{"id":"llm-ai-gateway","slug":"llm-ai-gateway","name":"Production LLM AI gateway","shortName":"Production LLM AI gateway","problemStatement":"Need a unified gateway in front of many model providers with fallbacks, virtual keys, budgets, guardrails, and request logs — not just a model marketplace.","whenNotTopPick":"You only need a multi-model catalog/router (OpenRouter), pure cheap request logs (Helicone), or are standardized on Palo Alto Prisma AIRS enterprise gateway.","categoryIds":["cat-observability","cat-inference-apis"],"depotPickProviderId":"portkey","depotPickRationale":"DX + reliability + capability for fallbacks/keys/guardrails. OpenRouter wins catalog breadth; Portkey wins production gateway controls.","runnersUpIds":["vercel-ai-gateway","cloudflare-ai-gateway","openrouter","helicone","cloudflare-workers-ai"],"weights":{"capabilityFit":0.25,"pricePerformance":0.18,"latencyReliability":0.15,"developerDx":0.15,"privacyPosture":0.1,"lockInRisk":0.07,"maturity":0.1},"methodologyNotes":"DX + reliability + capability for fallbacks/keys/guardrails. OpenRouter wins catalog breadth; Portkey wins production gateway controls.","tags":["llm"],"depth":{"whenNotToUse":{"text":"You only need a multi-model catalog/router (OpenRouter), pure cheap request logs (Helicone), or are standardized on Palo Alto Prisma AIRS enterprise gateway.","source":"editorial `whenNotTopPick` (data/jtbds.json)"},"whenNotToUseReason":null,"runnerUp":{"providerId":"vercel-ai-gateway","name":"Vercel AI Gateway","overallForJob":8.21,"pickOverallForJob":8.31,"beatsPickOn":["pricePerformance","developerDx"],"source":"first resolvable entry of the job's editorially ranked `runnersUpIds`; scores are stored job-weighted scores"},"runnerUpReason":null,"lockIn":{"pickLockInRisk":5,"runnerUpLockInRisk":5.8,"scale":"0–10 stored curated estimate; higher = more lock-in (worse)","pickExitSignals":["OpenAI-compatible API (provider tag `openai-compat`)"],"runnerUpExitSignals":[],"pickNotes":[{"text":"OSS self-host option","field":"strengths"}],"selfHostFallback":[{"id":"litellm-oss","name":"LiteLLM","license":"MIT outside enterprise/","sourceUrl":"https://github.com/BerriAI/litellm/blob/main/LICENSE"}],"migration":"The pick has lower stored lock-in risk than runner-up Vercel AI Gateway (5 vs 5.8). Pick exit signals: OpenAI-compatible API (provider tag `openai-compat`). Self-host fallback listed for this job: LiteLLM.","migrationReason":null,"derivedFrom":"stored lockInRisk scores, provider tags (oss, self-host, openai-compat, open-models), free rows that list this job, and verbatim provider notes. No migration guide was invented."}},"freshness":{"pick":{"score":{"asOf":"2026-09-14","ageDays":43,"stale":true,"staleAfterDays":30,"reason":null},"lastReviewed":{"asOf":"2026-09-14","ageDays":43,"stale":true,"staleAfterDays":30,"reason":null},"sourceCheck":{"checkedAt":"2026-10-27","sourceUrls":2,"sourcesReachable":2,"pricingRows":1,"pricingRowsReconfirmed":1,"note":"A source re-check confirms the page is reachable and, for pricing rows, that the stored amount and SKU name appear on it. It does not re-derive or change the score.","reason":null}}}}