Skip to content

LLMs & Privacy

When you use The Assistant, we make API requests to third-party model providers to generate responses. We are committed to protecting your privacy. The table below provides an overview of how each provider handles your data, including training practices, retention policies, and links to their privacy documentation.

ModelModel ProviderTrains on User Data via APIData Retention for APIPrivacy Policy / FAQ
  • Claude 3.5 Haiku
  • Claude 3.7 Sonnet
  • Claude 3.7 Sonnet with extended thinking
  • Claude 4 Sonnet
  • Claude 4 Sonnet with extended thinking
  • Claude 3 Opus
  • Claude 4 Opus
  • Claude 4 Opus with extended thinking
  • Anthropic
  • Amazon Bedrock
No30 days (flagged prompts: 2 years)
  • GPT 4o
  • ChatGPT 4o
  • GPT 4o mini
  • o3 mini
  • o4 mini
  • GPT 4.1
  • GPT 4.1 mini
  • GPT 4.1 nano
  • OpenAI
  • Microsoft Azure
No30 days
  • Mistral Pixtral
  • Mistral Large
  • Mistral Medium
  • Mistral AI
  • Microsoft Azure
No30 days
  • Mistral Small
  • Nebius
  • Mistral AI
No30 days
  • Gemini 2.0 Flash
  • Gemini 2.5 Flash Preview
  • Gemini 1.5 Pro
  • Gemini 2.5 Pro Preview
  • Google
No24 hours
  • Nova Lite
  • Nova Pro
  • Amazon
NoNot stored
  • Llama 3.3 70B
  • Llama 3.1 405B
  • Llama 4 Scout
  • Llama 4 Maverick
  • DeepSeek Chat V3
  • DeepSeek R1
  • Fireworks.ai
  • Together.ai
NoNot stored
  • Qwen QwQ 32b
  • Groq
  • Fireworks.ai
NoNot stored
  • Qwen 3 235B
  • Qwen 3 235B with Thinking
  • Qwen 3 30B with Thinking
  • Nebius
  • Fireworks.ai
NoNot stored
  • Qwen 3 32B
  • Qwen 3 32B with Thinking
  • Nebius
NoNot stored
  • Custom privacy agreement with Nebius
  • DeepSeek R1 Distill Llama 70B
  • Groq
  • Together.ai
NoNot stored
  • Grok 3
  • Grok 3 mini
  • xAI
No30 days