@narumitw/pi-usage
Pi extension that shows current-account usage and DeepSeek API balance for supported providers.
$ pi install npm:@narumitw/pi-usageExtensions, skills, prompt templates, and themes published to npm. Install with pi install npm:<package>. See the package docs for details.
Pi extension that shows current-account usage and DeepSeek API balance for supported providers.
$ pi install npm:@narumitw/pi-usageImprove Pi prompt/KV cache hit rates with stable prompts, OpenAI-compatible cache keys, proxy compat warnings, and footer cache stats.
$ pi install npm:pi-cache-optimizerPi extension for web search, URL content extraction, and image search (Tavily, Kimi, DeepSeek, Mimo, Z.AI, DashScope, Unsplash, and more)
$ pi install npm:@amaster.ai/pi-web-accessPi extension for monitoring DeepSeek API balance
$ pi install npm:@alexanderfortin/pi-deepseek-usageClinePass provider for pi — access GLM-5.2, Kimi K2.7, DeepSeek V4 and more open-weight coding models through Cline's $9.99/mo subscription
$ pi install npm:pi-clinepass-providerWeb search for Pi using DeepSeek's server side search. Only works with DeepSeek models.
$ pi install npm:pi-deepseek-searchDeepSeek prefix cache optimization for pi — date/CWD freeze, hit-rate telemetry, cache-friendly compaction, and TUI overlays
$ pi install npm:@rohaquinlop/pi-deepseek-cachePi extension for monitoring Z.ai, DeepSeek, OpenAI Codex, and Opencode Go usage
$ pi install npm:@beyona/pi-zai-usageGive DeepSeek (text-only) models vision in Claude Code, Codex, and Agent Plugins clients: describe images via any OpenAI-compatible vision endpoint.
$ pi install npm:deepseek-vl-supportQuota, balance, and spend indicators for current Pi providers
$ pi install npm:@hk_net/pi-usage-barspi-seek is an extension for Pi. It connects Pi to the DeepSeek V4 Flash and V4 Pro models. It uses the DeepSeek Responses API and the DeepSeek beta API.
$ pi install npm:@juvio15/pi-seekWindsurf/Cognition models in Pi — Claude, GPT, Gemini, Kimi, DeepSeek, SWE via your Windsurf subscription
$ pi install npm:pi-windsurfValidate-then-repair extension for pi — fixes common LLM tool-call mistakes (null fields, stringified arrays, wrong field names, anchor bleed) before tools execute
$ pi install npm:pi-tool-repairDeepSeek-backed web search tool for pi sessions
$ pi install npm:pi-deepseek-web-searchOfficial Pi Coding Agent extension for AgentRouter (agentrouter.org). Connects GPT-5.6 Sol, Claude Opus 5, DeepSeek V4 Flash, and GLM 5.3 with live USD pricing, batch quota health probe, prompt caching, and WAF protection.
$ pi install npm:@madgagarin/pi-agentrouterDeepSeek model pricing extension for pi coding agent — shows peak/off-peak pricing status in the status bar
$ pi install npm:pi-deepseek-pricingExtension for Pi (a minimal agent harness) to view usage and quota for AI providers: Z.ai / GLM Coding Plan, Kimi Coding Plan, DeepSeek, and OpenRouter. Not affiliated with any provider; trademarks belong to their owners.
$ pi install npm:@imdlan/pi-usageFeishu/Lark bridge for coding agents — chat with Pi or DeepSeek Harness from Feishu or Lark
$ pi install npm:ax-feishu-bridgePi Agent 的用量与计费状态栏 — 实时费用、token、缓存命中率与 GLM/DeepSeek 余额 | Usage & billing HUD for Pi Agent — real-time cost, tokens, cache & GLM/DeepSeek balance
$ pi install npm:@foolsecret/pi-usagerpi 的 Token 用量与配额监控扩展 —— Footer 实时显示 5h/周 配额剩余、缓存命中率、输出速率,跑到一半不再被限流中断;JSONL 记录 + /stats 日/小时/周/月多维查询
$ pi install npm:@liziy/token-statsDeepSeek Harness adapter for Pi: V4 Pro + V4 Flash on the anchored-standard surface (first-turn two-tool schema, then Pi tools). Measured on DeepSWE.
$ pi install npm:pi-dsh-minimalPi extension: detects and interrupts infinite thinking-block and tool-call loops in real time before they exhaust your context window.
$ pi install npm:pi-loop-policeRich custom status bar for pi with token usage, cost, DeepSeek balance, context window, and timing.
$ pi install npm:@fyeeme/pi-statuslinePi extension that shows your DeepSeek account balance in the status bar
$ pi install npm:pi-deepseek-balance-statusAgentRouter provider for pi — routes to GPT-6 Astra, GPT-5.6 Sol, Claude Opus 4.8, Claude Opus 5, DeepSeek V4 Flash, and GLM 5.3
$ pi install npm:@bismawy/pi-agentrouterPi extension showing DeepSeek peak hour status in the status bar
$ pi install npm:pi-deepseek-peakProvider quota monitoring and local skill activation statistics for Pi and pi-web
$ pi install npm:@wayner6/pi-usagePi Agent extension that maximizes prompt-cache hit rate and reduces token cost
$ pi install npm:pi-cache-guardianHarness techniques for DeepSeek V4 Pro on the pi coding agent (cache stability, storm-breaker, hashline editing, plan mode, rewind).
$ pi install npm:pi-deepseek-optimizedDeepSeek API account balance in the pi footer — CNY-correct currency selection, burn rate, low-balance alerts, /deepseek-balance report. Unofficial, not affiliated with DeepSeek.
$ pi install npm:pi-deepseek-balanceDeepSeek vision image offload for pi: Files API file_id references on the official gateway (deepseek-v4-flash-vision-exp), offload trimming on third-party gateways — kills the 50 MB 413 ceiling.
$ pi install npm:pi-imagefilesGive text-only pi models vision — a native vision tool with a bundled vision script and a multi-backend model chain (auto-fallback, timeout, retry). Configure models via .env, JSON, or a custom script.
$ pi install npm:pi-multivisionComplete model providers for pi — Alibaba Model Studio (Plan subscription + Cloud pay-per-token, Anthropic + OpenAI + Responses API shapes, native thinking levels. Qwen 3.8/3.7/3.6, DeepSeek V4, Kimi K2.6/K2.7, GLM-5.1/5.2, MiniMax M2.5) and DeepSeek offi
$ pi install npm:pi-models-accessRender pi's footer from a configurable string template; time and response throughput are reported in a notification configured the same way; multi-provider account balance with session deltas mirrors pi-tidy-footer, plus Codex/Claude OAuth quota-window br
$ pi install npm:pi-footer-templateDeepSeek-native optimizations for Pi: cache-first prefix stabilization, tool-call repair, and cost control.
$ pi install npm:pi-reasonixThe complete Alibaba provider for pi — Plan subscription + Cloud pay-per-token, International + China endpoints, Anthropic + OpenAI shapes, native thinking levels. Qwen 3.8 Max, Qwen 3.7/3.6, DeepSeek V4 Pro, Kimi K3, GLM-5, MiniMax M3.
$ pi install npm:pi-alibaba-modelsPi extension showing DeepSeek API peak pricing hours (Beijing-time windows displayed in your local timezone)
$ pi install npm:deepseek-peak-pricing-hoursPi extension: OpenCode Go / Zen provider — developer-role compat filter, multi-key rotation + quota awareness + session affinity, and usage/cost tracking
$ pi install npm:pi-opencodegoMinimal Pi extension for provider-native web search on OpenAI Codex, Kimi For Coding, and DeepSeek.
$ pi install npm:@sakiko233/pi-native-searchTime-of-day-aware DeepSeek cost accounting for pi: re-prices every DeepSeek assistant message with the official peak/off-peak rates in effect at the message's own UTC timestamp, so session totals, the footer, the statusline cost segment, and exports match
$ pi install npm:pi-deepseek-pricing-by-timePi extension for Volcengine Coding Plan, registering Volcengine as a custom OpenAI-compatible provider for domestic coding models.
$ pi install npm:pi-provider-volcengine-codingplanShow OpenAI Codex, GitHub Copilot, Z.ai GLM Coding Plan (global and China), and DeepSeek balance usage in the pi coding agent.
$ pi install npm:@tian.zuo/pi-usagepi (AI coding agent CLI) extension for mainland-China users: curated access to free-first model providers including OpenCode Zen, SenseNova, SiliconFlow, ModelScope, NVIDIA NIM, AMD Radeon Cloud, Cloudflare, and Agnes AI. Providers self-register apiKey: "
$ pi install npm:pi-cn-free-model-providersDeepSeek Harness minimal mode for Pi
$ pi install npm:pi-deepseek-minimal-modeNative web search for Prime Agent using DeepSeek's server side search. Kernel-callable skill (await deepseek_search), no extension tool. Install with: prime-agent package install npm:prime-deepseek-search
$ pi install npm:prime-deepseek-searchLocal MLX vision for text-only models on Apple Silicon Macs: a describe_image tool backed by LiquidAI LFM2.5-VL-3B-MLX-8bit, so non-vision models (DeepSeek, etc.) can see images.
$ pi install npm:pi-mlx-visionTask-aware reasoning-mode routing for DeepSeek V4 Flash — Flash-only gate, first-turn anchoring, near-field guidance. Ported from dsh-routing-suite mode-boost (official-API measured).
$ pi install npm:pi-deepseek-routeRunInfra.ai model provider extension for pi — DeepSeek V4 Flash/Pro, Nemotron 3.5 Lightning, Qwen3.8, GLM 5.3 Flash
$ pi install npm:pi-runinfra