max Output
qwen3-8b
2346 models
Minimum Subscription Basic
Context Size 32,768
Parameters 8B
Max Output
llama31-8b
2209 models
Minimum Subscription Basic
Context Size 32,768
Parameters 8B
Max Output
llama3-8b
3042 models
Minimum Subscription Basic
Context Size 8,192
Parameters 8B
Max Output
qwen3-embedding-8b
1 models
Minimum Subscription Basic
Context Size 32,768
Parameters 8B
Max Output
apertus-8b
8 models
Minimum Subscription Basic
Context Size 32,768
Parameters 8B
Max Output
qwen3vl-8b
268 models
Minimum Subscription Basic
Context Size 32,768
Parameters 8B
Max Output
granite-8b
27 models
Minimum Subscription Basic
Context Size 32,768
Parameters 8B
Max Output
internlm3-8b
3 models
Minimum Subscription Basic
Context Size 32,768
Parameters 8B
Max Output
qwen3-8b2
0 models
Minimum Subscription Basic
Context Size 32,768
Parameters 8.2B
Max Output
gemma3-8b3
2 models
Minimum Subscription Basic
Context Size 32,768
Parameters 8.3B
Max Output
gemma-7b
80 models
Minimum Subscription Basic
Context Size 8,192
Parameters 8.5B
Max Output
gemma2-9b
374 models
Minimum Subscription Basic
Context Size 16,384
Parameters 9B
Max Output
glm4-9b
60 models
Minimum Subscription Basic
Context Size 32,768
Parameters 9B
Max Output
qwen3.5-9b
4 models
Minimum Subscription Basic
Context Size 32,768
Parameters 9B
Max Output
qwen3_5-9b
636 models
Minimum Subscription Basic
Context Size 32,768
Parameters 9B
Max Output
bamba-9b
2 models
Minimum Subscription Basic
Context Size 32,768
Parameters 9B
Max Output
k2-horizon-9b
1 models
Minimum Subscription Basic
Context Size 32,768
Parameters 9B
Max Output
Llama 2 Solar 10B
llama2-solar-10b7-4k
0 models
Minimum Subscription Basic
Context Size 4,096
Parameters 10.7B
Max Output
llama2-10b7
0 models
Minimum Subscription Basic
Context Size 4,096
Parameters 10.7B
Max Output
llama2-solar-10b7
293 models
Minimum Subscription Basic
Context Size 4,096
Parameters 10.7B
Max Output
gemma3-12b
183 models
Minimum Subscription Basic
Context Size 32,768
Parameters 12B
Max Output
mistral-nemo
656 models
Minimum Subscription Basic
Context Size 32,768
Parameters 12B
Max Output
gemma4unified-12b
128 models
Minimum Subscription Basic
Context Size 32,768
Parameters 12B
Max Output
gemma4-12b
1 models
Minimum Subscription Basic
Context Size 32,768
Parameters 12B
Max Output
gemma3t-12b
3 models
Minimum Subscription Basic
Context Size 32,768
Parameters 12.2B
Max Output
Mistral Nemo 12B
mistral-nemo-12b-lc
16 models
Minimum Subscription Basic
Context Size 32,768
Parameters 12.2B
Max Output
Llama 2 13B
llama2-13b-4k
0 models
Minimum Subscription Basic
Context Size 4,096
Parameters 13B
Max Output
llama2-13b
1569 models
Minimum Subscription Basic
Context Size 4,096
Parameters 13B
Max Output
talkie-13b
5 models
Minimum Subscription Basic
Context Size 32,768
Parameters 13B
Max Output
rwkv7-13b3
1 models
Minimum Subscription Basic
Context Size 32,768
Parameters 13.3B
Max Output
rwkv6-14b-16k
0 models
Minimum Subscription Basic
Context Size 16,384
Parameters 14B
Max Output
qwen25-14b-lc
0 models
Minimum Subscription Basic
Context Size 32,768
Parameters 14B
Max Output
qwen2-14b-lc
50 models
Minimum Subscription Basic
Context Size 32,768
Parameters 14B
Max Output
qwen3-14b
453 models
Minimum Subscription Basic
Context Size 32,768
Parameters 14B
Max Output
rwkv6-14b
1 models
Minimum Subscription Basic
Context Size 16,384
Parameters 14B
Max Output
qwen15-14b
19 models
Minimum Subscription Basic
Context Size 32,768
Parameters 14.2B
Max Output
phi4-14b
75 models
Minimum Subscription Basic
Context Size 32,768
Parameters 14.7B
Max Output
qwen25-14b
579 models
Minimum Subscription Basic
Context Size 32,768
Parameters 14.8B
Max Output
Llama 3 15B
llama3-15b-8k
0 models
Minimum Subscription Basic
Context Size 8,192
Parameters 15B
Max Output
llama3-15b
68 models
Minimum Subscription Basic
Context Size 8,192
Parameters 15B
Max Output
gpt-oss-20b
3 models
Minimum Subscription Basic
Context Size 131,072
Parameters 20B
Max Output
gptoss-21b
59 models
Minimum Subscription Basic
Context Size 32,768
Parameters 20B
Max Output
gpt-sw3-20b
3 models
Minimum Subscription Basic
Context Size 2,048
Parameters 20.9B
Max Output
ernie4_5_moe-21b
23 models
Minimum Subscription Basic
Context Size 32,768
Parameters 21B
Max Output
mistral-24b-2503
84 models
Minimum Subscription Basic
Context Size 32,768
Parameters 24B
Max Output
mistral-24b
359 models
Minimum Subscription Basic
Context Size 32,768
Parameters 24B
Max Output
lfm2-moe-24b
1 models
Minimum Subscription Basic
Context Size 32,768
Parameters 24B
Max Output
gemma4-26b
3 models
Minimum Subscription Basic
Context Size 32,768
Parameters 26B
Max Output
gemma4-25b
136 models
Minimum Subscription Basic
Context Size 32,768
Parameters 26B
Max Output
gemma3-27b
114 models
Minimum Subscription Basic
Context Size 32,768
Parameters 27B
Max Output
gemma2-27b
40 models
Minimum Subscription Basic
Context Size 32,768
Parameters 27B
Max Output
gemma3t-27b
19 models
Minimum Subscription Basic
Context Size 32,768
Parameters 27B
Max Output
qwen3.5-27b
5 models
Minimum Subscription Basic
Context Size 32,768
Parameters 27B
Max Output
qwen3_5-27b
608 models
Minimum Subscription Basic
Context Size 32,768
Parameters 27B
Max Output
qwen3-5vl-27b8
1 models
Minimum Subscription Basic
Context Size 32,768
Parameters 27.8B
Max Output
qwen3-coder-30b
0 models
Minimum Subscription Premium
Context Size 32,768
Parameters 30B
Max Output
qwen3moe-30b
4 models
Minimum Subscription Basic
Context Size 32,768
Parameters 30B
Max Output
glm47-flash
1 models
Minimum Subscription Basic
Context Size 202,752
Parameters 30B
Max Output
qwen3vlmoe-30b
1 models
Minimum Subscription Basic
Context Size 131,072
Parameters 30B
Max Output
nemotronh-31b
47 models
Minimum Subscription Basic
Context Size 32,768
Parameters 30B
Max Output
glimmer-30b
31 models
Minimum Subscription Basic
Context Size 131,072
Parameters 30B
Max Output
gemma4-31b
197 models
Minimum Subscription Basic
Context Size 32,768
Parameters 31B
Max Output
Qwen 2 32B
qwen2-32b-lc
0 models
Minimum Subscription Basic
Context Size 32,768
Parameters 32B
Max Output
qrwkv-32b-32k
4 models
Minimum Subscription Basic
Context Size 32,768
Parameters 32B
Max Output
qwen15-32b-lc
0 models
Minimum Subscription Basic
Context Size 32,768
Parameters 32B
Max Output
qwen25-32b-lc
0 models
Minimum Subscription Basic
Context Size 32,768
Parameters 32B
Max Output
qwen3-32b
704 models
Minimum Subscription Basic
Context Size 32,768
Parameters 32B
Max Output
glm4-32b
27 models
Minimum Subscription Basic
Context Size 32,768
Parameters 32B
Max Output
qwen2-32b
49 models
Minimum Subscription Basic
Context Size 32,768
Parameters 32B
Max Output
olmo3-32b
1 models
Minimum Subscription Basic
Context Size 32,768
Parameters 32B
Max Output
qwen25vl-32b
21 models
Minimum Subscription Basic
Context Size 32,768
Parameters 32B
Max Output
exaone4-32b
2 models
Minimum Subscription Basic
Context Size 32,768
Parameters 32B
Max Output
qwen15-32b
15 models
Minimum Subscription Basic
Context Size 32,768
Parameters 32.5B
Max Output
qwen25-32b
518 models
Minimum Subscription Basic
Context Size 32,768
Parameters 32.8B
Max Output
qwen3vl-32b
37 models
Minimum Subscription Basic
Context Size 32,768
Parameters 33.4B
Max Output
Yi 1.5 34B
yi1.5-34b-lc
1 models
Minimum Subscription Basic
Context Size 16,384
Parameters 34B
Max Output
llama2-34b
50 models
Minimum Subscription Basic
Context Size 16,384
Parameters 34B
Max Output
llama-34b
124 models
Minimum Subscription Basic
Context Size 32,768
Parameters 34B
Max Output
k2-horizon-34b8
1 models
Minimum Subscription Basic
Context Size 32,768
Parameters 34.8B
Max Output
qwen3-5-moevl-35b
2 models
Minimum Subscription Basic
Context Size 32,768
Parameters 35B
Max Output
qwen3_5moe-35b
962 models
Minimum Subscription Basic
Context Size 32,768
Parameters 35.1B
Max Output
k2-horizon-36b
1 models
Minimum Subscription Basic
Context Size 32,768
Parameters 36B
Max Output
rwkv6moe-37b-16k
0 models
Minimum Subscription Basic
Context Size 16,384
Parameters 37B
Max Output
rwkv6moe-37b
1 models
Minimum Subscription Basic
Context Size 16,384
Parameters 37B
Max Output
gpt-sw3-40b
1 models
Minimum Subscription Basic
Context Size 32,768
Parameters 39.9B
Max Output
phimoe-42b
3 models
Minimum Subscription Basic
Context Size 32,768
Parameters 41.9B
Max Output
kimi-linear-48b
1 models
Minimum Subscription Basic
Context Size 32,768
Parameters 48B
Max Output
kimilinear-49b
0 models
Minimum Subscription Basic
Context Size 32,768
Parameters 48B
Max Output
decilm-49b
11 models
Minimum Subscription Basic
Context Size 32,768
Parameters 49B
Max Output
llama2-70b
179 models
Minimum Subscription Premium
Context Size 4,096
Parameters 69B
Max Output
Llama 3 70B
llama3-70b-8k
0 models
Minimum Subscription Premium
Context Size 8,192
Parameters 70B
Max Output
Llama 3.1 70B
llama31-70b-16k
0 models
Minimum Subscription Premium
Context Size 32,768
Parameters 70B
Max Output
llama31-70b
361 models
Minimum Subscription Premium
Context Size 32,768
Parameters 70B
Max Output
llama33-70b
140 models
Minimum Subscription Premium
Context Size 32,768
Parameters 70B
Max Output
llama3-70b
201 models
Minimum Subscription Premium
Context Size 8,192
Parameters 70B
Max Output
apertus-70b
5 models
Minimum Subscription Premium
Context Size 32,768
Parameters 70B
Max Output
Qwen 2 72B
qwen2-72b-lc
0 models
Minimum Subscription Premium
Context Size 32,768
Parameters 72B
Max Output
qwen25-72b-lc
0 models
Minimum Subscription Premium
Context Size 32,768
Parameters 72B
Max Output
qrwkv-72b-32k
1 models
Minimum Subscription Basic
Context Size 65,536
Parameters 72B
Max Output
qwrkv-72b-32k
0 models
Minimum Subscription Basic
Context Size 32,768
Parameters 72B
Max Output
qrwkv-72b
0 models
Minimum Subscription Basic
Context Size 16,384
Parameters 72B
Max Output
qwen25vl-72b
4 models
Minimum Subscription Premium
Context Size 32,768
Parameters 72B
Max Output
qwen15-72b
10 models
Minimum Subscription Premium
Context Size 32,768
Parameters 72.3B
Max Output
qwen2-72b
108 models
Minimum Subscription Premium
Context Size 32,768
Parameters 72.7B
Max Output
qwen25-72b
47 models
Minimum Subscription Premium
Context Size 32,768
Parameters 72.7B
Max Output
qwen3moe-80b
1 models
Minimum Subscription Basic
Context Size 32,768
Parameters 80B
Max Output
qwen3next-80b
2 models
Minimum Subscription Premium
Context Size 32,768
Parameters 80B
Max Output
qwen15-110b
0 models
Minimum Subscription Premium
Context Size 32,768
Parameters 111.2B
Max Output
laguna-s-21
1 models
Minimum Subscription Premium
Context Size 256,000
Parameters 118B
Max Output
gpt-oss-120b
1 models
Minimum Subscription Basic
Context Size 131,072
Parameters 120B
Max Output
nemotron3-120b
1 models
Minimum Subscription Premium
Context Size 262,144
Parameters 120B
Max Output
mistral-large
1 models
Minimum Subscription Premium
Context Size 32,768
Parameters 123B
Max Output
mistral-3.5
1 models
Minimum Subscription Premium
Context Size 128,000
Parameters 128B
Max Output
Mixtral 8x22B
mixtral-8x22b-lc
0 models
Minimum Subscription Premium
Context Size 16,384
Parameters 141B
Max Output
mixtral-8x22b
1 models
Minimum Subscription Premium
Context Size 32,768
Parameters 141B
Max Output
deepseek4-158b
0 models
Minimum Subscription Premium
Context Size 262,144
Parameters 158B
Max Output
qwen4-expvl-180b
1 models
Minimum Subscription Premium
Context Size 32,768
Parameters 180B
Max Output
step-3.5-199b
1 models
Minimum Subscription Premium
Context Size 262,144
Parameters 199B
Max Output
step3p7vl-201b4
1 models
Minimum Subscription Premium
Context Size 32,768
Parameters 201.4B
Max Output
minimax-m2-228b7
1 models
Minimum Subscription Premium
Context Size 204,800
Parameters 228.7B
Max Output
minimax-m2
1 models
Minimum Subscription Premium
Context Size 204,800
Parameters 229B
Max Output
minimax-m21
1 models
Minimum Subscription Premium
Context Size 204,800
Parameters 229B
Max Output
minimax-m25
1 models
Minimum Subscription Premium
Context Size 204,800
Parameters 229B
Max Output
qwen3-235b
1 models
Minimum Subscription Premium
Context Size 32,768
Parameters 235B
Max Output
qwen3vl-235b
1 models
Minimum Subscription Premium
Context Size 32,768
Parameters 235B
Max Output
qwen3moe-235b
1 models
Minimum Subscription Premium
Context Size 32,768
Parameters 235B
Max Output
deepseek4-284b
2 models
Minimum Subscription Premium
Context Size 262,144
Parameters 284B
Max Output
hy-v3-298b8
1 models
Minimum Subscription Premium
Context Size 32,768
Parameters 298.8B
Max Output
mimo2-flash
1 models
Minimum Subscription Premium
Context Size 262,144
Parameters 310B
Max Output
mimo25-311b
1 models
Minimum Subscription Premium
Context Size 32,768
Parameters 311B
Max Output
glm5-next-321b3
1 models
Minimum Subscription Premium
Context Size 262,144
Parameters 321.3B
Max Output
glm-45
0 models
Minimum Subscription Premium
Context Size 202,752
Parameters 357B
Max Output
glm46-357b
1 models
Minimum Subscription Premium
Context Size 202,752
Parameters 357B
Max Output
glm47-357b
1 models
Minimum Subscription Premium
Context Size 202,752
Parameters 357B
Max Output
glm47-358b
0 models
Minimum Subscription Premium
Context Size 202,752
Parameters 358B
Max Output
k2-horizon-375b
1 models
Minimum Subscription Premium
Context Size 32,768
Parameters 375B
Max Output
qwen3.5-397b
1 models
Minimum Subscription Premium
Context Size 262,144
Parameters 397B
Max Output
afmoe-399b
1 models
Minimum Subscription Premium
Context Size 262,144
Parameters 399B
Max Output
Llama 3 405B
llama3-405b-lc
0 models
Minimum Subscription Premium
Context Size 4,096
Parameters 405B
Max Output
minimax-m3
1 models
Minimum Subscription Premium
Context Size 262,144
Parameters 427B
Max Output
qwen3-coder-480b
1 models
Minimum Subscription Premium
Context Size 32,768
Parameters 480B
Max Output
deepseek-v3-lc
2 models
Minimum Subscription Premium
Context Size 131,072
Parameters 685B
Max Output
deepseek-v3.2
1 models
Minimum Subscription Premium
Context Size 131,072
Parameters 685B
Max Output
deepseek31-685b
2 models
Minimum Subscription Premium
Context Size 131,072
Parameters 685B
Max Output
glm52-753b
1 models
Minimum Subscription Premium
Context Size 262,144
Parameters 753B
Max Output
glm-moe-dsa-753b3
1 models
Minimum Subscription Premium
Context Size 262,144
Parameters 753.3B
Max Output
glm5-754b
1 models
Minimum Subscription Premium
Context Size 202,752
Parameters 754B
Max Output
glm51-754b
1 models
Minimum Subscription Premium
Context Size 202,752
Parameters 754B
Max Output
deepseek4-763b
1 models
Minimum Subscription Premium
Context Size 262,144
Parameters 763B
Max Output
deepseek4-1.6t
1 models
Minimum Subscription Premium
Context Size 262,144
Parameters 862B
Max Output
kimi-k2
3 models
Minimum Subscription Premium
Context Size 32,768
Parameters 1,000B
Max Output
ling2-1t
0 models
Minimum Subscription Premium
Context Size 32,768
Parameters 1,000B
Max Output
kimi-k25
3 models
Minimum Subscription Premium
Context Size 262,144
Parameters 1,000B
Max Output
ring2-1000b
0 models
Minimum Subscription Premium
Context Size 32,768
Parameters 1,000B
Max Output
qwen38-2400b
1 models
Minimum Subscription Premium
Context Size 262,144
Parameters 2,400B
Max Output
kimi3-2780b
1 models
Minimum Subscription Premium
Context Size 262,144
Parameters 2,780B
Max Output
kimi-k3
0 models
Minimum Subscription Premium
Context Size 262,144
Parameters 2,800B
Max Output