{"slug": "show-hn-phlox-gw-open-source-llm-gateway-without-the-enterprise-paywall", "title": "Show HN: Phlox-GW – Open-source LLM gateway without the enterprise paywall", "summary": "Phlox-GW, an open-source LLM gateway, was released on Hacker News, offering features like SSO, cost accounting, budget enforcement, rate limits, smart routing, guardrails, and observability without an enterprise paywall.", "body_md": "Full-featured by default\n## Everything between your users and your models\n\nPublish model routes, control who can use them, attach prices, enforce budgets and rate limits,\nand report usage for chargeback — from one admin console.\n\n🔐\n\n### Entra ID & OIDC SSO\n\nBrowser SSO with any OIDC identity provider. Auto-provisioning on first login, department claim mapping for chargeback, and group-based admin role mapping. Local accounts work too.\n\n💰\n\n### Cost accounting & chargeback\n\nPer-user and per-department monthly chargeback from an append-only usage ledger, with per-model USD pricing per million tokens. CSV download for finance, JSON API for automation.\n\n⛔\n\n### Budgets with real enforcement\n\nMonthly budgets per user, department, and API key with hard-limit enforcement — not just alerts. Burn-down views show spend, remaining budget, and projected month-end run rate.\n\n⏱️\n\n### Rate limits at every scope\n\nRPM and TPM controls by user, department, provider, model, and API key. Blunt one noisy script without throttling the whole org.\n\n🔀\n\n### Smart routing & failover\n\nStable route aliases like `chat/default`\n\n, ordered fallbacks, retries, per-attempt timeouts, health-aware routing, and weighted traffic splits — swap providers without touching clients.\n\n🛡️\n\n### Built-in guardrails\n\nDetect emails, phone numbers, SSNs, credit cards, API keys, and custom regex patterns. Redact or block on input and output, with an admin preview tool for testing policies before saving.\n\n🔑\n\n### User-owned API keys\n\nSelf-service key minting, rotation, and expiration. Admin key inventory with per-key model allowlists, budgets, and rate limits.\n\n📈\n\n### Observability included\n\nOperations dashboards for cost, tokens, requests, errors, and latency, plus Prometheus metrics and OpenTelemetry traces for your existing monitoring stack.\n\n📜\n\n### Immutable audit log\n\nEvery login, admin action, and API-key lifecycle event recorded with actor, target, details, and source IP.\n\n🕵️\n\n### Private by design\n\nRequest metadata search and CSV export without storing prompt text, response bodies, image bytes, tool contents, or secrets — by default.\n\n🧪\n\n### Admin playground\n\nSend test chat messages through any model route to validate providers and models end to end — no API key required.\n\n📦\n\n### Signed config export\n\nEd25519-signed, sanitized configuration export for review, backup, and environment promotion — secrets and credentials never leave the box.", "url": "https://wpnews.pro/news/show-hn-phlox-gw-open-source-llm-gateway-without-the-enterprise-paywall", "canonical_source": "https://robert-mcdermott.github.io/phlox-gw/", "published_at": "2026-07-13 20:16:14+00:00", "updated_at": "2026-07-13 20:35:26.527775+00:00", "lang": "en", "topics": ["ai-infrastructure", "ai-tools", "developer-tools"], "entities": ["Phlox-GW", "Entra ID", "OIDC", "Prometheus", "OpenTelemetry"], "alternates": {"html": "https://wpnews.pro/news/show-hn-phlox-gw-open-source-llm-gateway-without-the-enterprise-paywall", "markdown": "https://wpnews.pro/news/show-hn-phlox-gw-open-source-llm-gateway-without-the-enterprise-paywall.md", "text": "https://wpnews.pro/news/show-hn-phlox-gw-open-source-llm-gateway-without-the-enterprise-paywall.txt", "jsonld": "https://wpnews.pro/news/show-hn-phlox-gw-open-source-llm-gateway-without-the-enterprise-paywall.jsonld"}}