Skip to content

Dolphin Mistral 24B Venice Edition

JSON
cognitivecomputations/dolphin-mistral-24b-venice-edition

Text · 128K context · Jul 2025 · 1 upstreams

Dolphin Mistral 24B Venice Edition is an uncensored instruct model fine-tuned from Mistral Small 24B by dphn.ai and Venice.ai. It keeps the user in control of system prompts and alignment.

Needs your own keyTo use Dolphin Mistral 24B Venice Edition, add a key from OpenRouter. AnyRouter adds no fee.
context
128K
input / 1M (list)
$0.20
output / 1M (list)
$0.90
routes
1
speed, 24h
No data yet

Upstreams

1
  1. 1OpenRouterBYOKnot addedBilled to your key

Compare

Compared with models of similar price and context window.

ModelIn / out per 1MContext
Dolphin Mistral 24B Venice Edition$0.20 / $0.90128K (second best)
Qwen2.5-72B-Instruct$0.36 / $0.40128K (second best)
DeepSeek V3.1$0.21 / $0.79 (second best)131K (best)
Llama 3.1 70B Instruct$0.40 / $0.40131K (best)
Cydonia 24B V4.1$0.30 / $0.50 (best)131K (best)

Quick start

curl https://anyrouter.dev/api/v1/chat/completions \
  -H "Authorization: Bearer $ANYROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "cognitivecomputations/dolphin-mistral-24b-venice-edition",
  "messages": [
    {
      "role": "user",
      "content": "Say hi in 3 words."
    }
  ]
}'

Details

Owner
Cognitivecomputations
Kind
Chat
Released
Jul 2025
Context
128K
Data policy
Provider retention
Endpoint
/api/v1/chat/completions