{"jtbd":{"id":"confidential-tee-inference","slug":"confidential-tee-inference","name":"Confidential / TEE-backed LLM inference","shortName":"TEE inference","problemStatement":"Run inference where the host cannot read prompts/weights in cleartext — confidential VMs or TEE-backed serverless for regulated or high-trust agents."},"pick":{"id":"chutes","slug":"chutes","name":"Chutes","tagline":"Budget open-model overflow with a now-pinned public TEE matrix. Depot open-model production pick stays…","website":"https://chutes.ai","overall":6.82,"scoreBand":{"low":6.2,"mid":6.8,"high":7.4,"halfWidth":0.6,"basis":"editorial_prior","display":"6.2–7.4 (editorial prior)"},"scoreLayers":{"editorialPrior":6.82,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","pricingNotes":"As of 2026-10-27 (chutes.ai/pricing, fetched twice 2026-10-27): Public TEE inference PAYG per 1M tokens, input/output (the page says per-model rates are 'pulled live from our pricing API'): gemma-4-31B-turbo $0.12/$0.37; Qwen3.8-27B $0.039/$1.25; Qwen3.6-27B $0.25/$2.00; DeepSeek-V4-Flash-0731 $0.44/$1.32; Kimi K2.6 $0.39/$1.80; Qwen 3.5 (397B-A17B) $0.45/$3.00; DeepSeek-V3.2 $1.00/$1.00; GLM-5.1 $0.90/$2.90; GLM-5.2 $1.25/$3.95; Kimi-K3 $1.85/$9.50 (cached-input rates also on page, not stored). Mistral-Nemo, Nemotron-3-Nano-Omni-30B, Qwen3-32B and Qwen3-235B-A22B-Thinking-2507 are no longer on the page (re-checked 2026-10-27; stored rows kept at their 2026-10-03 amounts, marked unverified, never ranked). Private Chute self-serve TEE GPU RTX Pro 6000 96 GB $1.80/hr + one-time deploy fee 3× hourly ($5.40). Page FAQ: 'Monthly plans are no longer sold on chutes.ai' (stored Plus $10 and Pro $20 rows kept from 2026-10-03, marked unverified, never ranked); no free tier. Matrix moves — re-curl before commits.","scores":{"capabilityFit":7.4,"pricePerformance":9.2,"latencyReliability":6.8,"developerDx":7.6,"privacyPosture":5.8,"lockInRisk":4,"maturity":6.2,"overall":6.82,"kind":"curated_estimate","confidence":"high","asOf":"2026-09-14"}},"runnersUp":[{"id":"friendli","slug":"friendli","name":"FriendliAI","tagline":"Open-model production peer when latency/tool-calling matter. Fireworks remains depot open-model default…","website":"https://friendli.ai","overall":8.01,"scoreBand":{"low":7.4,"mid":8,"high":8.6,"halfWidth":0.6,"basis":"editorial_prior","display":"7.4–8.6 (editorial prior)"},"scoreLayers":{"editorialPrior":8.01,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-10-01","pricingNotes":"As of 2026-10-01 (friendli.ai/pricing live): Dedicated Endpoints on-demand step-up **is live** — A100 **$4.0**/hr, H100 **$5.0**/hr, H200 **$7.0**/hr, B200 **$9.0**/hr, B300 $12.0/hr (was through-Sep-30: A100 $2.9, H100 $3.9, H200 $4.5, B200 $8.9, B300 $12.0). Billed per second; no idle/startup charge. Model API token examples on page (GLM/DeepSeek/MiniMax/whisper). SOC2 + HIPAA.","scores":{"capabilityFit":8.4,"pricePerformance":8,"latencyReliability":8.4,"developerDx":8.2,"privacyPosture":8.2,"lockInRisk":4,"maturity":7.6,"overall":8.01,"kind":"curated_estimate","confidence":"high","asOf":"2026-10-01"}},{"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"}},{"id":"fireworks","slug":"fireworks","name":"Fireworks AI","tagline":"Top pick for production open-model serving with real DX. Prefer over random GPU DIY when you want tokens not…","website":"https://fireworks.ai","overall":8.08,"scoreBand":{"low":7.5,"mid":8.1,"high":8.7,"halfWidth":0.6,"basis":"editorial_prior","display":"7.5–8.7 (editorial prior)"},"scoreLayers":{"editorialPrior":8.08,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","pricingNotes":"Serverless per-token + on-demand GPU; day-0 OSS model support; post-training stack. Free credits often available.","scores":{"capabilityFit":8.6,"pricePerformance":8.8,"latencyReliability":8.4,"developerDx":9,"privacyPosture":7.5,"lockInRisk":3.5,"maturity":8,"overall":8.08,"kind":"curated_estimate","confidence":"high","asOf":"2026-09-14"}}],"scoreBand":{"low":6.2,"mid":6.8,"high":7.4,"halfWidth":0.6,"basis":"editorial_prior","display":"6.2–7.4 (editorial prior)"},"scoreLayers":{"editorialPrior":6.82,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"whyPickOverHigherScore":{"pickId":"chutes","pickName":"Chutes","pickScore":6.82,"highestScoredCandidateId":"fireworks","highestScoredCandidateName":"Fireworks AI","highestScore":8.08,"pickHasLowerCompositeScore":true,"delta":-1.26,"pickLeadsOnDimensions":["pricePerformance (9.2 vs 8.8)"],"explanation":"Chutes (6.82) is the editorial pick for Confidential / TEE-backed LLM inference over higher-composite Fireworks AI (8.08) because composite scores are provider-wide priors while Chutes wins on pricePerformance (9.2 vs 8.8): Capability = real TEE/confidential posture + model coverage. Privacy weighted high. Chutes publishes a TEE matrix agents can pin; hyperscalers win when enterprise paperwork dominates. Confidence: medium — re-curl chutes.ai/pricing TEE rows before production."},"cheapest":{"providerId":"chutes","providerName":"Chutes","skuId":"chutes-qwen3-8-27b-qwen-qwen3-8-27b-tee-in","item":"Qwen3.8-27B (Qwen/Qwen3.8-27B-TEE)","plan":"Qwen3.8-27B (Qwen/Qwen3.8-27B-TEE) — Public TEE inference, USD per 1M tokens","unit":"usd_per_million_input_tokens","amountUsd":0.039,"isFloorPrice":true,"floorWarning":"Provider-wide floor SKU; may not be the flagship model scored for this JTBD.","skuCountInUnit":10,"isDepotPick":true,"sourceUrl":"https://chutes.ai/pricing","asOf":"2026-10-27","verifiedAsOf":"2026-10-27"},"recommendedWorkloadQuote":{"providerId":"chutes","providerName":"Chutes","skuId":"chutes-qwen3-8-27b-qwen-qwen3-8-27b-tee-in","item":"Qwen3.8-27B (Qwen/Qwen3.8-27B-TEE)","plan":"Qwen3.8-27B (Qwen/Qwen3.8-27B-TEE) — Public TEE inference, USD per 1M tokens","unit":"usd_per_million_input_tokens","amountUsd":0.039,"outputSkuId":"chutes-qwen3-8-27b-qwen-qwen3-8-27b-tee-out","outputItem":"Qwen3.8-27B (Qwen/Qwen3.8-27B-TEE)","outputAmountUsd":1.25,"outputUnit":"usd_per_million_output_tokens","sourceUrl":"https://chutes.ai/pricing","asOf":"2026-10-27","pricingLastVerifiedAt":"2026-10-27","isFlagshipForJob":false,"differsFromFloorCheapest":false,"representativeQuote":{"skuId":"chutes-qwen3-8-27b-qwen-qwen3-8-27b-tee-in","item":"Qwen3.8-27B (Qwen/Qwen3.8-27B-TEE)","plan":"Qwen3.8-27B (Qwen/Qwen3.8-27B-TEE) — Public TEE inference, USD per 1M tokens","amountUsd":0.039,"inputOrUnitUsd":0.039,"unit":"usd_per_million_input_tokens","outputUsd":1.25,"outputUnit":"usd_per_million_output_tokens","sourceUrl":"https://chutes.ai/pricing","asOf":"2026-10-27"},"estimatedTaskCost":{"tasks":1000,"retryAndToolOverheadMultiplier":1.15,"retryToolOverheadMultiplier":1.15,"inputTokensPerTask":4000,"outputTokensPerTask":1000,"baseCostPer1kTasksUsd":1.406,"totalUsd":1.6169,"estimatedTotalUsd":1.6169,"perTaskUsd":0.001617,"estimatedCostPerTaskUsd":0.001617,"formula":"((4,000 in * $0.039/1M + 1,000 out * $1.25/1M) * 1,000 tasks) * 1.15 overhead","assumptions":"1,000 agent tasks @ 4k input + 1k output tokens/task with 1.15x retry/tool-call overhead."}},"representativeQuote":{"skuId":"chutes-qwen3-8-27b-qwen-qwen3-8-27b-tee-in","item":"Qwen3.8-27B (Qwen/Qwen3.8-27B-TEE)","plan":"Qwen3.8-27B (Qwen/Qwen3.8-27B-TEE) — Public TEE inference, USD per 1M tokens","amountUsd":0.039,"inputOrUnitUsd":0.039,"unit":"usd_per_million_input_tokens","outputUsd":1.25,"outputUnit":"usd_per_million_output_tokens","sourceUrl":"https://chutes.ai/pricing","asOf":"2026-10-27"},"estimatedTaskCost":{"tasks":1000,"retryAndToolOverheadMultiplier":1.15,"retryToolOverheadMultiplier":1.15,"inputTokensPerTask":4000,"outputTokensPerTask":1000,"baseCostPer1kTasksUsd":1.406,"totalUsd":1.6169,"estimatedTotalUsd":1.6169,"perTaskUsd":0.001617,"estimatedCostPerTaskUsd":0.001617,"formula":"((4,000 in * $0.039/1M + 1,000 out * $1.25/1M) * 1,000 tasks) * 1.15 overhead","assumptions":"1,000 agent tasks @ 4k input + 1k output tokens/task with 1.15x retry/tool-call overhead."},"freeAlternatives":[],"referenceDocs":[],"falsification":{"jtbdId":"confidential-tee-inference","jtbdName":"Confidential / TEE-backed LLM inference","currentPickId":"chutes","currentPickScore":6.82,"challengerId":"friendli","challengerScore":8.01,"currentScoreGap":1.19,"minVerifiedOutcomes":10,"requiredOutcomeMargin":1.34,"requiredSuccessRateDelta":0.15,"maxPickPriceIncreasePct":25,"whatWouldChangePick":["FriendliAI (friendli) outperforms Chutes (chutes) by >= 1.34 outcome points (or >= 15% worked-rate delta) across >= 10 Countersign-verified production outcomes.","A verified price increase > 25% on Chutes's representative SKU for confidential-tee-inference without a corresponding capability gain.","Live caller rail exhaustion (?exhausted=chutes) 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":"friendli","minVerifiedOutcomes":10,"requiredOutcomeMargin":1.34,"requiredWorkedRateDelta":0.15},{"kind":"verified_price_increase","providerId":"chutes","maxPriceIncreasePct":25},{"kind":"live_rail_exhaustion_or_degradation","providerId":"chutes","immediateOverrideUrl":"/api/decide?jtbd=confidential-tee-inference&exhausted=chutes"}],"submissionSpec":{"falsifyEndpoint":"/api/falsify?jtbd=confidential-tee-inference","outcomesEndpoint":"POST /api/feedback","correctionsEndpoint":"POST /api/corrections","payloadTemplate":{"agentIdentity":"agent:<your-agent-id>","jtbdId":"confidential-tee-inference","providerId":"friendli","outcome":"worked","detail":"Comparative production evaluation on confidential-tee-inference (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":["FriendliAI (friendli) outperforms Chutes (chutes) by >= 1.34 outcome points (or >= 15% worked-rate delta) across >= 10 Countersign-verified production outcomes.","A verified price increase > 25% on Chutes's representative SKU for confidential-tee-inference without a corresponding capability gain.","Live caller rail exhaustion (?exhausted=chutes) or sustained >= 30% degraded/failed rate in verified production outcomes."],"routePlan":{"jtbdId":"confidential-tee-inference","primary":{"providerId":"chutes","name":"Chutes","overall":6.82,"scoreBand":{"low":6.2,"mid":6.8,"high":7.4,"halfWidth":0.6,"basis":"editorial_prior","display":"6.2–7.4 (editorial prior)"},"scoreLayers":{"editorialPrior":6.82,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","role":"primary","reason":"Editorial Depot Pick for Confidential / TEE-backed LLM inference; healthy/eligible under caller constraints."},"fallback":[{"providerId":"friendli","name":"FriendliAI","overall":8.01,"scoreBand":{"low":7.4,"mid":8,"high":8.6,"halfWidth":0.6,"basis":"editorial_prior","display":"7.4–8.6 (editorial prior)"},"scoreLayers":{"editorialPrior":8.01,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-10-01","role":"fallback","reason":"Ranked fallback route for Confidential / TEE-backed LLM inference."},{"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 Confidential / TEE-backed LLM inference."},{"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 Confidential / TEE-backed LLM inference."},{"providerId":"fireworks","name":"Fireworks AI","overall":8.08,"scoreBand":{"low":7.5,"mid":8.1,"high":8.7,"halfWidth":0.6,"basis":"editorial_prior","display":"7.5–8.7 (editorial prior)"},"scoreLayers":{"editorialPrior":8.08,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","role":"fallback","reason":"Ranked fallback route for Confidential / TEE-backed LLM inference."}],"disqualified":[],"expectedRegret":{"scoreDeltaVsUnconstrainedPick":0,"unconstrainedPickId":"chutes","activePrimaryId":"chutes","summary":"0.00 score regret: unconstrained editorial pick satisfies all caller constraints."},"evidenceAgeDays":{"editorialScoreAgeDays":43,"pricingVerifiedAgeDays":0,"editorialPriorAsOf":"2026-09-14","pricingLastVerifiedAt":"2026-10-27"},"confidenceBand":{"low":6.2,"mid":6.8,"high":7.4,"halfWidth":0.6,"basis":"editorial_prior","display":"6.2–7.4 (editorial prior)"},"constraintsApplied":false,"constraintBundle":{"task":null,"jtbd":"confidential-tee-inference","quotaExhausted":[],"degraded":[],"healthy":[],"budgetUsd":null,"maxLatencyMs":null,"region":null,"privacy":null,"exit":[],"existing":[]}},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","tie":false,"scoreGap":-1.19,"decidingFactor":null,"tieNote":null,"rationale":"Capability = real TEE/confidential posture + model coverage. Privacy weighted high. Chutes publishes a TEE matrix agents can pin; hyperscalers win when enterprise paperwork dominates. Confidence: medium — re-curl chutes.ai/pricing TEE rows before production.","whenNotTopPick":"Need hyperscaler confidential-compute contracts with BAA/DPA already negotiated (Bedrock/Azure), or a dedicated Friendli/GPU TEE SKU your security team already approved.","skipTopPick":false,"skipReason":null,"matchedConstraints":[],"pricingSummary":"As of 2026-10-27 (chutes.ai/pricing, fetched twice 2026-10-27): Public TEE inference PAYG per 1M tokens, input/output (the page says per-model rates are 'pulled live from our pricing API'): gemma-4-31B-turbo $0.12/$0.37; Qwen3.8-27B $0.039/$1.25; Qwen3.6-27B $0.25/$2.00; DeepSeek…","cite":"Depot Pick for confidential-tee-inference: chutes (asOf 2026-09-14). See GET /api/jtbds/confidential-tee-inference + GET /api/methodology.","nextActions":[{"step":1,"title":"Inspect full JTBD + embeds","href":"/api/jtbds/confidential-tee-inference?embed=providers","why":"Confirm pick, runners-up, and methodology notes."},{"step":2,"title":"Quote sourced SKUs","href":"/api/quote?jtbd=confidential-tee-inference","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/chutes","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=confidential-tee-inference","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":"2026-09-14","depth":{"whenNotToUse":{"text":"Need hyperscaler confidential-compute contracts with BAA/DPA already negotiated (Bedrock/Azure), or a dedicated Friendli/GPU TEE SKU your security team already approved.","source":"editorial `whenNotTopPick` (data/jtbds.json)"},"whenNotToUseReason":null,"runnerUp":{"providerId":"friendli","name":"FriendliAI","overallForJob":8.01,"pickOverallForJob":6.82,"beatsPickOn":["capabilityFit","latencyReliability","developerDx","privacyPosture","maturity"],"source":"first resolvable entry of the job's editorially ranked `runnersUpIds`; scores are stored job-weighted scores"},"runnerUpReason":null,"lockIn":{"pickLockInRisk":4,"runnerUpLockInRisk":4,"scale":"0–10 stored curated estimate; higher = more lock-in (worse)","pickExitSignals":["serves open-weight models (provider tag `open-model`)"],"runnerUpExitSignals":[],"pickNotes":[],"selfHostFallback":[],"migration":"Pick exit signals: serves open-weight models (provider tag `open-model`).","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 (v0.12.153), Depot Pick for confidential-tee-inference: chutes, scores as of 2026-09-14, retrieved 2026-10-27. https://getagentdepot.com/jtbds/confidential-tee-inference","markdown":"[Agent Provider Depot](https://getagentdepot.com/jtbds/confidential-tee-inference) (v0.12.153) — Depot Pick for `confidential-tee-inference`: **chutes** (scores as of 2026-09-14, retrieved 2026-10-27)","fields":{"publisher":"Agent Provider Depot","version":"0.12.153","role":"depot_pick","jtbdId":"confidential-tee-inference","providerId":"chutes","scoreAsOf":"2026-09-14","retrievedOn":"2026-10-27","page":"https://getagentdepot.com/jtbds/confidential-tee-inference","api":"https://getagentdepot.com/api/decide?jtbd=confidential-tee-inference"},"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":"2026-09-14","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":3,"sourcesReachable":3,"pricingRows":32,"pricingRowsReconfirmed":22,"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":"2026-09-14","editorialPriorAsOf":"2026-09-14","pricingLastVerifiedAt":"2026-10-27","pickLastReviewed":"2026-09-14","runnersUpScoreAsOf":["2026-10-01","2026-09-14","2026-09-14","2026-09-14"],"contractAsOf":"2026-10-03","pricingShape":"sourced_rows","normalizedUsdPerMillionTokens":null,"normalizationStatus":"ambiguous","normalizationReason":"input_output_split_not_a_single_rate"},"pricingContract":{"normalizedUsdPerMillionTokens":null,"normalizationStatus":"ambiguous","normalizationReason":"input_output_split_not_a_single_rate","shape":"sourced_rows","filterable":false,"priceSortEligible":true,"priceSortKeyUsdPerMillionInputTokens":0.039,"rows":[{"id":"chutes-mistral-nemo-instruct-2407-unsloth-mistral-nemo-instruct-2407-tee-in","providerId":"chutes","sku":"Mistral-Nemo-Instruct-2407 (unsloth/Mistral-Nemo-Instruct-2407-TEE)","unit":"usd_per_million_input_tokens","amountUsd":0.0245,"currency":"USD","sourceUrl":"https://chutes.ai/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.0245,"normalizationReason":null,"priceSortEligible":false,"qualifier":"Public TEE inference, USD per 1M tokens. Workload estimate on the same card was not used. TAO column not used. Not on chutes.ai/pricing 2026-10-27 (v0.12.141): the Model pricing table no longer lists this model; amount kept from 2026-10-03, not reconfirmed (asOf unchanged).","sourceStatus":"unverified","sourceStatusReason":"model_not_on_source_page: on 2026-10-27 the Model pricing table lists gemma-4-31B-turbo, Qwen3.8-27B, Qwen3.6-27B, DeepSeek-V4-Flash-0731, Kimi K2.6, Qwen 3.5, DeepSeek-V3.2, GLM-5.1, GLM-5.2 and Kimi-K3 (re-checked twice, also absent in the 2026-10-27 06:06 ET fetch); Mistral-Nemo-Instruct-2407 is no longer on https://chutes.ai/pricing (no occurrence of the name anywhere in the page text). Kept for history, never ranked.","sourceStatusCheckedOn":"2026-10-27"},{"id":"chutes-mistral-nemo-instruct-2407-unsloth-mistral-nemo-instruct-2407-tee-out","providerId":"chutes","sku":"Mistral-Nemo-Instruct-2407 (unsloth/Mistral-Nemo-Instruct-2407-TEE)","unit":"usd_per_million_output_tokens","amountUsd":0.0978,"currency":"USD","sourceUrl":"https://chutes.ai/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.0978,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"Public TEE inference output per 1M tokens. Not on chutes.ai/pricing 2026-10-27 (v0.12.141): the Model pricing table no longer lists this model; amount kept from 2026-10-03, not reconfirmed (asOf unchanged).","sourceStatus":"unverified","sourceStatusReason":"model_not_on_source_page: on 2026-10-27 the Model pricing table lists gemma-4-31B-turbo, Qwen3.8-27B, Qwen3.6-27B, DeepSeek-V4-Flash-0731, Kimi K2.6, Qwen 3.5, DeepSeek-V3.2, GLM-5.1, GLM-5.2 and Kimi-K3 (re-checked twice, also absent in the 2026-10-27 06:06 ET fetch); Mistral-Nemo-Instruct-2407 is no longer on https://chutes.ai/pricing (no occurrence of the name anywhere in the page text). Kept for history, never ranked.","sourceStatusCheckedOn":"2026-10-27"},{"id":"chutes-nemotron-3-nano-omni-30b-nemotron-3-nano-omni-30b-tee-in","providerId":"chutes","sku":"Nemotron-3-Nano-Omni-30B (Nemotron-3-Nano-Omni-30B-TEE)","unit":"usd_per_million_input_tokens","amountUsd":0.0245,"currency":"USD","sourceUrl":"https://chutes.ai/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.0245,"normalizationReason":null,"priceSortEligible":false,"qualifier":"Public TEE inference, USD per 1M tokens. Workload estimate on the same card was not used. TAO column not used. Not on chutes.ai/pricing 2026-10-27 (v0.12.141): the Model pricing table no longer lists this model; amount kept from 2026-10-03, not reconfirmed (asOf unchanged).","sourceStatus":"unverified","sourceStatusReason":"model_not_on_source_page: on 2026-10-27 the Model pricing table lists gemma-4-31B-turbo, Qwen3.8-27B, Qwen3.6-27B, DeepSeek-V4-Flash-0731, Kimi K2.6, Qwen 3.5, DeepSeek-V3.2, GLM-5.1, GLM-5.2 and Kimi-K3 (re-checked twice, also absent in the 2026-10-27 06:06 ET fetch); Nemotron-3-Nano-Omni-30B is no longer on https://chutes.ai/pricing (no occurrence of the name anywhere in the page text). Kept for history, never ranked.","sourceStatusCheckedOn":"2026-10-27"},{"id":"chutes-nemotron-3-nano-omni-30b-nemotron-3-nano-omni-30b-tee-out","providerId":"chutes","sku":"Nemotron-3-Nano-Omni-30B (Nemotron-3-Nano-Omni-30B-TEE)","unit":"usd_per_million_output_tokens","amountUsd":0.0978,"currency":"USD","sourceUrl":"https://chutes.ai/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.0978,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"Public TEE inference output per 1M tokens. Not on chutes.ai/pricing 2026-10-27 (v0.12.141): the Model pricing table no longer lists this model; amount kept from 2026-10-03, not reconfirmed (asOf unchanged).","sourceStatus":"unverified","sourceStatusReason":"model_not_on_source_page: on 2026-10-27 the Model pricing table lists gemma-4-31B-turbo, Qwen3.8-27B, Qwen3.6-27B, DeepSeek-V4-Flash-0731, Kimi K2.6, Qwen 3.5, DeepSeek-V3.2, GLM-5.1, GLM-5.2 and Kimi-K3 (re-checked twice, also absent in the 2026-10-27 06:06 ET fetch); Nemotron-3-Nano-Omni-30B is no longer on https://chutes.ai/pricing (no occurrence of the name anywhere in the page text). Kept for history, never ranked.","sourceStatusCheckedOn":"2026-10-27"},{"id":"chutes-qwen3-32b-qwen-qwen3-32b-tee-in","providerId":"chutes","sku":"Qwen3-32B (Qwen/Qwen3-32B-TEE)","unit":"usd_per_million_input_tokens","amountUsd":0.104,"currency":"USD","sourceUrl":"https://chutes.ai/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.104,"normalizationReason":null,"priceSortEligible":false,"qualifier":"Public TEE inference, USD per 1M tokens. Workload estimate on the same card was not used. TAO column not used. Not on chutes.ai/pricing 2026-10-27 (v0.12.141): the Model pricing table no longer lists this model; amount kept from 2026-10-03, not reconfirmed (asOf unchanged).","sourceStatus":"unverified","sourceStatusReason":"model_not_on_source_page: on 2026-10-27 the Model pricing table lists gemma-4-31B-turbo, Qwen3.8-27B, Qwen3.6-27B, DeepSeek-V4-Flash-0731, Kimi K2.6, Qwen 3.5, DeepSeek-V3.2, GLM-5.1, GLM-5.2 and Kimi-K3 (re-checked twice, also absent in the 2026-10-27 06:06 ET fetch); Qwen3-32B is no longer on https://chutes.ai/pricing (no occurrence of the name anywhere in the page text). Kept for history, never ranked.","sourceStatusCheckedOn":"2026-10-27"},{"id":"chutes-qwen3-32b-qwen-qwen3-32b-tee-out","providerId":"chutes","sku":"Qwen3-32B (Qwen/Qwen3-32B-TEE)","unit":"usd_per_million_output_tokens","amountUsd":0.416,"currency":"USD","sourceUrl":"https://chutes.ai/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.416,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"Public TEE inference output per 1M tokens. Not on chutes.ai/pricing 2026-10-27 (v0.12.141): the Model pricing table no longer lists this model; amount kept from 2026-10-03, not reconfirmed (asOf unchanged).","sourceStatus":"unverified","sourceStatusReason":"model_not_on_source_page: on 2026-10-27 the Model pricing table lists gemma-4-31B-turbo, Qwen3.8-27B, Qwen3.6-27B, DeepSeek-V4-Flash-0731, Kimi K2.6, Qwen 3.5, DeepSeek-V3.2, GLM-5.1, GLM-5.2 and Kimi-K3 (re-checked twice, also absent in the 2026-10-27 06:06 ET fetch); Qwen3-32B is no longer on https://chutes.ai/pricing (no occurrence of the name anywhere in the page text). Kept for history, never ranked.","sourceStatusCheckedOn":"2026-10-27"},{"id":"chutes-gemma-4-31b-turbo-google-gemma-4-31b-turbo-tee-in","providerId":"chutes","sku":"gemma-4-31B-turbo (google/gemma-4-31B-turbo-TEE)","unit":"usd_per_million_input_tokens","amountUsd":0.12,"currency":"USD","sourceUrl":"https://chutes.ai/pricing","asOf":"2026-10-27","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.12,"normalizationReason":null,"priceSortEligible":true,"qualifier":"Public TEE inference, USD per 1M tokens. Workload estimate on the same card was not used. TAO column not used. Reconfirmed 2026-10-27 (v0.12.141). The page says per-model rates are 'pulled live from our pricing API'; cached-input rate on the same card not stored."},{"id":"chutes-gemma-4-31b-turbo-google-gemma-4-31b-turbo-tee-out","providerId":"chutes","sku":"gemma-4-31B-turbo (google/gemma-4-31B-turbo-TEE)","unit":"usd_per_million_output_tokens","amountUsd":0.37,"currency":"USD","sourceUrl":"https://chutes.ai/pricing","asOf":"2026-10-27","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.37,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"Public TEE inference output per 1M tokens. Reconfirmed 2026-10-27 (v0.12.141). The page says per-model rates are 'pulled live from our pricing API'; cached-input rate on the same card not stored."},{"id":"chutes-qwen3-235b-a22b-thinking-2507-qwen-qwen3-235b-a22b-thinking-2507-tee-in","providerId":"chutes","sku":"Qwen3-235B-A22B-Thinking-2507 (Qwen/Qwen3-235B-A22B-Thinking-2507-TEE)","unit":"usd_per_million_input_tokens","amountUsd":0.2989,"currency":"USD","sourceUrl":"https://chutes.ai/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.2989,"normalizationReason":null,"priceSortEligible":false,"qualifier":"Public TEE inference, USD per 1M tokens. Workload estimate on the same card was not used. TAO column not used. Not on chutes.ai/pricing 2026-10-27 (v0.12.141): the Model pricing table no longer lists this model; amount kept from 2026-10-03, not reconfirmed (asOf unchanged).","sourceStatus":"unverified","sourceStatusReason":"model_not_on_source_page: on 2026-10-27 the Model pricing table lists gemma-4-31B-turbo, Qwen3.8-27B, Qwen3.6-27B, DeepSeek-V4-Flash-0731, Kimi K2.6, Qwen 3.5, DeepSeek-V3.2, GLM-5.1, GLM-5.2 and Kimi-K3 (re-checked twice, also absent in the 2026-10-27 06:06 ET fetch); Qwen3-235B-A22B-Thinking-2507 is no longer on https://chutes.ai/pricing (no occurrence of the name anywhere in the page text). Kept for history, never ranked.","sourceStatusCheckedOn":"2026-10-27"},{"id":"chutes-qwen3-235b-a22b-thinking-2507-qwen-qwen3-235b-a22b-thinking-2507-tee-out","providerId":"chutes","sku":"Qwen3-235B-A22B-Thinking-2507 (Qwen/Qwen3-235B-A22B-Thinking-2507-TEE)","unit":"usd_per_million_output_tokens","amountUsd":1.1957,"currency":"USD","sourceUrl":"https://chutes.ai/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":1.1957,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"Public TEE inference output per 1M tokens. Not on chutes.ai/pricing 2026-10-27 (v0.12.141): the Model pricing table no longer lists this model; amount kept from 2026-10-03, not reconfirmed (asOf unchanged).","sourceStatus":"unverified","sourceStatusReason":"model_not_on_source_page: on 2026-10-27 the Model pricing table lists gemma-4-31B-turbo, Qwen3.8-27B, Qwen3.6-27B, DeepSeek-V4-Flash-0731, Kimi K2.6, Qwen 3.5, DeepSeek-V3.2, GLM-5.1, GLM-5.2 and Kimi-K3 (re-checked twice, also absent in the 2026-10-27 06:06 ET fetch); Qwen3-235B-A22B-Thinking-2507 is no longer on https://chutes.ai/pricing (no occurrence of the name anywhere in the page text). Kept for history, never ranked.","sourceStatusCheckedOn":"2026-10-27"},{"id":"chutes-qwen3-8-27b-qwen-qwen3-8-27b-tee-in","providerId":"chutes","sku":"Qwen3.8-27B (Qwen/Qwen3.8-27B-TEE)","unit":"usd_per_million_input_tokens","amountUsd":0.039,"currency":"USD","sourceUrl":"https://chutes.ai/pricing","asOf":"2026-10-27","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.039,"normalizationReason":null,"priceSortEligible":true,"qualifier":"Public TEE inference, USD per 1M tokens. Workload estimate on the same card was not used. TAO column not used. Reconfirmed 2026-10-27 (v0.12.141). The page says per-model rates are 'pulled live from our pricing API'; cached-input rate on the same card not stored."},{"id":"chutes-qwen3-8-27b-qwen-qwen3-8-27b-tee-out","providerId":"chutes","sku":"Qwen3.8-27B (Qwen/Qwen3.8-27B-TEE)","unit":"usd_per_million_output_tokens","amountUsd":1.25,"currency":"USD","sourceUrl":"https://chutes.ai/pricing","asOf":"2026-10-27","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":1.25,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"Public TEE inference output per 1M tokens. Reconfirmed 2026-10-27 (v0.12.141). The page says per-model rates are 'pulled live from our pricing API'; cached-input rate on the same card not stored."},{"id":"chutes-qwen3-6-27b-qwen-qwen3-6-27b-tee-in","providerId":"chutes","sku":"Qwen3.6-27B (Qwen/Qwen3.6-27B-TEE)","unit":"usd_per_million_input_tokens","amountUsd":0.25,"currency":"USD","sourceUrl":"https://chutes.ai/pricing","asOf":"2026-10-27","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.25,"normalizationReason":null,"priceSortEligible":true,"qualifier":"Public TEE inference, USD per 1M tokens. Workload estimate on the same card was not used. TAO column not used. Reconfirmed 2026-10-27 (v0.12.141). The page says per-model rates are 'pulled live from our pricing API'; cached-input rate on the same card not stored."},{"id":"chutes-qwen3-6-27b-qwen-qwen3-6-27b-tee-out","providerId":"chutes","sku":"Qwen3.6-27B (Qwen/Qwen3.6-27B-TEE)","unit":"usd_per_million_output_tokens","amountUsd":2,"currency":"USD","sourceUrl":"https://chutes.ai/pricing","asOf":"2026-10-27","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":2,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"Public TEE inference output per 1M tokens. Reconfirmed 2026-10-27 (v0.12.141). The page says per-model rates are 'pulled live from our pricing API'; cached-input rate on the same card not stored."},{"id":"chutes-deepseek-v4-flash-0731-deepseek-ai-deepseek-v4-flash-0731-tee-in","providerId":"chutes","sku":"DeepSeek-V4-Flash-0731 (deepseek-ai/DeepSeek-V4-Flash-0731-TEE)","unit":"usd_per_million_input_tokens","amountUsd":0.44,"currency":"USD","sourceUrl":"https://chutes.ai/pricing","asOf":"2026-10-27","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.44,"normalizationReason":null,"priceSortEligible":true,"qualifier":"Public TEE inference, USD per 1M tokens. Workload estimate on the same card was not used. TAO column not used. Reconfirmed 2026-10-27 (v0.12.141). The page says per-model rates are 'pulled live from our pricing API'; cached-input rate on the same card not stored."},{"id":"chutes-deepseek-v4-flash-0731-deepseek-ai-deepseek-v4-flash-0731-tee-out","providerId":"chutes","sku":"DeepSeek-V4-Flash-0731 (deepseek-ai/DeepSeek-V4-Flash-0731-TEE)","unit":"usd_per_million_output_tokens","amountUsd":1.32,"currency":"USD","sourceUrl":"https://chutes.ai/pricing","asOf":"2026-10-27","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":1.32,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"Public TEE inference output per 1M tokens. Reconfirmed 2026-10-27 (v0.12.141). The page says per-model rates are 'pulled live from our pricing API'; cached-input rate on the same card not stored."},{"id":"chutes-qwen-3-5-qwen-qwen3-5-397b-a17b-tee-in","providerId":"chutes","sku":"Qwen 3.5 (Qwen/Qwen3.5-397B-A17B-TEE)","unit":"usd_per_million_input_tokens","amountUsd":0.45,"currency":"USD","sourceUrl":"https://chutes.ai/pricing","asOf":"2026-10-27","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.45,"normalizationReason":null,"priceSortEligible":true,"qualifier":"Public TEE inference, USD per 1M tokens. Workload estimate on the same card was not used. TAO column not used. Reconfirmed 2026-10-27 (v0.12.141). The page says per-model rates are 'pulled live from our pricing API'; cached-input rate on the same card not stored."},{"id":"chutes-qwen-3-5-qwen-qwen3-5-397b-a17b-tee-out","providerId":"chutes","sku":"Qwen 3.5 (Qwen/Qwen3.5-397B-A17B-TEE)","unit":"usd_per_million_output_tokens","amountUsd":3,"currency":"USD","sourceUrl":"https://chutes.ai/pricing","asOf":"2026-10-27","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":3,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"Public TEE inference output per 1M tokens. Reconfirmed 2026-10-27 (v0.12.141). The page says per-model rates are 'pulled live from our pricing API'; cached-input rate on the same card not stored."},{"id":"chutes-kimi-k2-6-moonshotai-kimi-k2-6-tee-in","providerId":"chutes","sku":"Kimi K2.6 (moonshotai/Kimi-K2.6-TEE)","unit":"usd_per_million_input_tokens","amountUsd":0.39,"currency":"USD","sourceUrl":"https://chutes.ai/pricing","asOf":"2026-10-27","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.39,"normalizationReason":null,"priceSortEligible":true,"qualifier":"Public TEE inference, USD per 1M tokens. Workload estimate on the same card was not used. TAO column not used. Re-priced 2026-10-27 (v0.12.141): 0.45 -> 0.39 USD per 1M input tokens from the page's Model pricing table. The page says per-model rates are 'pulled live from our pricing API', so they can move; cached-input rate on the same card not stored."},{"id":"chutes-kimi-k2-6-moonshotai-kimi-k2-6-tee-out","providerId":"chutes","sku":"Kimi K2.6 (moonshotai/Kimi-K2.6-TEE)","unit":"usd_per_million_output_tokens","amountUsd":1.8,"currency":"USD","sourceUrl":"https://chutes.ai/pricing","asOf":"2026-10-27","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":1.8,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"Public TEE inference output per 1M tokens. Re-priced 2026-10-27 (v0.12.141): 1.95 -> 1.8 USD per 1M output tokens from the page's Model pricing table. The page says per-model rates are 'pulled live from our pricing API', so they can move; cached-input rate on the same card not stored."},{"id":"chutes-deepseek-v3-2-deepseek-ai-deepseek-v3-2-tee-in","providerId":"chutes","sku":"DeepSeek-V3.2 (deepseek-ai/DeepSeek-V3.2-TEE)","unit":"usd_per_million_input_tokens","amountUsd":1,"currency":"USD","sourceUrl":"https://chutes.ai/pricing","asOf":"2026-10-27","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":1,"normalizationReason":null,"priceSortEligible":true,"qualifier":"Public TEE inference, USD per 1M tokens. Workload estimate on the same card was not used. TAO column not used. Reconfirmed 2026-10-27 (v0.12.141). The page says per-model rates are 'pulled live from our pricing API'; cached-input rate on the same card not stored."},{"id":"chutes-deepseek-v3-2-deepseek-ai-deepseek-v3-2-tee-out","providerId":"chutes","sku":"DeepSeek-V3.2 (deepseek-ai/DeepSeek-V3.2-TEE)","unit":"usd_per_million_output_tokens","amountUsd":1,"currency":"USD","sourceUrl":"https://chutes.ai/pricing","asOf":"2026-10-27","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":1,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"Public TEE inference output per 1M tokens. Reconfirmed 2026-10-27 (v0.12.141). The page says per-model rates are 'pulled live from our pricing API'; cached-input rate on the same card not stored."},{"id":"chutes-glm-5-1-zai-org-glm-5-1-tee-in","providerId":"chutes","sku":"GLM-5.1 (zai-org/GLM-5.1-TEE)","unit":"usd_per_million_input_tokens","amountUsd":0.9,"currency":"USD","sourceUrl":"https://chutes.ai/pricing","asOf":"2026-10-27","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.9,"normalizationReason":null,"priceSortEligible":true,"qualifier":"Public TEE inference, USD per 1M tokens. Workload estimate on the same card was not used. TAO column not used. Re-priced 2026-10-27 (v0.12.141): 0.98 -> 0.9 USD per 1M input tokens from the page's Model pricing table. The page says per-model rates are 'pulled live from our pricing API', so they can move; cached-input rate on the same card not stored."},{"id":"chutes-glm-5-1-zai-org-glm-5-1-tee-out","providerId":"chutes","sku":"GLM-5.1 (zai-org/GLM-5.1-TEE)","unit":"usd_per_million_output_tokens","amountUsd":2.9,"currency":"USD","sourceUrl":"https://chutes.ai/pricing","asOf":"2026-10-27","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":2.9,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"Public TEE inference output per 1M tokens. Re-priced 2026-10-27 (v0.12.141): 3.08 -> 2.9 USD per 1M output tokens from the page's Model pricing table. The page says per-model rates are 'pulled live from our pricing API', so they can move; cached-input rate on the same card not stored."},{"id":"chutes-glm-5-2-zai-org-glm-5-2-tee-in","providerId":"chutes","sku":"GLM-5.2 (zai-org/GLM-5.2-TEE)","unit":"usd_per_million_input_tokens","amountUsd":1.25,"currency":"USD","sourceUrl":"https://chutes.ai/pricing","asOf":"2026-10-27","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":1.25,"normalizationReason":null,"priceSortEligible":true,"qualifier":"Public TEE inference, USD per 1M tokens. Workload estimate on the same card was not used. TAO column not used. Reconfirmed 2026-10-27 (v0.12.141). The page says per-model rates are 'pulled live from our pricing API'; cached-input rate on the same card not stored."},{"id":"chutes-glm-5-2-zai-org-glm-5-2-tee-out","providerId":"chutes","sku":"GLM-5.2 (zai-org/GLM-5.2-TEE)","unit":"usd_per_million_output_tokens","amountUsd":3.95,"currency":"USD","sourceUrl":"https://chutes.ai/pricing","asOf":"2026-10-27","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":3.95,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"Public TEE inference output per 1M tokens. Reconfirmed 2026-10-27 (v0.12.141). The page says per-model rates are 'pulled live from our pricing API'; cached-input rate on the same card not stored."},{"id":"chutes-kimi-k3-moonshotai-kimi-k3-tee-in","providerId":"chutes","sku":"Kimi-K3 (moonshotai/Kimi-K3-TEE)","unit":"usd_per_million_input_tokens","amountUsd":1.85,"currency":"USD","sourceUrl":"https://chutes.ai/pricing","asOf":"2026-10-27","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":1.85,"normalizationReason":null,"priceSortEligible":true,"qualifier":"Public TEE inference, USD per 1M tokens. Workload estimate on the same card was not used. TAO column not used. Reconfirmed 2026-10-27 (v0.12.141). The page says per-model rates are 'pulled live from our pricing API'; cached-input rate on the same card not stored."},{"id":"chutes-kimi-k3-moonshotai-kimi-k3-tee-out","providerId":"chutes","sku":"Kimi-K3 (moonshotai/Kimi-K3-TEE)","unit":"usd_per_million_output_tokens","amountUsd":9.5,"currency":"USD","sourceUrl":"https://chutes.ai/pricing","asOf":"2026-10-27","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":9.5,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"Public TEE inference output per 1M tokens. Reconfirmed 2026-10-27 (v0.12.141). The page says per-model rates are 'pulled live from our pricing API'; cached-input rate on the same card not stored."},{"id":"chutes-rtx-pro-6000-96gb-usd-per-gpu-hour","providerId":"chutes","sku":"RTX Pro 6000 96GB","unit":"usd_per_gpu_hour","amountUsd":1.8,"currency":"USD","sourceUrl":"https://chutes.ai/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"gpu_hour_not_coerced_to_per_million_tokens","priceSortEligible":false,"qualifier":"Self-serve TEE GPU hourly rate. Not converted from per-second. Reconfirmed 2026-10-27 (v0.12.140): page adds a 'One-time deployment fee $5.40 = 3× hourly rate' (not stored as a row) and 'Billed by the second at the GPU's hourly rate'."},{"id":"chutes-private-chute-deployment-fee-usd-one-time","providerId":"chutes","sku":"Private chute deployment fee","unit":"usd_one_time","amountUsd":5.4,"currency":"USD","sourceUrl":"https://chutes.ai/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_one_time_fee","priceSortEligible":false,"qualifier":"Page states one-time fee equals 3× the $1.80 hourly rate ($5.40) for this GPU class. Reconfirmed 2026-10-27 (v0.12.141): page prints 'One-time deployment fee $5.40 = 3× hourly rate' next to the $1.80 / hour RTX Pro 6000 96 GB self-serve TEE rate."},{"id":"chutes-plus-usd-per-month","providerId":"chutes","sku":"Plus","unit":"usd_per_month","amountUsd":10,"currency":"USD","sourceUrl":"https://chutes.ai/pricing","asOf":"2026-10-03","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_month","priceSortEligible":false,"qualifier":"Optional plan. 6% off PAYG was not applied to token rows. chutes.ai/pricing 2026-10-27 (v0.12.141) FAQ: 'Monthly plans are no longer sold on chutes.ai' (existing plans run to the end of the current billing period, then usage is pay-as-you-go); amount kept from 2026-10-03, not reconfirmed (asOf unchanged).","sourceStatus":"unverified","sourceStatusReason":"plan_no_longer_sold: on 2026-10-27 the https://chutes.ai/pricing FAQ says 'Monthly plans are no longer sold on chutes.ai. If you already have one, it stays active until the end of your current billing period' (re-checked twice, same as the 2026-10-27 06:06 ET fetch); the page shows no Plus plan or $10 amount. Kept for history, never ranked.","sourceStatusCheckedOn":"2026-10-27"},{"id":"chutes-pro-usd-per-month","providerId":"chutes","sku":"Pro","unit":"usd_per_month","amountUsd":20,"currency":"USD","sourceUrl":"https://chutes.ai/pricing","asOf":"2026-10-03","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_month","priceSortEligible":false,"qualifier":"Optional plan. 10% off PAYG was not applied to token rows. chutes.ai/pricing 2026-10-27 (v0.12.141) FAQ: 'Monthly plans are no longer sold on chutes.ai' (existing plans run to the end of the current billing period, then usage is pay-as-you-go); amount kept from 2026-10-03, not reconfirmed (asOf unchanged).","sourceStatus":"unverified","sourceStatusReason":"plan_no_longer_sold: on 2026-10-27 the https://chutes.ai/pricing FAQ says 'Monthly plans are no longer sold on chutes.ai. If you already have one, it stays active until the end of your current billing period' (re-checked twice, same as the 2026-10-27 06:06 ET fetch); the page shows no Pro plan or $20 amount. Kept for history, never ranked.","sourceStatusCheckedOn":"2026-10-27"}],"notesExcerpt":"As of 2026-10-27 (chutes.ai/pricing, fetched twice 2026-10-27): Public TEE inference PAYG per 1M tokens, input/output (the page says per-model rates are 'pulled live from our pricing API'): gemma-4-31B-turbo $0.12/$0.37; Qwen3.8-27B $0.039/$1.25; Qwen3.6-27B $0.25/$2.00; DeepSeek…","notesCheck":{"status":"no_known_contradiction","pairs":[],"review":null,"note":null},"lastReviewed":"2026-09-14","scoreAsOf":"2026-09-14","website":"https://chutes.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":"Partial coverage. Providers without a fetched SKU are omitted. See GET /api/pricing."},"links":{"jtbd":"/jtbds/confidential-tee-inference","jtbdApi":"/api/jtbds/confidential-tee-inference","leaderboard":"/api/leaderboards?jtbd=confidential-tee-inference","methodology":"/api/methodology","badge":"/api/badge?type=depot-pick&jtbd=confidential-tee-inference","decide":"/api/decide?jtbd=confidential-tee-inference","humanPage":"/jtbds/confidential-tee-inference","alternatives":"/api/alternatives?provider=chutes","canonical":"/api/canonical","quote":"/api/quote?jtbd=confidential-tee-inference","falsify":"/api/falsify?jtbd=confidential-tee-inference"},"constraintBundle":{"task":null,"jtbd":"confidential-tee-inference","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":"chutes","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=confidential-tee-inference"},"report":"POST /api/feedback {agentIdentity, outcome: failed|degraded|worked, detail, providerId, jtbdId, failureModeId?, receipt?}"}}