Click ‘Void Settings’

Enter baseURL [ https://api.venice.ai/api/v1 ] and your API Key [https://venice.ai/settings/api]

Click ‘Add Model’

Current models, type the name as listed or ‘default_code’ for the default.

1. llama-3.3-70b
   • Context Tokens: 65,536
   • Traits: Function calling, default
   • Source: Meta Llama 3.3 70B
2. llama-3.2-3b
   • Context Tokens: 131,072
   • Traits: Fastest
   • Source: Meta Llama 3.2 3B
3. dolphin-2.9.2-qwen2-72b
   • Context Tokens: 32,768
   • Traits: Most uncensored
   • Source: Dolphin 2.9.2 Qwen2 72B
4. llama-3.1-405b
   • Context Tokens: 63,920
   • Traits: Most intelligent
   • Source: Meta Llama 3.1 405B
5. qwen32b
   • Context Tokens: 131,072
   • Traits: Default code
   • Source: Qwen 32B Coder
6. deepseek-r1-llama-70b
   • Context Tokens: 65,536
   • Traits: None listed
   • Source: DeepSeek R1 Llama 70B
7. deepseek-r1-671b
   • Context Tokens: 131,072
   • Traits: None listed
   • Source: DeepSeek R1 671B