OpenTokenMini

OpenTokenMini is an open source tool that measures AI agent costs, links them to commits, and optimizes spending.

OpenTokenMini is an open source tool designed for monitoring and optimizing AI agent costs. It measures the cost of every agent call, links the expense directly to the commits it produced, and feeds this data back to the agent to reduce spending. The platform integrates with coding agents like Claude Code, Codex, OpenAI, Anthropic, and open models. It installs using your coding agent, explaining each step and asking for permission before activating features. It is built for developers and teams looking to track and control expenses generated by autonomous AI coding agents.

OpenTokenMini at a glance

Best for: Software engineer
Pricing: Free and open source
Released: October 2026
Category: AI coding tool
Website: opentokenmini.org

Key features

Measures every agent call cost
Links costs to produced code commits
Feeds spending data back to the agent
Integrates with OpenAI and Anthropic
Supports open models and Codex
Installs using your coding agent

Use it for

Monitor AI agent spending per task
Link AI expenses to specific code commits
Optimize agent spending to reduce costs

Companions

Tools that articles about OpenTokenMini recommend using with it, each with its job.

Context7 — Provides up-to-date documentation for AI agents and code editors.
Ollama — Run local models at zero marginal cost, with code kept on your machine.
OpenRouter — Access over 500 models and 80 providers through one unified API.
Daytona — Runs sessions in isolated sandboxes synced to git branches.
Composio — Equips AI agents with tools, managed user auth, and sandboxes across 1,500+ apps
Oh My OpenCode Slim — Lightweight multi-agent orchestration and background tasks.

Alternatives to OpenTokenMini

OpenCode — Works with 75+ model providers, local models, and existing subscriptions
Opaline — Track team-wide token costs and coding session analytics.
ccusage — Tracks token usage and costs locally across multiple coding agent CLIs.
OpenChamber — Run and review multi-model AI coding agents from desktop, browser, and mobile devices.
Wiyomi — Saves up to 70 percent on tokens while handling coding and research tasks.
Oh My OpenAgent — Executes complex coding and research tasks independently using a keyword.
TokenTracker — Monitor AI spending across 43 coding tools in one local, private dashboard.
Endlesstokens — Pay for a time window instead of per token, with no usage caps.
Ctxvitals — Measures exact token costs and security risks before agent launch.
OpenMonoAgent — Runs locally on your own hardware with no recurring subscription fees.
Tokscale — Track and compare token usage across multiple AI coding agents.
Kilo Code — Open-source agent with any model and no markup on inference

All OpenTokenMini alternatives