BriefLoopBRIEFLOOP / GUIDES
Models and costs
Understand execution, data recipients and billing.
Applies to desktop 0.21.0 and the 0.20.x service. Labels and capabilities vary by channel; the installer version is authoritative. Development features are not implied.
Before you start
Use a workspace you can back up. Model tasks require an authenticated runtime and permission to process the chosen materials.
Steps
- A runtime is the local execution tool; a model is the generation service it connects to. Authenticate or configure its API first, then select it in BriefLoop.
- Use a model ID supported by that runtime. Saving settings is not a successful connection test; validate with a short public-text conversation.
- The main agent, Evaluator, Wiki Maintainer and Skill Proposer can use separate models. Evaluation and learning may also consume model usage.
- Set research limits, length and execution time. These are not a complete monetary cap; metering of runtime-native search varies.
- Check actual quotas and bills with the model and search providers. BriefLoop does not supply their subscriptions or model credits.
What success looks like
The first conversation should return an actual response. New tasks use saved settings; queued and running tasks retain their original configuration.
If something goes wrong
For quota errors, 429, 503 or an unknown model, inspect the task error and runtime authentication. Matching model names do not imply shared subscriptions. Read-only and network controls vary by runtime.