pi-sub2api
Pi extension for a sub2api gateway: dynamic model registration and a /usage command for balance and cost.
6.2k listings for pi · 0 reviewed by us
691 results · page 3 of 15
Pi extension for a sub2api gateway: dynamic model registration and a /usage command for balance and cost.
A pi extension that enables Anthropic Claude Fast mode for supported Claude Opus models by injecting speed=fast.
Pi extension for llama-server router - model discovery, auto-load, per-project config
Pi extension that registers Novita AI as an OpenAI-compatible model provider.
Pi coding agent provider for MiniMax AI with M3, Anthropic-compatible streaming, and native MiniMax tools
Auto-continue after Z.ai usage limit resets, with a live countdown and retry suppression.
Custom model providers for pi
Pi and Oh My Pi extension for managing custom providers through an interactive wizard.
Personal pi extension that improves OpenAI with fast mode, usage stats, and footer polish.
Pi extension package for toggling OpenAI Fast Mode priority inference
QwenCloud provider for pi — access Qwen3.8, DeepSeek V4, GLM-5.2, Wan image generation, and HappyHorse video generation through QwenCloud's OpenAI-compatible API
Pi extension that auto-registers sub2api/OpenAI-compatible providers and displays quota usage.
See your agent usage and cost directly in Pi — costs, languages, models, projects, and tools from session logs.
Unified tool-wrapping, argument repair, reasoning management, DeepSeek V4 guidance + Super Power Mode, defensive leak-cleaning, edit mismatch repair (read-notice stripping + trim-tolerant retry), and a Codex-style apply_patch diff tool for DeepSeek V4 and
Pi coding agent extension that uses your Claude Code credentials — no separate login needed.
Smart per-turn model router for Pi that optimizes your AI budget and usage limits by dynamically switching LLM tiers based on task complexity, budget, and phase awareness.
One-command installer that points Claude Code, Codex, opencode, or pi at the Weave Router. For pi it also ships the routing extension, loaded via pi.extensions.
Subscription usage/rate-limit command extension for pi-agent (Claude and OpenAI Codex plans).
Offer a plan-only Pi recovery flow for classified Anthropic compatibility errors.
Pi extension for Qoder AI — with OAuth authentication, COSY signatures and WAF bypass
Inline ghost-text autocomplete extension for the Pi coding agent (pi.dev). Cloud and local LLM providers, zero-flicker rendering, no popup interference.
CrofAI provider extension for pi - Access Kimi, GLM, Qwen, DeepSeek, MiniMax, and Gemma models through the CrofAI API
Pi extension for the Kiro API, maintained by Arvore
HyperCharm provider extension for pi - Access DeepSeek, GLM, Kimi, Qwen, MiniMax, Gemma, and GPT-OSS models through the Charm Hyper API
Pi provider extension for Volcengine Ark Coding API models.
Cursor Agent provider extension for pi
DeepSeek model pricing extension for pi coding agent — shows peak/off-peak pricing status in the status bar
Synthetic (synthetic.new) model provider for pi - Dynamic model fetching with reasoning, vision, and tools support
Patch Anthropic OAuth payloads and companion tools for Claude Code-style subscription use
Charm Hyper model provider extension for Pi.
Shared usage data core for pi extensions
CodeCompass cut 66%-82% of token usage on real coding work. And used to map your codebase and reduce the amount of code your agent reads and opens.
Pi extension that switches to a fallback model after provider failures such as 429 rate limits.
Minimal Codex/OpenAI native tools for Pi: Codex image_generation, view_image, apply_patch
Pi Coding Agent extension for 9router — connect to your 9router AI routing proxy instance
OAuth login provider extension for Google Antigravity models in the Pi Coding Agent
IO Intelligence provider extension for pi - Access DeepSeek, Kimi, GLM, Llama, Qwen, Mistral, and more through the IO Intelligence API
Automatic per-prompt model and thinking-level routing for pi
Validate-then-repair extension for pi — fixes common LLM tool-call mistakes (null fields, stringified arrays, wrong field names, anchor bleed) before tools execute
pi 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
Usage limit checker for pi coding agent — shows Codex, Anthropic, Copilot, OpenCode, and compatible subscription limits at startup
Merius provider extension for pi - Open models on Merius's own GPUs via an OpenAI-compatible API
Pi statusline extension — shows context usage, token speed, and provider quota in the footer.
Pi extension that routes model groups to concrete models. Balances intelligence, cost, and availability.
Custom pi footer: session name, model/effort, context, provider usage, git branch/PR/diff
Pi extension: wizard for managing custom providers in ~/.pi/agent/models.json.
Wafer Serverless provider extension for pi - Access Qwen3.5-397B-A17B, GLM-5.1, Kimi K2.6, and DeepSeek-V4 through the Wafer Serverless API
OpenCode provider for Pi Agent. Auto-discovers models from OpenCode registry and uses Pi's native OpenAI-compatible handler.