Effort levels
The Agent control in the composer sets the effort for the next turn. The default is Basic.
| Lite | Basic (default) | Deep | |
|---|---|---|---|
| Searches per turn | up to 4 | up to 8 | unlimited |
| Sub-agents (parallel delegation) | no | yes | yes |
| Report | none — a sourced chat answer is the deliverable | 3–4 section report | 3–6 section, longer report |
| Coverage checks and gap planning | off | on | on |
| Review repair | off | on | on, with re-runs |
| Steps per turn | 14 | 30 | 48 |
| Illustration quality | draft | standard | publication |
| Typical literature turn | ~150 credits | ~400–500 | ~800+ |
Use Lite for quick questions and orientation, Basic for day-to-day research turns, Deep for the final pass on something that matters. The level applies to the whole turn, including report synthesis and review.
Models
The Model control chooses the model for the next turn. Gemini, Claude and ChatGPT models are available on managed cloud credits; models marked premium use more credits per token and are not selectable on the Free plan.
When you don't pick a model, the router picks a tier per task: a stronger model for research and writing, a faster one for analysis code. Lite drops one tier to save credits.
Your own keys and local models
Turns that run on your own provider keys (Gemini, Anthropic, OpenAI) or on a local model server (Ollama, vLLM) are never billed as credits — they are unlimited on every plan, including Free. The per-account settings for adding keys and pointing Neutropic at a local server are rolling out with the desktop app; until then, turns run on managed credits. Watch the changelog.
Research-platform tokens (Scopus, Web of Science and similar) for the search skills are coming to Customize as well; open databases need none.
Credits
A credit is worth $0.001 of managed tokens. Each answer shows the tokens it used; the profile menu and Customize → Usage show the month's balance, the daily cap and a per-session breakdown. See Plans & credits.