Model Selection & Cost Control

How to Optimize Credits & Configure Custom BYOK Models

Combine WorkBuddy's built-in TokenHub routing with your own API keys (Avatar → Settings → Models) to balance frontier reasoning quality and token cost.

1. Tier Your Models by Task Complexity

Use Claude Sonnet 4.6 or GPT-5.4 for high-level planning and slide narrative, while routing bulk CSV cleaning and log summarization to DeepSeek-V3.2 or Gemini 2.5 Flash to cut credit consumption by up to 70%.

2. Use 1M-Context Models for Multi-Document Audits

Select Gemini 2.5 Pro when cross-checking dozens of local PDFs or large codebases so the agent inspects full documents without chunk-boundary loss.

3. Connect BYOK & Local Ollama Endpoints

In Settings → Models, add any OpenAI-compatible API key (OpenAI, Anthropic, DeepSeek, Gemini, OpenRouter) or a local Ollama server to run tasks at zero WorkBuddy credit cost.

4. Specify Verifiable Deliverable Paths

Always define the target folder and output filename (.pptx, .xlsx, .md) up front so the agent validates its output in a single pass without costly retries.