cognitivecomputations
Mistral

Venice: Uncensored

cognitivecomputations/dolphin-mistral-24b-venice-edition
Контекст
128 000
Вход токены
24,61 ₽/M
Выход токены
110,75 ₽/M
описание

Venice Uncensored Dolphin Mistral 24B Venice Edition is a fine-tuned variant of Mistral-Small-24B-Instruct-2501, developed by dphn.ai in collaboration with Venice.ai. This model is designed as an “uncensored” instruct-tuned LLM, preserving...

модальности
интеграция

Как использовать через API

bash
# Запрос к API VEGA через cognitivecomputations/dolphin-mistral-24b-venice-edition
curl https://api.vega.chat/api/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $VEGA_API_KEY" \
  -d '{
    "model": "cognitivecomputations/dolphin-mistral-24b-venice-edition",
    "messages": [
      {  "role": "user", "content": "Hello!"  }
    ]
  }'