api-cost

Restore prior Claude Code AND Codex sessions with zero LLM calls. Cross-tool session handoff, cache-expiry prevention, real cost dashboard. One plugin, both hosts.

跨平台 AI 编程助手用量监控桌面应用 | Cross-platform AI coding usage monitor: track Claude / Codex quota, tokens & costs. Data stays local.

VL-JEPA inspired pipeline — compress images/text locally via Ollama, send compact payloads to any LLM API. Cut token costs by ~80%.

Real-time observability for OpenClaw agents — token usage, API cost, context health, and smart alerts. Zero config. 100% local.

Find out what your Claude Code subscription is actually worth. Self-hosted dashboard for tracking token usage, API costs, quota utilization, and session analytics.

DeepSeek Harness（DSH）网页客户端插件：实时展示会话级 API token 用量与估算费用，支持缓存命中/未命中分桶、上下文占用，自动适配 DeepSeek 峰谷计价与调价｜DSH web plugin: real-time token usage & cost estimate

Compare AI API pricing across providers with real-time data

Free read-only AI/LLM API cost review for GitHub: find token, retry, cache, and model-call signals without uploading source.

Free unofficial GPT-6 Astra API pricing calculator — cache, 272K cliff, Batch/Flex/Fast

算账 (suanzhang) — DeepSeek Harness 计费插件：余额/今日消费/按步骤费用，交易终端风格，官方价自动同步。

Live DeepSeek API cost + peak/off-peak countdown banner for the DSH web UI. Node/npm. FinOps for your DeepSeek tokens.

An open-source, local-first framework for building multi-model, multi-agent RAG pipelines.

DeepSeek Harness 会话与单次回复费用显示插件

usage monitor for codex with reset history and forecasts

Universal LLM token counting and cost management. Track spending, set budgets, compare providers.

Claude Code Skill — estimate and compare LLM API costs across OpenAI, Anthropic, Google, DeepSeek, Mistral. Per-token pricing, batch/caching discounts, workload templates, cross-provider comparison.

DeepSeek Harness plugin pack: API cost meter, ChatGPT Plus/Pro subscription login + usage badge, and home-loss resilience - as a patch series

Local-first token usage and billing audit for OpenAI-compatible LLM APIs. Detect retries, prompt variance, context bloat, and verify Claude Code, Codex, CC Switch, and Cherry Studio setups.

Passive cost memory for AI Assisted Coding— detects paid services, tracks spend, injects budget context into your AI coding sessions.