Chat-based language models

Try the LLM extension Show all providers

Connect more than 10 providers

and access an infinite number of models

GPT-5

chat Use GPT-5

GPT-5 Mini

chat Use GPT-5 Mini

GPT-5 Nano

chat Use GPT-5 Nano

GPT-5-Chat Latest

chat Use GPT-5-Chat Latest

GPT-4.1

chat Use GPT-4.1

GPT-4.1 nano

chat Use GPT-4.1 nano

o4 Mini

chat Use o4 Mini

o1 Pro

chat Use o1 Pro

o3 Pro

chat Use o3 Pro

o3 Mini

chat Use o3 Mini

o1

chat Use o1

o1 Mini

chat Use o1 Mini

GPT-4o

chat Use GPT-4o

GPT-4o-mini

chat Use GPT-4o-mini

GPT-4 Turbo

chat Use GPT-4 Turbo

GPT-3.5 Turbo

chat Use GPT-3.5 Turbo

Claude Opus 4

chat Use Claude Opus 4

Claude Sonnet 4

chat Use Claude Sonnet 4

Claude Sonnet 3.7

chat Use Claude Sonnet 3.7

Claude Sonnet 3.5

chat Use Claude Sonnet 3.5

Claude Haiku 3.5

chat Use Claude Haiku 3.5

Claude 3 Opus

chat Use Claude 3 Opus

Claude 3 Sonnet

chat Use Claude 3 Sonnet

Claude 3 Haiku

chat Use Claude 3 Haiku

Gemini 2.5 Pro

chat Use Gemini 2.5 Pro

Gemini 2.5 Flash

chat Use Gemini 2.5 Flash

Gemini 2.5 Flash Lite

chat Use Gemini 2.5 Flash Lite

Gemini 2.5 Flash Live

chat Use Gemini 2.5 Flash Live

Gemini 1.5 Pro

chat Use Gemini 1.5 Pro

Gemini 1.5 Flash

chat Use Gemini 1.5 Flash

Gemma 3 1B

chat Use Gemma 3 1B

Gemma 3 4B

chat Use Gemma 3 4B

Gemma 3 12B

chat Use Gemma 3 12B

Gemma 3 27B

chat Use Gemma 3 27B

Qwen 32B

chat Use Qwen 32B

DeepSeek R1 7B

chat Use DeepSeek R1 7B

DeepSeek R1 671B

chat Use DeepSeek R1 671B

LLaMA 4 Scout 109B

chat Use LLaMA 4 Scout 109B

LLaMA 4 Maverick 400B

chat Use LLaMA 4 Maverick 400B

LLaMA 3.3 70B

chat Use LLaMA 3.3 70B

LLaMA 3.2 27B

chat Use LLaMA 3.2 27B

LLaMA 3.2 3B

chat Use LLaMA 3.2 3B

LLaMA 3.2 1B

chat Use LLaMA 3.2 1B

Phi 4 14B

chat Use Phi 4 14B

Phi 4 Mini 3.8B

chat Use Phi 4 Mini 3.8B

Mistral 7B

chat Use Mistral 7B

Moondream 2 1.4B

chat Use Moondream 2 1.4B

Neural Chat 7B

chat Use Neural Chat 7B

Starling LM 7B

chat Use Starling LM 7B

LLaMA 2 Uncensored 7B

chat Use LLaMA 2 Uncensored 7B

Granite 3.3 8B

chat Use Granite 3.3 8B

Mistral 7B

chat Use Mistral 7B

Mixtral 8x7B

chat Use Mixtral 8x7B

Mistral 7B

chat Use Mistral 7B

llama-3.3-70b-instruct

chat Use llama-3.3-70b-instruct

llama-3.1-8b-instruct

chat Use llama-3.1-8b-instruct

qwen2.5-coder-32b-instruct

chat Use qwen2.5-coder-32b-instruct

deepseek-r1

chat Use deepseek-r1

deepseek-r1-distill-llama-70b

chat Use deepseek-r1-distill-llama-70b

Mixtral 8x7B

chat Use Mixtral 8x7B

Deepseek Coder

chat Use Deepseek Coder

Deepseek LLM

chat Use Deepseek LLM

Deepseek Chat (DeepSeek-V3-0324)

chat Use Deepseek Chat (DeepSeek-V3-0324)

Deepseek Reasoner (DeepSeek-R1-0528)

chat Use Deepseek Reasoner (DeepSeek-R1-0528)

Grok 4

chat Use Grok 4

Grok 3

chat Use Grok 3

Grok 3 Mini

chat Use Grok 3 Mini

Grok 3 Fast

chat Use Grok 3 Fast

Grok 3 Mini Fast

chat Use Grok 3 Mini Fast

llama-4-scout-17b-16e-instruct

chat Use llama-4-scout-17b-16e-instruct

mistral-small-3.1-24b-instruct

chat Use mistral-small-3.1-24b-instruct

llama-guard-3-8b

chat Use llama-guard-3-8b

gemma-3-12b-it

chat Use gemma-3-12b-it

LLaMA 3

chat Use LLaMA 3

Mistral

chat Use Mistral

Gemma

chat Use Gemma

LLaMA 3 8B

chat Use LLaMA 3 8B

Mixtral 8x7B

chat Use Mixtral 8x7B

Gemma 7B

chat Use Gemma 7B

facebook/bart-large-cnn

chat Use facebook/bart-large-cnn

Meta-Llama-3_3-70B-Instruct

chat Use Meta-Llama-3_3-70B-Instruct

NVIDIA-RIVA

chat Use NVIDIA-RIVA

Qwen/Qwen2.5-VL-72B-Instruct

chat Use Qwen/Qwen2.5-VL-72B-Instruct

mistralai/Mistral-Nemo-Instruct-2407

chat Use mistralai/Mistral-Nemo-Instruct-2407

llava-next-mistral-7b

chat Use llava-next-mistral-7b

Command R

chat Use Command R

Command R+

chat Use Command R+

GPT-4

chat Use GPT-4

GPT-3.5

chat Use GPT-3.5

LLaMA 3 8B

chat Use LLaMA 3 8B

Tester maintenant avec nos instances managées