Models
Which AI models does Operant support?
Operant supports seven frontier models: GPT-6 Astra and GPT-6.1 Sol from OpenAI; Claude Opus 5.5, Claude Sonnet 5 and Claude Fable 5.1 from Anthropic; and Gemini 4 Argon and Gemini 3.8 Flash from Google. You choose the model and reasoning effort for each conversation and voice call, no API keys required.
Model comparison
| Model | Provider | Best for | Reasoning effort |
|---|---|---|---|
| GPT-6 Astra | OpenAI | Hardest reasoning, research, planning | Low – Max |
| GPT-6.1 Sol | OpenAI | Fast, strong everyday work | Low – Max |
| Claude Opus 5.5 | Anthropic | Long, careful agentic tasks and writing | Low – Max |
| Claude Sonnet 5 | Anthropic | Balanced speed and intelligence | Low – Max |
| Claude Fable 5.1 | Anthropic | Demanding reasoning | Low – Max |
| Gemini 4 Argon | Large context, multi-document analysis | Low – High | |
| Gemini 3.8 Flash | Fastest replies, high volume | Off – High |
Model questions
Which AI models can I use?
GPT-6 Astra and GPT-6.1 Sol from OpenAI, Claude Opus 5.5, Claude Sonnet 5 and Claude Fable 5.1 from Anthropic, and Gemini 4 Argon and Gemini 3.8 Flash from Google. You choose the model and reasoning effort for each conversation.
What is reasoning effort?
Reasoning effort controls how long a model thinks before answering. Low is fast and cheap for everyday questions; high and max think longer for analysis, planning and tricky problems.
Do I need API keys?
No. Models are included and run through Operant. You don't need accounts with OpenAI, Anthropic or Google.
Put AI colleagues to work today
Free to start. No API keys, no setup, your first colleagues are waiting.