{"jtbd":{"id":"prompt-caching-optimization","slug":"prompt-caching-optimization","name":"Prompt-caching cost optimization","shortName":"Prompt caching","problemStatement":"Cut spend on long system prompts, tool schemas, and RAG prefixes via provider prompt caching / context caching with predictable hit rates."},"pick":{"id":"anthropic","slug":"anthropic","name":"Anthropic","tagline":"Depot default for serious coding and production agents. Prefer Sonnet for cost/quality; reserve Opus for hard…","website":"https://www.anthropic.com","overall":8,"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,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-10-19","pricingNotes":"Sonnet 5 ~$2/$10 per 1M; Opus ~$5/$25; Haiku 4.5 ~$1/$5; Fable higher. Prompt caching + batch. Managed Agents session-hour fees. US-only inference ~1.1x.","scores":{"capabilityFit":9.7,"pricePerformance":6.8,"latencyReliability":8.7,"developerDx":9.2,"privacyPosture":9,"lockInRisk":6.5,"maturity":9.4,"overall":8,"kind":"curated_estimate","confidence":"high","asOf":"2026-10-19"}},"runnersUp":[{"id":"openai","slug":"openai","name":"OpenAI","tagline":"Default when you want maximum capability and ecosystem glue. Multi-home critical paths behind OpenAI-compat…","website":"https://openai.com","overall":7.72,"scoreBand":{"low":7.1,"mid":7.7,"high":8.3,"halfWidth":0.6,"basis":"editorial_prior","display":"7.1–8.3 (editorial prior)"},"scoreLayers":{"editorialPrior":7.72,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","pricingNotes":"GPT-5.6 tiers (Sol/Terra/Luna) roughly $5/$30 to $1/$6 per 1M tokens; prompt caching with explicit breakpoints; batch discounts. Media (images/audio) billed separately.","scores":{"capabilityFit":9.6,"pricePerformance":6.2,"latencyReliability":8.8,"developerDx":9.5,"privacyPosture":7.8,"lockInRisk":7.2,"maturity":9.8,"overall":7.72,"kind":"curated_estimate","confidence":"high","asOf":"2026-09-14"}},{"id":"google-ai","slug":"google-ai","name":"Google AI (Gemini)","tagline":"Best value frontier stack and multimodal king. Use Flash for high-volume agent loops; Pro when quality…","website":"https://ai.google.dev","overall":8.37,"scoreBand":{"low":7.8,"mid":8.4,"high":9,"halfWidth":0.6,"basis":"editorial_prior","display":"7.8–9.0 (editorial prior)"},"scoreLayers":{"editorialPrior":8.37,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-10-19","pricingNotes":"Gemini 3.x Pro often ~$2/$12 under 200K; Flash tiers much cheaper. 1M context. Vertex for enterprise. Batch half-price common.","scores":{"capabilityFit":9.2,"pricePerformance":8.8,"latencyReliability":8.5,"developerDx":8.2,"privacyPosture":8,"lockInRisk":6,"maturity":9.6,"overall":8.37,"kind":"curated_estimate","confidence":"high","asOf":"2026-10-19"}},{"id":"portkey","slug":"portkey","name":"Portkey","tagline":"Depot pick for production AI gateway (fallbacks, virtual keys, budgets). OpenRouter when you want a model…","website":"https://portkey.ai","overall":8.2,"scoreBand":{"low":7.6,"mid":8.2,"high":8.8,"halfWidth":0.6,"basis":"editorial_prior","display":"7.6–8.8 (editorial prior)"},"scoreLayers":{"editorialPrior":8.2,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","pricingNotes":"As of 2026-09-14 (portkey.ai/pricing): Developer free forever (10k logs/mo, 3-day log / 30-day metrics retention). Production $49/mo (100k logs, +$9/100k overage, 30/90-day retention, guardrails, RBAC). Enterprise custom (10M+ logs, VPC, HIPAA/BAA, private cloud). OSS self-host gateway available. Note: packaging increasingly tied to Palo Alto Prisma AIRS AI Gateway narrative — same lineage as catalogued prisma-airs enterprise SKU.","scores":{"capabilityFit":8.8,"pricePerformance":8.2,"latencyReliability":8.6,"developerDx":9,"privacyPosture":8.2,"lockInRisk":5,"maturity":8.2,"overall":8.2,"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":7.34,"scoreBand":{"low":6.7,"mid":7.3,"high":7.9,"halfWidth":0.6,"basis":"editorial_prior","display":"6.7–7.9 (editorial prior)"},"scoreLayers":{"editorialPrior":7.34,"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":7.34,"kind":"curated_estimate","confidence":"high","asOf":"2026-09-14"}}],"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,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"whyPickOverHigherScore":{"pickId":"anthropic","pickName":"Anthropic","pickScore":8,"highestScoredCandidateId":"google-ai","highestScoredCandidateName":"Google AI (Gemini)","highestScore":8.37,"pickHasLowerCompositeScore":true,"delta":-0.37,"pickLeadsOnDimensions":["capabilityFit (9.7 vs 9.2)","latencyReliability (8.7 vs 8.5)","developerDx (9.2 vs 8.2)","privacyPosture (9 vs 8)"],"explanation":"Anthropic (8) is the editorial pick for Prompt-caching cost optimization over higher-composite Google AI (Gemini) (8.37) because composite scores are provider-wide priors while Anthropic wins on capabilityFit (9.7 vs 9.2), latencyReliability (8.7 vs 8.5), developerDx (9.2 vs 8.2), privacyPosture (9 vs 8): pricePerf + DX of cache controls + hit-rate observability. Anthropic prompt caching is the clearest agent-facing story; OpenAI/Gemini close. Confidence: high."},"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":{"providerId":"anthropic","providerName":"Anthropic","skuId":"anthropic-sonnet-55-input","item":"Sonnet 5.5","plan":"Sonnet 5.5 — standard input; cache read/write on the same card were not folded in","unit":"usd_per_million_input_tokens","amountUsd":2,"outputSkuId":"anthropic-sonnet-55-output","outputItem":"Sonnet 5.5","outputAmountUsd":10,"outputUnit":"usd_per_million_output_tokens","sourceUrl":"https://claude.com/pricing","asOf":"2026-10-27","pricingLastVerifiedAt":"2026-10-27","isFlagshipForJob":true,"differsFromFloorCheapest":true,"representativeQuote":{"skuId":"anthropic-sonnet-55-input","item":"Sonnet 5.5","plan":"Sonnet 5.5 — standard input; cache read/write on the same card were not folded in","amountUsd":2,"inputOrUnitUsd":2,"unit":"usd_per_million_input_tokens","outputUsd":10,"outputUnit":"usd_per_million_output_tokens","sourceUrl":"https://claude.com/pricing","asOf":"2026-10-27"},"estimatedTaskCost":{"tasks":1000,"retryAndToolOverheadMultiplier":1.15,"retryToolOverheadMultiplier":1.15,"inputTokensPerTask":4000,"outputTokensPerTask":1000,"baseCostPer1kTasksUsd":18,"totalUsd":20.7,"estimatedTotalUsd":20.7,"perTaskUsd":0.0207,"estimatedCostPerTaskUsd":0.0207,"formula":"((4,000 in * $2/1M + 1,000 out * $10/1M) * 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":"anthropic-sonnet-55-input","item":"Sonnet 5.5","plan":"Sonnet 5.5 — standard input; cache read/write on the same card were not folded in","amountUsd":2,"inputOrUnitUsd":2,"unit":"usd_per_million_input_tokens","outputUsd":10,"outputUnit":"usd_per_million_output_tokens","sourceUrl":"https://claude.com/pricing","asOf":"2026-10-27"},"estimatedTaskCost":{"tasks":1000,"retryAndToolOverheadMultiplier":1.15,"retryToolOverheadMultiplier":1.15,"inputTokensPerTask":4000,"outputTokensPerTask":1000,"baseCostPer1kTasksUsd":18,"totalUsd":20.7,"estimatedTotalUsd":20.7,"perTaskUsd":0.0207,"estimatedCostPerTaskUsd":0.0207,"formula":"((4,000 in * $2/1M + 1,000 out * $10/1M) * 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":"prompt-caching-optimization","jtbdName":"Prompt-caching cost optimization","currentPickId":"anthropic","currentPickScore":8,"challengerId":"openai","challengerScore":7.72,"currentScoreGap":0.28,"minVerifiedOutcomes":10,"requiredOutcomeMargin":0.43,"requiredSuccessRateDelta":0.15,"maxPickPriceIncreasePct":25,"whatWouldChangePick":["OpenAI (openai) outperforms Anthropic (anthropic) by >= 0.43 outcome points (or >= 15% worked-rate delta) across >= 10 Countersign-verified production outcomes.","A verified price increase > 25% on Anthropic's representative SKU for prompt-caching-optimization without a corresponding capability gain.","Live caller rail exhaustion (?exhausted=anthropic) 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":"openai","minVerifiedOutcomes":10,"requiredOutcomeMargin":0.43,"requiredWorkedRateDelta":0.15},{"kind":"verified_price_increase","providerId":"anthropic","maxPriceIncreasePct":25},{"kind":"live_rail_exhaustion_or_degradation","providerId":"anthropic","immediateOverrideUrl":"/api/decide?jtbd=prompt-caching-optimization&exhausted=anthropic"}],"submissionSpec":{"falsifyEndpoint":"/api/falsify?jtbd=prompt-caching-optimization","outcomesEndpoint":"POST /api/feedback","correctionsEndpoint":"POST /api/corrections","payloadTemplate":{"agentIdentity":"agent:<your-agent-id>","jtbdId":"prompt-caching-optimization","providerId":"openai","outcome":"worked","detail":"Comparative production evaluation on prompt-caching-optimization (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":["OpenAI (openai) outperforms Anthropic (anthropic) by >= 0.43 outcome points (or >= 15% worked-rate delta) across >= 10 Countersign-verified production outcomes.","A verified price increase > 25% on Anthropic's representative SKU for prompt-caching-optimization without a corresponding capability gain.","Live caller rail exhaustion (?exhausted=anthropic) or sustained >= 30% degraded/failed rate in verified production outcomes."],"routePlan":{"jtbdId":"prompt-caching-optimization","primary":{"providerId":"anthropic","name":"Anthropic","overall":8,"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,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-10-19","role":"primary","reason":"Editorial Depot Pick for Prompt-caching cost optimization; healthy/eligible under caller constraints."},"fallback":[{"providerId":"openai","name":"OpenAI","overall":7.72,"scoreBand":{"low":7.1,"mid":7.7,"high":8.3,"halfWidth":0.6,"basis":"editorial_prior","display":"7.1–8.3 (editorial prior)"},"scoreLayers":{"editorialPrior":7.72,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","role":"fallback","reason":"Ranked fallback route for Prompt-caching cost optimization."},{"providerId":"google-ai","name":"Google AI (Gemini)","overall":8.37,"scoreBand":{"low":7.8,"mid":8.4,"high":9,"halfWidth":0.6,"basis":"editorial_prior","display":"7.8–9.0 (editorial prior)"},"scoreLayers":{"editorialPrior":8.37,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-10-19","role":"fallback","reason":"Ranked fallback route for Prompt-caching cost optimization."},{"providerId":"portkey","name":"Portkey","overall":8.2,"scoreBand":{"low":7.6,"mid":8.2,"high":8.8,"halfWidth":0.6,"basis":"editorial_prior","display":"7.6–8.8 (editorial prior)"},"scoreLayers":{"editorialPrior":8.2,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","role":"fallback","reason":"Ranked fallback route for Prompt-caching cost optimization."},{"providerId":"amazon-bedrock","name":"Amazon Bedrock","overall":7.34,"scoreBand":{"low":6.7,"mid":7.3,"high":7.9,"halfWidth":0.6,"basis":"editorial_prior","display":"6.7–7.9 (editorial prior)"},"scoreLayers":{"editorialPrior":7.34,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","role":"fallback","reason":"Ranked fallback route for Prompt-caching cost optimization."}],"disqualified":[],"expectedRegret":{"scoreDeltaVsUnconstrainedPick":0,"unconstrainedPickId":"anthropic","activePrimaryId":"anthropic","summary":"0.00 score regret: unconstrained editorial pick satisfies all caller constraints."},"evidenceAgeDays":{"editorialScoreAgeDays":9,"pricingVerifiedAgeDays":1,"editorialPriorAsOf":"2026-10-19","pricingLastVerifiedAt":"2026-10-27"},"confidenceBand":{"low":7.4,"mid":8,"high":8.6,"halfWidth":0.6,"basis":"editorial_prior","display":"7.4–8.6 (editorial prior)"},"constraintsApplied":false,"constraintBundle":{"task":null,"jtbd":"prompt-caching-optimization","quotaExhausted":[],"degraded":[],"healthy":[],"budgetUsd":null,"maxLatencyMs":null,"region":null,"privacy":null,"exit":[],"existing":[]}},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-10-19","tie":false,"scoreGap":0.28,"decidingFactor":null,"tieNote":null,"rationale":"pricePerf + DX of cache controls + hit-rate observability. Anthropic prompt caching is the clearest agent-facing story; OpenAI/Gemini close. Confidence: high.","whenNotTopPick":"Workloads are short-prefix high-variance (cache thrash), or gateway-level cache across vendors (Portkey/CF AI Gateway) matters more than first-party cache.","skipTopPick":false,"skipReason":null,"matchedConstraints":[],"pricingSummary":"Sonnet 5 ~$2/$10 per 1M; Opus ~$5/$25; Haiku 4.5 ~$1/$5; Fable higher. Prompt caching + batch. Managed Agents session-hour fees. US-only inference ~1.1x.","cite":"Depot Pick for prompt-caching-optimization: anthropic (asOf 2026-10-19). See GET /api/jtbds/prompt-caching-optimization + GET /api/methodology.","nextActions":[{"step":1,"title":"Inspect full JTBD + embeds","href":"/api/jtbds/prompt-caching-optimization?embed=providers","why":"Confirm pick, runners-up, and methodology notes."},{"step":2,"title":"Quote sourced SKUs","href":"/api/quote?jtbd=prompt-caching-optimization","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/anthropic","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=prompt-caching-optimization","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":"Workloads are short-prefix high-variance (cache thrash), or gateway-level cache across vendors (Portkey/CF AI Gateway) matters more than first-party cache.","source":"editorial `whenNotTopPick` (data/jtbds.json)"},"whenNotToUseReason":null,"runnerUp":{"providerId":"openai","name":"OpenAI","overallForJob":7.72,"pickOverallForJob":8,"beatsPickOn":["latencyReliability","developerDx","maturity"],"source":"first resolvable entry of the job's editorially ranked `runnersUpIds`; scores are stored job-weighted scores"},"runnerUpReason":null,"lockIn":{"pickLockInRisk":6.5,"runnerUpLockInRisk":7.2,"scale":"0–10 stored curated estimate; higher = more lock-in (worse)","pickExitSignals":[],"runnerUpExitSignals":[],"pickNotes":[],"selfHostFallback":[],"migration":"The pick has lower stored lock-in risk than runner-up OpenAI (6.5 vs 7.2).","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 (v0.12.156), Depot Pick for prompt-caching-optimization: anthropic, scores as of 2026-10-19, retrieved 2026-10-28. https://getagentdepot.com/jtbds/prompt-caching-optimization","markdown":"[Agent Provider Depot](https://getagentdepot.com/jtbds/prompt-caching-optimization) (v0.12.156) — Depot Pick for `prompt-caching-optimization`: **anthropic** (scores as of 2026-10-19, retrieved 2026-10-28)","fields":{"publisher":"Agent Provider Depot","version":"0.12.156","role":"depot_pick","jtbdId":"prompt-caching-optimization","providerId":"anthropic","scoreAsOf":"2026-10-19","retrievedOn":"2026-10-28","page":"https://getagentdepot.com/jtbds/prompt-caching-optimization","api":"https://getagentdepot.com/api/decide?jtbd=prompt-caching-optimization"},"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":9,"stale":false,"staleAfterDays":30,"reason":null},"lastReviewed":{"asOf":"2026-10-19","ageDays":9,"stale":false,"staleAfterDays":30,"reason":null},"sourceCheck":{"checkedAt":"2026-10-27","sourceUrls":2,"sourcesReachable":2,"pricingRows":15,"pricingRowsReconfirmed":15,"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","2026-10-19","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":0.1,"rows":[{"id":"anthropic-fable-51-input","providerId":"anthropic","sku":"Fable 5.1","unit":"usd_per_million_input_tokens","amountUsd":10,"currency":"USD","sourceUrl":"https://claude.com/pricing","asOf":"2026-10-27","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":10,"normalizationReason":null,"priceSortEligible":true,"qualifier":"standard input; cache read/write on the same card were not folded in"},{"id":"anthropic-fable-51-output","providerId":"anthropic","sku":"Fable 5.1","unit":"usd_per_million_output_tokens","amountUsd":50,"currency":"USD","sourceUrl":"https://claude.com/pricing","asOf":"2026-10-27","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":50,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"standard output"},{"id":"anthropic-opus-55-input","providerId":"anthropic","sku":"Opus 5.5","unit":"usd_per_million_input_tokens","amountUsd":4,"currency":"USD","sourceUrl":"https://claude.com/pricing","asOf":"2026-10-27","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":4,"normalizationReason":null,"priceSortEligible":true,"qualifier":"standard input; cache read/write on the same card were not folded in"},{"id":"anthropic-opus-55-output","providerId":"anthropic","sku":"Opus 5.5","unit":"usd_per_million_output_tokens","amountUsd":20,"currency":"USD","sourceUrl":"https://claude.com/pricing","asOf":"2026-10-27","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":20,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"standard output"},{"id":"anthropic-sonnet-55-input","providerId":"anthropic","sku":"Sonnet 5.5","unit":"usd_per_million_input_tokens","amountUsd":2,"currency":"USD","sourceUrl":"https://claude.com/pricing","asOf":"2026-10-27","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":2,"normalizationReason":null,"priceSortEligible":true,"qualifier":"standard input; cache read/write on the same card were not folded in"},{"id":"anthropic-sonnet-55-output","providerId":"anthropic","sku":"Sonnet 5.5","unit":"usd_per_million_output_tokens","amountUsd":10,"currency":"USD","sourceUrl":"https://claude.com/pricing","asOf":"2026-10-27","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":10,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"standard output"},{"id":"anthropic-haiku-45-input","providerId":"anthropic","sku":"Haiku 4.5","unit":"usd_per_million_input_tokens","amountUsd":1,"currency":"USD","sourceUrl":"https://claude.com/pricing","asOf":"2026-10-27","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":1,"normalizationReason":null,"priceSortEligible":true,"qualifier":"standard input; cache read/write on the same card were not folded in","lifecycle":"legacy","lifecycleSourceUrl":"https://platform.claude.com/docs/en/about-claude/models/overview","lifecycleAsOf":"2026-10-21"},{"id":"anthropic-haiku-45-output","providerId":"anthropic","sku":"Haiku 4.5","unit":"usd_per_million_output_tokens","amountUsd":5,"currency":"USD","sourceUrl":"https://claude.com/pricing","asOf":"2026-10-27","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":5,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"standard output","lifecycle":"legacy","lifecycleSourceUrl":"https://platform.claude.com/docs/en/about-claude/models/overview","lifecycleAsOf":"2026-10-21"},{"id":"anthropic-web-search","providerId":"anthropic","sku":"Web search","unit":"usd_per_1k_searches","amountUsd":10,"currency":"USD","sourceUrl":"https://claude.com/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_1k_searches","priceSortEligible":false,"qualifier":"page says does not include input and output tokens"},{"id":"anthropic-code-exec-hour","providerId":"anthropic","sku":"Code execution additional hours","unit":"usd_per_hour","amountUsd":0.05,"currency":"USD","sourceUrl":"https://claude.com/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_hour","priceSortEligible":false,"qualifier":"per hour per container"},{"id":"anthropic-managed-agents-session-hour","providerId":"anthropic","sku":"Managed Agents session runtime","unit":"usd_per_session_hour","amountUsd":0.08,"currency":"USD","sourceUrl":"https://claude.com/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_session_hour","priceSortEligible":false,"qualifier":"Managed Agents card ('$0.08 per session-hour for active runtime'; 'Standard token rates apply.'), added 2026-10-27 (v0.12.149) as a reviewed addition. The platform pricing docs table says 'Session runtime $0.08 USD per session-hour', metered on 'running status duration' ('Runtime is measured to the millisecond and accrues only while the session's status is running'). Token usage is billed separately at standard rates and is not included. Not coerced to per-hour, per-container-hour or to $/1M; never blended with anthropic-code-exec-hour."},{"id":"anthropic-haiku-55-input-le-100k","providerId":"anthropic","sku":"Haiku 5.5 (prompts up to 100K tokens)","unit":"usd_per_million_input_tokens","amountUsd":0.1,"currency":"USD","sourceUrl":"https://platform.claude.com/docs/en/about-claude/pricing","asOf":"2026-10-27","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.1,"normalizationReason":null,"priceSortEligible":true,"qualifier":"Base input, prompts up to 100,000 tokens (docs pricing table). Cache write 5m $0.125, cache hit $0.01 not folded in. The claude.com/pricing card agrees as of 2026-10-27 (the 2026-10-21 card/docs mismatch is resolved)."},{"id":"anthropic-haiku-55-output-le-100k","providerId":"anthropic","sku":"Haiku 5.5 (prompts up to 100K tokens)","unit":"usd_per_million_output_tokens","amountUsd":0.5,"currency":"USD","sourceUrl":"https://platform.claude.com/docs/en/about-claude/pricing","asOf":"2026-10-27","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.5,"normalizationReason":null,"priceSortEligible":false,"qualifier":"Output, prompts up to 100,000 tokens (docs pricing table)."},{"id":"anthropic-haiku-55-input-gt-100k","providerId":"anthropic","sku":"Haiku 5.5 (prompts over 100K tokens)","unit":"usd_per_million_input_tokens","amountUsd":0.5,"currency":"USD","sourceUrl":"https://platform.claude.com/docs/en/about-claude/pricing","asOf":"2026-10-27","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.5,"normalizationReason":null,"priceSortEligible":false,"qualifier":"Base input, prompts over 100,000 tokens (whole request priced at this rate, including cache reads/writes in the count). Cache write 5m $0.625, cache hit $0.05 not folded in."},{"id":"anthropic-haiku-55-output-gt-100k","providerId":"anthropic","sku":"Haiku 5.5 (prompts over 100K tokens)","unit":"usd_per_million_output_tokens","amountUsd":2.5,"currency":"USD","sourceUrl":"https://platform.claude.com/docs/en/about-claude/pricing","asOf":"2026-10-27","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":2.5,"normalizationReason":null,"priceSortEligible":false,"qualifier":"Output, prompts over 100,000 tokens."}],"notesExcerpt":"Sonnet 5 ~$2/$10 per 1M; Opus ~$5/$25; Haiku 4.5 ~$1/$5; Fable higher. Prompt caching + batch. Managed Agents session-hour fees. US-only inference ~1.1x.","notesCheck":{"status":"no_known_contradiction","pairs":[],"review":null,"note":null},"lastReviewed":"2026-10-19","scoreAsOf":"2026-10-19","website":"https://www.anthropic.com","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/prompt-caching-optimization","jtbdApi":"/api/jtbds/prompt-caching-optimization","leaderboard":"/api/leaderboards?jtbd=prompt-caching-optimization","methodology":"/api/methodology","badge":"/api/badge?type=depot-pick&jtbd=prompt-caching-optimization","decide":"/api/decide?jtbd=prompt-caching-optimization","humanPage":"/jtbds/prompt-caching-optimization","alternatives":"/api/alternatives?provider=anthropic","canonical":"/api/canonical","quote":"/api/quote?jtbd=prompt-caching-optimization","falsify":"/api/falsify?jtbd=prompt-caching-optimization"},"constraintBundle":{"task":null,"jtbd":"prompt-caching-optimization","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":"anthropic","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=prompt-caching-optimization"},"report":"POST /api/feedback {agentIdentity, outcome: failed|degraded|worked, detail, providerId, jtbdId, failureModeId?, receipt?}"}}