portkey

Self-hosted LLM router with a managed safety net. OpenAI-compatible. BYOK. Single-workspace. Streaming. For more advanced routing choose hosted OrcaRouter

Build, Improve Performance, and Productionize your AI Application

Build reliable, secure, and production-ready AI apps easily.

Public Codex skill for claiming AI bounty on aelf tDVV via RewardClaimContract, supporting EOA Claim() and Portkey CA ClaimByPortkeyToCa().

Build reliable, secure, and production-ready AI apps easily.

AI API gateway / relay: 307 models behind one OpenAI-compatible key. image2.5 $0.0085/image, Seedance 2.0 Mini $0.01056/sec, LLM from $0.0228/M tokens. USD settlement, pay-as-you-go, $1 minimum top-up.

AI API gateway / relay: 307 models behind one OpenAI-compatible key. image2.5 $0.0085/image, Seedance 2.0 Mini $0.01056/sec, LLM from $0.0228/M tokens. USD settlement, pay-as-you-go, $1 minimum top-up.

MultiversX AI Agent Kit

MCP Testing Tool — Like Postman, but for the Model Context Protocol.

Guide to AI gateways. Integration examples for OpenRouter, Vercel AI SDK, LiteLLM, Portkey, Kong, and Cloudflare.

Portkey AI official helm charts for kubernetes deployment

OpenAPI specification for the Portkey API

Portkey Admin API control-plane MCP server with Prisma AIRS interoperability guidance

One-command local Kubernetes sandbox for macOS — kind + Argo CD + Kargo + Istio + wildcard TLS, with a built-in AI agentic gateway suite (LiteLLM, Portkey, MLflow, Tyk) and a real GitOps deploy loop.

Kubernetes Configs for Portkey Gateway deployment

Gateway-agnostic control plane for LLMs — an OpenAI-compatible governance proxy (auth, guardrails, budgets, routing, cost, observability) over a swappable engine: Bifrost / LiteLLM / Portkey / Direct. Own the control plane, swap the translator.

One source of truth for AI coding agent configuration and model routing. Generates native configs for OpenCode, omp, Claude Code, Codex, Cursor, Aider, and Goose with OpenRouter, Cloudflare, Vercel, LiteLLM, and Portkey routing.

Cut LLM output-token spend without losing information. Judged replays decide; it refuses when the saving drops content.

An adaptive, resilient, and autonomous Playwright agent for complex web automation.