Running OpenClaw with Anthrophic API and it burned through ~USD 50 in one day.
What are other OpenClaw users seeing? Anyone found effective ways to cut costs (model tiering, caching, etc.)?
👤 NetworkPerson Accepted Answer ✓
I found it far too expensive for Anthropic. Entire context of every conversation is sent each time you type anything. Switched to a local model running from Ollama. Not quite as smart as opus, but good enough for my needs.
👤 atemerev
Had to write my own agent which is better with token economy: https://lethe.gg