{"id":"self-host-nim","slug":"self-host-nim","name":"Self-hosted optimized model serving","shortName":"Self-hosted optimized model serving","problemStatement":"Run optimized inference containers on your own NVIDIA GPUs across clouds.","whenNotTopPick":"Don't want to operate GPUs — use Fireworks/Together serverless.","categoryIds":["cat-inference-apis","cat-gpu-cloud"],"depotPickProviderId":"nvidia-nim","depotPickRationale":"Capability of CUDA stacks + privacy. Note: vllm-note is conceptual — prefer NIM or Baseten if no vLLM provider entry.","runnersUpIds":["baseten","fireworks","replicate"],"weights":{"capabilityFit":0.25,"pricePerformance":0.18,"latencyReliability":0.15,"developerDx":0.15,"privacyPosture":0.1,"lockInRisk":0.07,"maturity":0.1},"methodologyNotes":"Capability of CUDA stacks + privacy. Note: vllm-note is conceptual — prefer NIM or Baseten if no vLLM provider entry.","tags":["self"],"depth":{"whenNotToUse":{"text":"Don't want to operate GPUs — use Fireworks/Together serverless.","source":"editorial `whenNotTopPick` (data/jtbds.json)"},"whenNotToUseReason":null,"runnerUp":{"providerId":"baseten","name":"Baseten","overallForJob":7.99,"pickOverallForJob":7.66,"beatsPickOn":["pricePerformance","latencyReliability","developerDx","lockInRisk"],"source":"first resolvable entry of the job's editorially ranked `runnersUpIds`; scores are stored job-weighted scores"},"runnerUpReason":null,"lockIn":{"pickLockInRisk":6,"runnerUpLockInRisk":4.5,"scale":"0–10 stored curated estimate; higher = more lock-in (worse)","pickExitSignals":["self-hostable (provider tag `self-host`)"],"runnerUpExitSignals":[],"pickNotes":[{"text":"Portable across GPU clouds","field":"strengths"},{"text":"Choose when you self-host inference on NVIDIA GPUs and want blessed containers.","field":"scores.notes"}],"selfHostFallback":[],"migration":"Runner-up Baseten has lower stored lock-in risk (4.5 vs 6, 0–10, higher = more lock-in). Pick exit signals: self-hostable (provider tag `self-host`).","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":"2026-10-19","ageDays":8,"stale":false,"staleAfterDays":30,"reason":null},"lastReviewed":{"asOf":"2026-10-19","ageDays":8,"stale":false,"staleAfterDays":30,"reason":null},"sourceCheck":{"checkedAt":"2026-10-27","sourceUrls":3,"sourcesReachable":3,"pricingRows":0,"pricingRowsReconfirmed":0,"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}}}}