{"jtbd":{"id":"air-gapped-model-serve","slug":"air-gapped-model-serve","name":"Air-gapped / VPC model serving","shortName":"Air-gapped serve","problemStatement":"Serve optimized models inside VPC/air-gapped networks with no mandatory data egress to public LLM APIs."},"pick":{"id":"nvidia-nim","slug":"nvidia-nim","name":"NVIDIA NIM / NGC","tagline":"Choose when you self-host inference on NVIDIA GPUs and want blessed containers. For serverless tokens use…","website":"https://www.nvidia.com/en-us/ai/","overall":7.83,"scoreBand":{"low":7.2,"mid":7.8,"high":8.4,"halfWidth":0.6,"basis":"editorial_prior","display":"7.2–8.4 (editorial prior)"},"scoreLayers":{"editorialPrior":7.83,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-10-19","pricingNotes":"As of 2026-10-24 (nvidia.com/en-us/ai-data-science/products/nim-microservices, fetched 2026-10-24; NVIDIA publishes no NIM price page, and this product page states no price figures, so production licence price stays null — 'Contact Sales'): hosted prototyping 'Start Prototyping for Free' ('Access for development and testing as part of the NVIDIA Developer Program'); self-hosting 'Start with free access for development and testing, and move to an NVIDIA AI Enterprise license for production.' Deploy as 'hosted APIs for NIM accelerated by NVIDIA DGX™ Cloud' or 'self-hosting models on your preferred infrastructure'.","scores":{"capabilityFit":8.6,"pricePerformance":7,"latencyReliability":8,"developerDx":6.8,"privacyPosture":8.5,"lockInRisk":6,"maturity":9,"overall":7.83,"kind":"curated_estimate","confidence":"medium","asOf":"2026-10-19"}},"runnersUp":[{"id":"huggingface-inference","slug":"huggingface-inference","name":"Hugging Face Inference","tagline":"Perfect for Hub-native workflows and custom models. For hard production latency, graduate to…","website":"https://endpoints.huggingface.co","overall":7.93,"scoreBand":{"low":7.3,"mid":7.9,"high":8.5,"halfWidth":0.6,"basis":"editorial_prior","display":"7.3–8.5 (editorial prior)"},"scoreLayers":{"editorialPrior":7.93,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","pricingNotes":"Inference Providers (pay-as-you-go access to partner inference providers plus Hugging Face's own hf-inference provider) + dedicated Inference Endpoints ('Pay for what you use, per minute' per https://endpoints.huggingface.co, fetched 2026-10-25; instance rates are the price rows: single-GPU x1 rows per GPU-hour, multi-GPU x2/x4/x8 rows per instance-hour (usd_per_instance_hour since v0.12.138, re-checked 2026-10-27 on https://huggingface.co/docs/inference-endpoints/pricing), never divided per GPU). The 'Serverless Inference API' name is retired: https://huggingface.co/docs/inference-providers/pricing (fetched 2026-10-25) says hf-inference 'used to be called “Inference API (serverless)” prior to Inference Providers' and 'just pay for what you use, with no markup from Hugging Face.' Monthly credits: 'Free Users None - yes (credits purchase required)'; PRO users and Team/Enterprise organizations get included monthly credits. Hub-centric. No price changed here; any price change goes through the reviewed --catalog step.","scores":{"capabilityFit":8.4,"pricePerformance":7.2,"latencyReliability":7.4,"developerDx":8.6,"privacyPosture":7.8,"lockInRisk":3.5,"maturity":9.2,"overall":7.93,"kind":"curated_estimate","confidence":"high","asOf":"2026-09-14"}},{"id":"amazon-bedrock","slug":"amazon-bedrock","name":"Amazon Bedrock","tagline":"Enterprise multi-model switchboard. Great when AWS is mandatory; mediocre when you just want the best Claude…","website":"https://aws.amazon.com/bedrock/","overall":8.04,"scoreBand":{"low":7.4,"mid":8,"high":8.6,"halfWidth":0.6,"basis":"editorial_prior","display":"7.4–8.6 (editorial prior)"},"scoreLayers":{"editorialPrior":8.04,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","pricingNotes":"Pay-per-token for Claude, Llama, Amazon, Cohere, etc.; Provisioned Throughput for steady load. AWS marketplace billing.","scores":{"capabilityFit":8.8,"pricePerformance":6,"latencyReliability":9.2,"developerDx":6.8,"privacyPosture":9,"lockInRisk":7,"maturity":9.6,"overall":8.04,"kind":"curated_estimate","confidence":"high","asOf":"2026-09-14"}},{"id":"azure-openai","slug":"azure-openai","name":"Azure OpenAI","tagline":"Pick when IT already standardized on Azure and needs VNET/private endpoints. Otherwise go direct OpenAI and…","website":"https://azure.microsoft.com/products/ai-services/openai-service","overall":7.9,"scoreBand":{"low":7.3,"mid":7.9,"high":8.5,"halfWidth":0.6,"basis":"editorial_prior","display":"7.3–8.5 (editorial prior)"},"scoreLayers":{"editorialPrior":7.9,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","pricingNotes":"OpenAI models via Azure with regional deployment; enterprise agreements, PTUs, and Microsoft billing. Often premium vs direct OpenAI.","scores":{"capabilityFit":9,"pricePerformance":5.5,"latencyReliability":9,"developerDx":7,"privacyPosture":8.8,"lockInRisk":7.8,"maturity":9.5,"overall":7.9,"kind":"curated_estimate","confidence":"high","asOf":"2026-09-14"}}],"scoreBand":{"low":7.2,"mid":7.8,"high":8.4,"halfWidth":0.6,"basis":"editorial_prior","display":"7.2–8.4 (editorial prior)"},"scoreLayers":{"editorialPrior":7.83,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"whyPickOverHigherScore":{"pickId":"nvidia-nim","pickName":"NVIDIA NIM / NGC","pickScore":7.83,"highestScoredCandidateId":"amazon-bedrock","highestScoredCandidateName":"Amazon Bedrock","highestScore":8.04,"pickHasLowerCompositeScore":true,"delta":-0.21,"pickLeadsOnDimensions":["pricePerformance (7 vs 6)","lower lockInRisk (6 vs 7)"],"explanation":"NVIDIA NIM / NGC (7.83) is the editorial pick for Air-gapped / VPC model serving over higher-composite Amazon Bedrock (8.04) because composite scores are provider-wide priors while NVIDIA NIM / NGC wins on pricePerformance (7 vs 6), lower lockInRisk (6 vs 7): Remove invalid runner if any. NIM for optimized self-host. Confidence: medium on packaging/licensing."},"cheapest":{"providerId":"amazon-bedrock","providerName":"Amazon Bedrock","skuId":"amazon-bedrock-gemma-3-4b-in","item":"Gemma 3 4B","plan":"Gemma 3 4B — Standard on-demand","unit":"usd_per_million_input_tokens","amountUsd":0.04,"isFloorPrice":true,"floorWarning":"Provider-wide floor SKU; may not be the flagship model scored for this JTBD.","skuCountInUnit":26,"isDepotPick":false,"sourceUrl":"https://aws.amazon.com/bedrock/pricing/","asOf":"2026-10-03","verifiedAsOf":"2026-10-27"},"recommendedWorkloadQuote":null,"representativeQuote":null,"estimatedTaskCost":null,"freeAlternatives":[],"referenceDocs":[],"falsification":{"jtbdId":"air-gapped-model-serve","jtbdName":"Air-gapped / VPC model serving","currentPickId":"nvidia-nim","currentPickScore":7.83,"challengerId":"huggingface-inference","challengerScore":7.93,"currentScoreGap":0.1,"minVerifiedOutcomes":10,"requiredOutcomeMargin":0.25,"requiredSuccessRateDelta":0.15,"maxPickPriceIncreasePct":25,"whatWouldChangePick":["Hugging Face Inference (huggingface-inference) outperforms NVIDIA NIM / NGC (nvidia-nim) by >= 0.25 outcome points (or >= 15% worked-rate delta) across >= 10 Countersign-verified production outcomes.","A verified price increase > 25% on NVIDIA NIM / NGC's representative SKU for air-gapped-model-serve without a corresponding capability gain.","Live caller rail exhaustion (?exhausted=nvidia-nim) or sustained >= 30% degraded/failed rate in verified production outcomes."],"frozenHoldoutPolicy":{"holdoutSplit":"20% frozen benchmark holdout tasks + 80% live production outcome receipts","requireCountersignReceipt":true,"requiredEvidenceTiers":["outcome_verified","reference_checked"],"minDistinctContributors":2,"antiGamingRule":"Unverified self-reports and seed/editorial rows never mutate picks or scores."},"triggers":[{"kind":"verified_outcomes_outperformance","challengerId":"huggingface-inference","minVerifiedOutcomes":10,"requiredOutcomeMargin":0.25,"requiredWorkedRateDelta":0.15},{"kind":"verified_price_increase","providerId":"nvidia-nim","maxPriceIncreasePct":25},{"kind":"live_rail_exhaustion_or_degradation","providerId":"nvidia-nim","immediateOverrideUrl":"/api/decide?jtbd=air-gapped-model-serve&exhausted=nvidia-nim"}],"submissionSpec":{"falsifyEndpoint":"/api/falsify?jtbd=air-gapped-model-serve","outcomesEndpoint":"POST /api/feedback","correctionsEndpoint":"POST /api/corrections","payloadTemplate":{"agentIdentity":"agent:<your-agent-id>","jtbdId":"air-gapped-model-serve","providerId":"huggingface-inference","outcome":"worked","detail":"Comparative production evaluation on air-gapped-model-serve (n>=10 tasks) with Countersign receipt.","confidence":"high","receipt":{"countersign":{"claim_id":"cs-00000000","status":"verified","evidence_tier":"outcome_verified","counts_as_verified":true}}}}},"whatWouldChangePick":["Hugging Face Inference (huggingface-inference) outperforms NVIDIA NIM / NGC (nvidia-nim) by >= 0.25 outcome points (or >= 15% worked-rate delta) across >= 10 Countersign-verified production outcomes.","A verified price increase > 25% on NVIDIA NIM / NGC's representative SKU for air-gapped-model-serve without a corresponding capability gain.","Live caller rail exhaustion (?exhausted=nvidia-nim) or sustained >= 30% degraded/failed rate in verified production outcomes."],"routePlan":{"jtbdId":"air-gapped-model-serve","primary":{"providerId":"nvidia-nim","name":"NVIDIA NIM / NGC","overall":7.83,"scoreBand":{"low":7.2,"mid":7.8,"high":8.4,"halfWidth":0.6,"basis":"editorial_prior","display":"7.2–8.4 (editorial prior)"},"scoreLayers":{"editorialPrior":7.83,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-10-19","role":"primary","reason":"Editorial Depot Pick for Air-gapped / VPC model serving; healthy/eligible under caller constraints."},"fallback":[{"providerId":"huggingface-inference","name":"Hugging Face Inference","overall":7.93,"scoreBand":{"low":7.3,"mid":7.9,"high":8.5,"halfWidth":0.6,"basis":"editorial_prior","display":"7.3–8.5 (editorial prior)"},"scoreLayers":{"editorialPrior":7.93,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","role":"fallback","reason":"Ranked fallback route for Air-gapped / VPC model serving."},{"providerId":"amazon-bedrock","name":"Amazon Bedrock","overall":8.04,"scoreBand":{"low":7.4,"mid":8,"high":8.6,"halfWidth":0.6,"basis":"editorial_prior","display":"7.4–8.6 (editorial prior)"},"scoreLayers":{"editorialPrior":8.04,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","role":"fallback","reason":"Ranked fallback route for Air-gapped / VPC model serving."},{"providerId":"azure-openai","name":"Azure OpenAI","overall":7.9,"scoreBand":{"low":7.3,"mid":7.9,"high":8.5,"halfWidth":0.6,"basis":"editorial_prior","display":"7.3–8.5 (editorial prior)"},"scoreLayers":{"editorialPrior":7.9,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","role":"fallback","reason":"Ranked fallback route for Air-gapped / VPC model serving."}],"disqualified":[],"expectedRegret":{"scoreDeltaVsUnconstrainedPick":0,"unconstrainedPickId":"nvidia-nim","activePrimaryId":"nvidia-nim","summary":"0.00 score regret: unconstrained editorial pick satisfies all caller constraints."},"evidenceAgeDays":{"editorialScoreAgeDays":8,"pricingVerifiedAgeDays":0,"editorialPriorAsOf":"2026-10-19","pricingLastVerifiedAt":"2026-10-27"},"confidenceBand":{"low":7.2,"mid":7.8,"high":8.4,"halfWidth":0.6,"basis":"editorial_prior","display":"7.2–8.4 (editorial prior)"},"constraintsApplied":false,"constraintBundle":{"task":null,"jtbd":"air-gapped-model-serve","quotaExhausted":[],"degraded":[],"healthy":[],"budgetUsd":null,"maxLatencyMs":null,"region":null,"privacy":null,"exit":[],"existing":[]}},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-10-19","tie":true,"scoreGap":-0.1,"decidingFactor":"privacyPosture (8.5 vs 7.8)","tieNote":"Scores are within 0.10 on a curated_estimate 0-10 scale (7.83 vs 7.93); treat as a statistical tie and decide on decidingFactor or whenNotTopPick.","rationale":"Remove invalid runner if any. NIM for optimized self-host. Confidence: medium on packaging/licensing.","whenNotTopPick":"Private Bedrock/Azure endpoints suffice without NIM packaging, or HF Inference Endpoints already in VPC.","skipTopPick":false,"skipReason":null,"matchedConstraints":[],"pricingSummary":"As of 2026-10-24 (nvidia.com/en-us/ai-data-science/products/nim-microservices, fetched 2026-10-24; NVIDIA publishes no NIM price page, and this product page states no price figures, so production licence price stays null — 'Contact Sales'): hosted prototyping 'Start Prototyping f…","cite":"Depot Pick for air-gapped-model-serve: nvidia-nim (asOf 2026-10-19). See GET /api/jtbds/air-gapped-model-serve + GET /api/methodology.","nextActions":[{"step":1,"title":"Inspect full JTBD + embeds","href":"/api/jtbds/air-gapped-model-serve?embed=providers","why":"Confirm pick, runners-up, and methodology notes."},{"step":2,"title":"Quote sourced SKUs","href":"/api/quote?jtbd=air-gapped-model-serve","why":"Depot Pick SKUs plus the cheapest sourced SKU whose unit matches this job. Does not change the pick. Does not blend input and output or borrow a chat rate for a non-chat job."},{"step":3,"title":"Open provider detail","href":"/api/providers/nvidia-nim","why":"Scores, pricingNotes, strengths/weaknesses, communitySignals (claims only)."},{"step":4,"title":"Cite methodology","href":"/api/methodology","why":"Required when publishing a Depot Pick citation."},{"step":5,"title":"Grab badge SVG","href":"/api/badge?type=depot-pick&jtbd=air-gapped-model-serve","why":"Embed in README / agent passport."},{"step":6,"title":"Post production insight","method":"POST","href":"/api/insights","why":"Unverified until curated; never auto-mutates official scores."}],"honesty":["Do not invent scores or benches.","Insights are claims until curated/reviewed; they never silently mutate official scores.","lockInRisk higher = more lock-in (worse).","normalizedUsdPerMillionTokens is set only for a single sourced token row. Otherwise null, with a machine-readable reason. Do not coerce GPU, minute, or per-1k search units.","Runners-up are not Depot Picks.","Depot overall is editorial_weighted, not Arena Elo and not an Artificial Analysis index."],"asOf":"2026-10-19","depth":{"whenNotToUse":{"text":"Private Bedrock/Azure endpoints suffice without NIM packaging, or HF Inference Endpoints already in VPC.","source":"editorial `whenNotTopPick` (data/jtbds.json)"},"whenNotToUseReason":null,"runnerUp":{"providerId":"huggingface-inference","name":"Hugging Face Inference","overallForJob":7.93,"pickOverallForJob":7.83,"beatsPickOn":["pricePerformance","developerDx","lockInRisk","maturity"],"source":"first resolvable entry of the job's editorially ranked `runnersUpIds`; scores are stored job-weighted scores"},"runnerUpReason":null,"lockIn":{"pickLockInRisk":6,"runnerUpLockInRisk":3.5,"scale":"0–10 stored curated estimate; higher = more lock-in (worse)","pickExitSignals":["self-hostable (provider tag `self-host`)"],"runnerUpExitSignals":["serves open-weight models (provider tag `open-models`)"],"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 Hugging Face Inference has lower stored lock-in risk (3.5 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."}},"citation":{"text":"Agent Provider Depot (v0.12.149), Depot Pick for air-gapped-model-serve: nvidia-nim, scores as of 2026-10-19, retrieved 2026-10-27. https://getagentdepot.com/jtbds/air-gapped-model-serve","markdown":"[Agent Provider Depot](https://getagentdepot.com/jtbds/air-gapped-model-serve) (v0.12.149) — Depot Pick for `air-gapped-model-serve`: **nvidia-nim** (scores as of 2026-10-19, retrieved 2026-10-27)","fields":{"publisher":"Agent Provider Depot","version":"0.12.149","role":"depot_pick","jtbdId":"air-gapped-model-serve","providerId":"nvidia-nim","scoreAsOf":"2026-10-19","retrievedOn":"2026-10-27","page":"https://getagentdepot.com/jtbds/air-gapped-model-serve","api":"https://getagentdepot.com/api/decide?jtbd=air-gapped-model-serve"},"howToCite":"Cite Depot as an editorial, dated recommendation, not a benchmark: name the job, the Depot Pick (or runner-up), the score asOf date and the day you retrieved it, and link the job page. Format: “Agent Provider Depot (v{version}), Depot Pick for {jobId}: {providerId}, scores as of {scoreAsOf}, retrieved {retrievedOn}. {baseUrl}/jtbds/{jobId}”. Quote prices only with their own sourceUrl and asOf. If the pick's score is stale (freshness.pick.score.stale), say so."},"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}},"scoreAsOf":"2026-10-19","editorialPriorAsOf":"2026-10-19","pricingLastVerifiedAt":"2026-10-27","pickLastReviewed":"2026-10-19","runnersUpScoreAsOf":["2026-09-14","2026-09-14","2026-09-14"],"contractAsOf":"2026-10-03","pricingShape":"prose_notes_only","normalizedUsdPerMillionTokens":null,"normalizationStatus":"unavailable","normalizationReason":"no_sourced_price"},"pricingContract":{"normalizedUsdPerMillionTokens":null,"normalizationStatus":"unavailable","normalizationReason":"no_sourced_price","shape":"prose_notes_only","filterable":false,"priceSortEligible":false,"priceSortKeyUsdPerMillionInputTokens":null,"rows":[],"notesExcerpt":"As of 2026-10-24 (nvidia.com/en-us/ai-data-science/products/nim-microservices, fetched 2026-10-24; NVIDIA publishes no NIM price page, and this product page states no price figures, so production licence price stays null — 'Contact Sales'): hosted prototyping 'Start Prototyping f…","notesCheck":{"status":"no_known_contradiction","pairs":[],"review":null,"note":null},"lastReviewed":"2026-10-19","scoreAsOf":"2026-10-19","website":"https://www.nvidia.com/en-us/ai/","doNotParse":"Do not parse pricingNotes. Use rows only. normalizedUsdPerMillionTokens is a single number only when this provider has exactly one sourced token row. Input/output, context tiers, and non-token units stay null at this level.","gap":"No sourced price row for this provider. pricingNotes stay prose. See research/gaps.md."},"links":{"jtbd":"/jtbds/air-gapped-model-serve","jtbdApi":"/api/jtbds/air-gapped-model-serve","leaderboard":"/api/leaderboards?jtbd=air-gapped-model-serve","methodology":"/api/methodology","badge":"/api/badge?type=depot-pick&jtbd=air-gapped-model-serve","decide":"/api/decide?jtbd=air-gapped-model-serve","humanPage":"/jtbds/air-gapped-model-serve","alternatives":"/api/alternatives?provider=nvidia-nim","canonical":"/api/canonical","quote":"/api/quote?jtbd=air-gapped-model-serve","falsify":"/api/falsify?jtbd=air-gapped-model-serve"},"constraintBundle":{"task":null,"jtbd":"air-gapped-model-serve","quotaExhausted":[],"degraded":[],"healthy":[],"budgetUsd":null,"maxLatencyMs":null,"region":null,"privacy":null,"exit":[],"existing":[]},"stackContext":{"host":null,"framework":null,"repo":null,"lang":null,"existing":[],"volume":null,"sender":null,"detectedFromTask":[]},"keep":null,"contextAdvice":null,"communityFeedback":{"pickOnThisJob":{"failed":0,"degraded":0,"worked":0,"insights":0,"withVerifiedReceipt":0,"failureModes":{},"latestAt":null,"note":"Agent-reported claims (unverified unless a receipt is verified by Depot's re-check). They never change scores or picks."},"outcomes":{"job":{"n":0,"worked":0,"degraded":0,"failed":0,"failureModes":{},"verifiedReports":0,"contributors":0,"excluded":{"seed_editorial":0,"test":0,"notFeedback":0},"reason":"no_submitted_outcome_reports_yet"},"pick":{"providerId":"nvidia-nim","n":0,"worked":0,"degraded":0,"failed":0,"failureModes":{},"evidenceTiers":{"agent_claim":0,"self_declared":0,"reference_checked":0,"outcome_verified":0},"reason":"no_submitted_outcome_reports_yet"},"scoresMutated":false,"more":"/api/outcomes?jtbd=air-gapped-model-serve"},"report":"POST /api/feedback {agentIdentity, outcome: failed|degraded|worked, detail, providerId, jtbdId, failureModeId?, receipt?}"}}