OpenModel tracks AI agent tokens and costs locally
OpenModel is a tool for running and connecting AI models on a local computer or through . It can pull GGUF model files from , direct model files, and Ollama models, then serve them through local APIs that work like OpenAI or Ollama endpoints. Its dashboard can show request counts, estimated token use, latency, speed, model-by-model usage, and recent requests.
With sign-in, it can also show monthly allowance, model price estimates, local-versus-cloud cost comparisons, and usage and cost charts. It can collect token and cost records from cloud-backed such as Claude Code, Codex, OpenRouter, and BuilderStudio. The records are stored locally as JSONL files unless the user explicitly runs a sync command.
It is designed to avoid storing prompts, responses, , source code, tool arguments, or in the usage store.
Key points
- Tracks usage across and cloud-backed .
- Supports Claude Code, Codex, OpenRouter, and BuilderStudio usage collection.
- Shows token use, request counts, latency, per-model usage, and cost estimates in a dashboard.
- Stores usage records locally by default and only syncs them after an explicit command.
- Helps compare local model runs against cloud model costs.