pi-codex-token
pi provider plugin: use gpt-5.5 on the OpenAI Codex backend via a personal access token (PAT), non-interactively.
6.2k listings for pi · 0 reviewed by us
691 results · page 5 of 15
pi provider plugin: use gpt-5.5 on the OpenAI Codex backend via a personal access token (PAT), non-interactively.
Google Antigravity OAuth extension for pi - access Gemini 3 and Claude 4.6 using Google credentials
StarRouter is a focused model-routing extension for Pi. It chooses the best available model and thinking level for each prompt using a deterministic heuristic prompt profiler, Artificial Analysis benchmark data, provider-scoped model pools, strict model i
Pi package that adds [CoreInfra AI Hub](https://hub.coreinfra.ai/) as a model provider.
Pi extension providing access to Cursor models via OAuth and a local OpenAI-compatible gRPC proxy
Two-tier model router for pi-agent — automatic execution/judgment routing with LLM Judge. Pairs a fast everyday model with a strong model for planning and review.
Pi extension: active-provider quota footer for OpenAI Codex and Kimi Coding.
Opencode Go provider extension for pi - Fast, efficient GLM, Kimi, and MiniMax models through the opencode.ai API
Live observability dashboard for pi coding agent sessions — tokens, cost, TPS, runtime, git stats, and context usage
Minimal Pi extension for OpenAI Fast mode.
Create reusable Pi provider aliases for separate logins.
pi provider extension for self-hosted NewAPI AI gateway — dynamic model discovery with cost calculation from ratio_config
Pi extension scaffolding for showing subscription and quota usage across AI providers.
Pi extension that syncs models from an OpenAI-compatible API and enriches them with pricing and capability metadata.
Roundrobin failover engine for the pi coding agent — virtual provider pooling multiple candidates with sticky failover and cooldown
Pi extension that restores the Antigravity (Gemini 3, Claude, GPT-OSS) OAuth provider.
Pi extension that shows session cost including subagent sessions, not just the main thread
UMANS provider extension for pi - Access Kimi K2.6, GLM 5.1, Qwen 3.6, and coding-optimized models through the UMANS API
OpenAI-compatible local API on top of pi.dev — LiteLLM-shape stateless protocol translator. Standalone CLI + pi-extension wrapper.
OpenAI Codex personal access token provider for pi
ACP bridge providing Claude Code, Codex, and Gemini CLI backends to pi-coding-agent, with the entwurf orchestration surface for cross-session delegation.
Pi extension for Kimi K2 Coding plan — OAuth-based provider with kimi-for-coding model
Pi extension for managing OpenAI-compatible custom providers with /models discovery and models.dev enrichment.
Pi provider extension for [Edgee](https://www.edgee.ai), the Agent Gateway that compresses, routes, and observes LLM requests.
Pi extension: interactive multi-dimensional drill-down of local token usage (time / project / model)
Pi extension that replaces pi's built-in LLM provider with an external agent CLI (Codex CLI or Claude CLI) for advisor consultation.
Pi extension for monitoring API key balance and subscription quota (DeepSeek, OpenCode Go, and more)
Kiro provider for the pi coding agent: AWS Builder ID / IAM Identity Center login and the CodeWhisperer streaming API, exposing the Kiro Claude model family.
Pi Agent extension for Scaleway's Generative APIs
Pi extension for Volcengine Coding Plan, registering Volcengine as a custom OpenAI-compatible provider for domestic coding models.
FriendliAI model provider for Pi with live model discovery
The complete Alibaba provider for pi — Plan subscription + Cloud pay-per-token, International + China endpoints, Anthropic + OpenAI shapes, native thinking levels. Qwen 3.7 Max, Qwen 3.7 Plus, Qwen 3.6 Max, Qwen 3.6 Plus, DeepSeek V4 Pro, Kimi K2.6, GLM-5
Pi extension that connects to a 9router AI routing proxy instance via its OpenAI-compatible API.
NVIDIA NIM provider for pi — full model catalog, per-family thinking handlers, and aggressive rate-limit retry
Ollama extension for pi-coding-agent. Unified local + cloud Ollama support with model management
Quota, balance, and spend indicators for current Pi providers
OpenAI fast mode toggle for pi - Enables priority service tier on supported GPT-5 models
Token and cost statistics extension for pi coding agent sessions.
Provider-agnostic speech-to-text dictation extension for the Pi TUI.
Model usage analytics extension for pi — track tokens & cost by model, project, and session
Zyloo provider extension for pi - Claude, GPT, Gemini, Grok, Kimi, GLM, DeepSeek, Qwen & MiniMax through the Zyloo OpenAI-compatible API
Token & cost ledger for Pi. Captures every assistant message to a per-day JSONL ledger and exposes a /usage command with by-model, by-period breakdowns (today/day/week/month/year/all) showing both real USD and API-equivalent USD.
Lean Poolside AI model provider for Pi with live model discovery
/usage command for pi – shows current provider's daily & weekly limits
Pi provider extension for Ollama Cloud (ollama.com), direct connection without a local server.
Pi provider extension for Volcengine Ark Agent Plan (api/plan/v3).
Pi extension for llama.cpp integration. Supports router, single and legacy models. Supports multiple servers.
Pi coding-agent extension: use frontier Anthropic, OpenAI, and Tinfoil models through nullsink — the anonymous, account-less, crypto-paid metered proxy.