{"jtbd":{"id":"multimodal","slug":"multimodal","name":"Multimodal understanding (vision+)","shortName":"Multimodal understanding (vision+)","problemStatement":"Agents must reason over images/video/audio inputs at scale."},"pick":{"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":8.43,"scoreBand":{"low":7.8,"mid":8.4,"high":9,"halfWidth":0.6,"basis":"editorial_prior","display":"7.8–9.0 (editorial prior)"},"scoreLayers":{"editorialPrior":8.43,"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":8.43,"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":8.22,"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":8.22,"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":8.22,"kind":"curated_estimate","confidence":"high","asOf":"2026-09-14"}},{"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":8.42,"scoreBand":{"low":7.8,"mid":8.4,"high":9,"halfWidth":0.6,"basis":"editorial_prior","display":"7.8–9.0 (editorial prior)"},"scoreLayers":{"editorialPrior":8.42,"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":8.42,"kind":"curated_estimate","confidence":"high","asOf":"2026-10-19"}},{"id":"minimax","slug":"minimax","name":"MiniMax","tagline":"Primary indie-usable Chinese multimodal API alongside Moonshot. Prefer Anthropic/OpenAI for coding agents…","website":"https://www.minimax.io","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":"2026-09-14","pricingNotes":"As of 2026-09-14 (platform.minimax.io/docs/guides/pricing-paygo): International api.minimax.io (OpenAI + Anthropic-compat). MiniMax-M3 ≤512k: list $0.60/$2.40 → permanent 50% off $0.30/$1.20 per 1M (cache read $0.06); >512k $0.60/$2.40 after promo. Priority tier 1.5×. M2.7 $0.30/$1.20 (highspeed $0.60/$2.40). TTS speech-2.8-turbo $60/M chars, hd $100/M. ASR $0.38/hr. Video H3 768P $0.08/s / 2K $0.13/s. image-01 $0.0035. Token Plan (Plus/Max/Ultra) is closed to new purchases; its figure was removed. It is replaced by M Plan, listed at platform.minimax.io/docs/m-plan/monthly-offer as of 2026-10-21 at regular prices of Go $22/month, Explore $55/month and Build $132/month (first month 50% off; not stored as rows). Mainland keys use api.minimaxi.com — not interchangeable.","scores":{"capabilityFit":8.4,"pricePerformance":8.8,"latencyReliability":7.8,"developerDx":8.2,"privacyPosture":6.2,"lockInRisk":4.8,"maturity":7.6,"overall":7.83,"kind":"curated_estimate","confidence":"high","asOf":"2026-09-14"}},{"id":"dashscope","slug":"dashscope","name":"Alibaba Cloud Model Studio (DashScope)","tagline":"Catalog dashscope for Alibaba Model Studio / DashScope international Qwen. Complements Moonshot/MiniMax/Z.AI…","website":"https://www.alibabacloud.com/help/en/model-studio/","overall":7.86,"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":7.86,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","pricingNotes":"As of 2026-09-14 (alibabacloud.com/help/en/model-studio/model-pricing International): Qwen3.8-Max $2/$6 per 1M; Qwen3.7-Max $2.5/$7.5 (limited-time 50% off on some SKUs); Qwen3-Max $1.2/$6 (≤32k) tiering up at longer contexts; Qwen-Plus class ~$0.40/$1.20–$1.60. Batch often 50% off. Singapore free quotas (~1M tokens/90d) on many models. Intl endpoint dashscope-intl.aliyuncs.com; regional MaaS hosts for CN/EU/US/JP. Coding/Token Plans available in Singapore.","scores":{"capabilityFit":8.6,"pricePerformance":8.2,"latencyReliability":8.4,"developerDx":7.2,"privacyPosture":7,"lockInRisk":5.5,"maturity":8.8,"overall":7.86,"kind":"curated_estimate","confidence":"high","asOf":"2026-09-14"}},{"id":"zai","slug":"zai","name":"Z.AI (Zhipu GLM)","tagline":"International GLM via z.ai — catalog zai, not a second Zhipu mainland-only SKU. Strong cheap/coding runner…","website":"https://z.ai","overall":7.79,"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":7.79,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","pricingNotes":"As of 2026-09-14 (docs.z.ai/guides/overview/pricing): International OpenAI-compat api.z.ai. GLM-5.3 / 5.2 / 5.1 $1.40 in / $0.26 cached / $4.40 out per 1M; GLM-5 input $1, cached $0.20, output $3.20; GLM-4.7 input $0.60, cached $0.11, output $2.20; GLM-4.7-FlashX input $0.07, cached $0.01, output $0.40 (all per 1M, matching stored rows; re-checked on docs.z.ai/guides/overview/pricing 2026-10-21); GLM-4.7-Flash and GLM-4.5-Flash free. Vision GLM-4.6V $0.30/$0.90; GLM-OCR $0.03; GLM-Image $0.015/img; CogVideoX-3 $0.20/video; GLM-ASR-2512 $0.03/MTok (~$0.0024/min). Web Search tool $0.01/use. Cached-input storage limited-time free.","scores":{"capabilityFit":8.2,"pricePerformance":9,"latencyReliability":7.6,"developerDx":8,"privacyPosture":6,"lockInRisk":4.6,"maturity":8,"overall":7.79,"kind":"curated_estimate","confidence":"high","asOf":"2026-09-14"}}],"scoreBand":{"low":7.8,"mid":8.4,"high":9,"halfWidth":0.6,"basis":"editorial_prior","display":"7.8–9.0 (editorial prior)"},"scoreLayers":{"editorialPrior":8.43,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"whyPickOverHigherScore":{"pickId":"google-ai","pickName":"Google AI (Gemini)","pickScore":8.43,"highestScoredCandidateId":"google-ai","highestScoredCandidateName":"Google AI (Gemini)","highestScore":8.43,"pickHasLowerCompositeScore":false,"delta":0,"pickLeadsOnDimensions":[],"explanation":"Google AI (Gemini) (8.43) holds both the highest composite score among ranked candidates and the editorial pick for Multimodal understanding (vision+): capability multimodal + pricePerf. Gemini often wins value; OpenAI strong ecosystem."},"cheapest":{"providerId":"zai","providerName":"Z.AI (Zhipu GLM)","skuId":"zai-glm-4-6v-flashx-in","item":"GLM-4.6V-FlashX","plan":"GLM-4.6V-FlashX — Prices per 1M tokens","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":18,"isDepotPick":false,"sourceUrl":"https://docs.z.ai/guides/overview/pricing","asOf":"2026-10-03","verifiedAsOf":"2026-10-27"},"recommendedWorkloadQuote":{"providerId":"google-ai","providerName":"Google AI (Gemini)","skuId":"google-gemini-3-flash-input-text","item":"gemini-3-flash-preview","plan":"gemini-3-flash-preview — text/image/video input","unit":"usd_per_million_input_tokens","amountUsd":0.5,"outputSkuId":"google-gemini-3-flash-output","outputItem":"gemini-3-flash-preview","outputAmountUsd":3,"outputUnit":"usd_per_million_output_tokens","sourceUrl":"https://ai.google.dev/gemini-api/docs/pricing","asOf":"2026-10-03","pricingLastVerifiedAt":"2026-10-03","isFlagshipForJob":true,"differsFromFloorCheapest":true,"representativeQuote":{"skuId":"google-gemini-3-flash-input-text","item":"gemini-3-flash-preview","plan":"gemini-3-flash-preview — text/image/video input","amountUsd":0.5,"inputOrUnitUsd":0.5,"unit":"usd_per_million_input_tokens","outputUsd":3,"outputUnit":"usd_per_million_output_tokens","sourceUrl":"https://ai.google.dev/gemini-api/docs/pricing","asOf":"2026-10-03"},"estimatedTaskCost":{"tasks":1000,"retryAndToolOverheadMultiplier":1.15,"retryToolOverheadMultiplier":1.15,"inputTokensPerTask":4000,"outputTokensPerTask":1000,"baseCostPer1kTasksUsd":5,"totalUsd":5.75,"estimatedTotalUsd":5.75,"perTaskUsd":0.00575,"estimatedCostPerTaskUsd":0.00575,"formula":"((4,000 in * $0.5/1M + 1,000 out * $3/1M) * 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":"google-gemini-3-flash-input-text","item":"gemini-3-flash-preview","plan":"gemini-3-flash-preview — text/image/video input","amountUsd":0.5,"inputOrUnitUsd":0.5,"unit":"usd_per_million_input_tokens","outputUsd":3,"outputUnit":"usd_per_million_output_tokens","sourceUrl":"https://ai.google.dev/gemini-api/docs/pricing","asOf":"2026-10-03"},"estimatedTaskCost":{"tasks":1000,"retryAndToolOverheadMultiplier":1.15,"retryToolOverheadMultiplier":1.15,"inputTokensPerTask":4000,"outputTokensPerTask":1000,"baseCostPer1kTasksUsd":5,"totalUsd":5.75,"estimatedTotalUsd":5.75,"perTaskUsd":0.00575,"estimatedCostPerTaskUsd":0.00575,"formula":"((4,000 in * $0.5/1M + 1,000 out * $3/1M) * 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":[{"id":"florence-2-base","name":"Florence-2-base","kind":"open_weights","jtbdIds":["layout-aware-ocr","document-parse","multimodal"],"whatYouGet":"Downloadable Microsoft Florence-2-base weights for vision and OCR-style tasks.","cost":"oss","license":"MIT","sourceUrl":"https://huggingface.co/microsoft/Florence-2-base/raw/main/LICENSE","notes":"LICENSE file fetched 2026-10-03 is the MIT License. LICENSE re-fetched twice 2026-10-25 (HTTP 200, byte-identical): 'MIT License'.","providerId":null,"limits":null,"asOf":"2026-10-25","freeType":"open_weights","substitutable":true},{"id":"qwen2-5-vl-7b-instruct","name":"Qwen2.5-VL-7B-Instruct","kind":"open_weights","jtbdIds":["multimodal","open-model-inference"],"whatYouGet":"Downloadable Qwen2.5-VL 7B Instruct weights for image-text tasks.","cost":"oss","license":"Apache-2.0","sourceUrl":"https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct/raw/main/README.md","notes":"Model card front matter fetched 2026-10-03 says license: apache-2.0. The 3B checkpoint uses a different Qwen Research LICENSE and is not this row. README re-fetched twice 2026-10-25 (HTTP 200, byte-identical): front matter 'license: apache-2.0'; raw/main/LICENSE 404 (twice). The 3B README fetched the same day says 'license_name: qwen-research'.","providerId":null,"limits":null,"asOf":"2026-10-25","freeType":"open_weights","substitutable":true},{"id":"visualwebarena","name":"VisualWebArena","kind":"free_data","jtbdIds":["evals","web-agent","multimodal"],"whatYouGet":"Public VisualWebArena benchmark, a multimodal successor to WebArena.","cost":"oss","license":"MIT","sourceUrl":"https://raw.githubusercontent.com/web-arena-x/visualwebarena/main/LICENSE","notes":"LICENSE fetched 2026-10-03 begins with a free-of-charge permission grant (MIT). Copyright 2024 Jing Yu Koh, Robert Lo, Lawrence Jang, Vikram Duvvur, Ming Chong Lim, and Po-Yu Huang. LICENSE re-fetched twice 2026-10-25 (HTTP 200, byte-identical): 'Copyright (c) 2024 Jing Yu Koh, Robert Lo, Lawrence Jang, Vikram Duvvur, Ming Chong Lim, and Po-Yu Huang' / 'Permission is hereby granted, free of charge'.","providerId":null,"limits":null,"asOf":"2026-10-25","freeType":"free_data","substitutable":true}],"referenceDocs":[],"falsification":{"jtbdId":"multimodal","jtbdName":"Multimodal understanding (vision+)","currentPickId":"google-ai","currentPickScore":8.43,"challengerId":"openai","challengerScore":8.22,"currentScoreGap":0.21,"minVerifiedOutcomes":10,"requiredOutcomeMargin":0.36,"requiredSuccessRateDelta":0.15,"maxPickPriceIncreasePct":25,"whatWouldChangePick":["OpenAI (openai) outperforms Google AI (Gemini) (google-ai) by >= 0.36 outcome points (or >= 15% worked-rate delta) across >= 10 Countersign-verified production outcomes.","A verified price increase > 25% on Google AI (Gemini)'s representative SKU for multimodal without a corresponding capability gain.","Live caller rail exhaustion (?exhausted=google-ai) 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":0.36,"requiredWorkedRateDelta":0.15},{"kind":"verified_price_increase","providerId":"google-ai","maxPriceIncreasePct":25},{"kind":"live_rail_exhaustion_or_degradation","providerId":"google-ai","immediateOverrideUrl":"/api/decide?jtbd=multimodal&exhausted=google-ai"}],"submissionSpec":{"falsifyEndpoint":"/api/falsify?jtbd=multimodal","outcomesEndpoint":"POST /api/feedback","correctionsEndpoint":"POST /api/corrections","payloadTemplate":{"agentIdentity":"agent:<your-agent-id>","jtbdId":"multimodal","providerId":"openai","outcome":"worked","detail":"Comparative production evaluation on multimodal (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 Google AI (Gemini) (google-ai) by >= 0.36 outcome points (or >= 15% worked-rate delta) across >= 10 Countersign-verified production outcomes.","A verified price increase > 25% on Google AI (Gemini)'s representative SKU for multimodal without a corresponding capability gain.","Live caller rail exhaustion (?exhausted=google-ai) or sustained >= 30% degraded/failed rate in verified production outcomes."],"routePlan":{"jtbdId":"multimodal","primary":{"providerId":"google-ai","name":"Google AI (Gemini)","overall":8.43,"scoreBand":{"low":7.8,"mid":8.4,"high":9,"halfWidth":0.6,"basis":"editorial_prior","display":"7.8–9.0 (editorial prior)"},"scoreLayers":{"editorialPrior":8.43,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-10-19","role":"primary","reason":"Editorial Depot Pick for Multimodal understanding (vision+); healthy/eligible under caller constraints."},"fallback":[{"providerId":"openai","name":"OpenAI","overall":8.22,"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":8.22,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","role":"fallback","reason":"Ranked fallback route for Multimodal understanding (vision+)."},{"providerId":"anthropic","name":"Anthropic","overall":8.42,"scoreBand":{"low":7.8,"mid":8.4,"high":9,"halfWidth":0.6,"basis":"editorial_prior","display":"7.8–9.0 (editorial prior)"},"scoreLayers":{"editorialPrior":8.42,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-10-19","role":"fallback","reason":"Ranked fallback route for Multimodal understanding (vision+)."},{"providerId":"minimax","name":"MiniMax","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":"2026-09-14","role":"fallback","reason":"Ranked fallback route for Multimodal understanding (vision+)."},{"providerId":"dashscope","name":"Alibaba Cloud Model Studio (DashScope)","overall":7.86,"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":7.86,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","role":"fallback","reason":"Ranked fallback route for Multimodal understanding (vision+)."},{"providerId":"zai","name":"Z.AI (Zhipu GLM)","overall":7.79,"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":7.79,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","role":"fallback","reason":"Ranked fallback route for Multimodal understanding (vision+)."}],"disqualified":[],"expectedRegret":{"scoreDeltaVsUnconstrainedPick":0,"unconstrainedPickId":"google-ai","activePrimaryId":"google-ai","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":7.8,"mid":8.4,"high":9,"halfWidth":0.6,"basis":"editorial_prior","display":"7.8–9.0 (editorial prior)"},"constraintsApplied":false,"constraintBundle":{"task":null,"jtbd":"multimodal","quotaExhausted":[],"degraded":[],"healthy":[],"budgetUsd":null,"maxLatencyMs":null,"region":null,"privacy":null,"exit":[],"existing":[]}},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-10-19","tie":false,"scoreGap":0.21,"decidingFactor":null,"tieNote":null,"rationale":"capability multimodal + pricePerf. Gemini often wins value; OpenAI strong ecosystem.","whenNotTopPick":"Text-only coding agents — Anthropic; or OpenAI Realtime voice stacks.","skipTopPick":false,"skipReason":null,"matchedConstraints":[],"pricingSummary":"Gemini 3.x Pro often ~$2/$12 under 200K; Flash tiers much cheaper. 1M context. Vertex for enterprise. Batch half-price common.","cite":"Depot Pick for multimodal: google-ai (asOf 2026-10-19). See GET /api/jtbds/multimodal + GET /api/methodology.","nextActions":[{"step":1,"title":"Inspect full JTBD + embeds","href":"/api/jtbds/multimodal?embed=providers","why":"Confirm pick, runners-up, and methodology notes."},{"step":2,"title":"Quote sourced SKUs","href":"/api/quote?jtbd=multimodal","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/google-ai","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=multimodal","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":"Text-only coding agents — Anthropic; or OpenAI Realtime voice stacks.","source":"editorial `whenNotTopPick` (data/jtbds.json)"},"whenNotToUseReason":null,"runnerUp":{"providerId":"openai","name":"OpenAI","overallForJob":8.22,"pickOverallForJob":8.43,"beatsPickOn":["capabilityFit","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,"runnerUpLockInRisk":7.2,"scale":"0–10 stored curated estimate; higher = more lock-in (worse)","pickExitSignals":[],"runnerUpExitSignals":[],"pickNotes":[],"selfHostFallback":[{"id":"qwen2-5-vl-7b-instruct","name":"Qwen2.5-VL-7B-Instruct","license":"Apache-2.0","sourceUrl":"https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct/raw/main/README.md"},{"id":"florence-2-base","name":"Florence-2-base","license":"MIT","sourceUrl":"https://huggingface.co/microsoft/Florence-2-base/raw/main/LICENSE"},{"id":"visualwebarena","name":"VisualWebArena","license":"MIT","sourceUrl":"https://raw.githubusercontent.com/web-arena-x/visualwebarena/main/LICENSE"}],"migration":"The pick has lower stored lock-in risk than runner-up OpenAI (6 vs 7.2). Self-host fallback listed for this job: Qwen2.5-VL-7B-Instruct, Florence-2-base, VisualWebArena.","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 (v0.12.154), Depot Pick for multimodal: google-ai, scores as of 2026-10-19, retrieved 2026-10-27. https://getagentdepot.com/jtbds/multimodal","markdown":"[Agent Provider Depot](https://getagentdepot.com/jtbds/multimodal) (v0.12.154) — Depot Pick for `multimodal`: **google-ai** (scores as of 2026-10-19, retrieved 2026-10-27)","fields":{"publisher":"Agent Provider Depot","version":"0.12.154","role":"depot_pick","jtbdId":"multimodal","providerId":"google-ai","scoreAsOf":"2026-10-19","retrievedOn":"2026-10-27","page":"https://getagentdepot.com/jtbds/multimodal","api":"https://getagentdepot.com/api/decide?jtbd=multimodal"},"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":2,"sourcesReachable":2,"pricingRows":19,"pricingRowsReconfirmed":3,"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","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":0.3,"rows":[{"id":"google-gemini-38-flash-input-through-2026-12-31","providerId":"google-ai","sku":"gemini-3.8-flash","unit":"usd_per_million_input_tokens","amountUsd":0.75,"currency":"USD","sourceUrl":"https://ai.google.dev/gemini-api/docs/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.75,"normalizationReason":null,"priceSortEligible":true,"qualifier":"Paid tier standard. Page also lists $1.50 starting 2027-01-01. Sort uses the through-2026-12-31 figure only.","promo":{"label":"Introductory price through 2026-12-31 (page lists the 2027 price alongside)","endsOn":"2026-12-31","listAmountUsd":1.5}},{"id":"google-gemini-38-flash-input-from-2027-01-01","providerId":"google-ai","sku":"gemini-3.8-flash","unit":"usd_per_million_input_tokens","amountUsd":1.5,"currency":"USD","sourceUrl":"https://ai.google.dev/gemini-api/docs/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":1.5,"normalizationReason":"scheduled_rate_not_yet_effective","priceSortEligible":false,"qualifier":"starting January 1, 2027"},{"id":"google-gemini-38-flash-output-through-2026-12-31","providerId":"google-ai","sku":"gemini-3.8-flash","unit":"usd_per_million_output_tokens","amountUsd":3.75,"currency":"USD","sourceUrl":"https://ai.google.dev/gemini-api/docs/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":3.75,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"including thinking tokens; through 2026-12-31","promo":{"label":"Introductory price through 2026-12-31 (page lists the 2027 price alongside)","endsOn":"2026-12-31","listAmountUsd":7.5}},{"id":"google-gemini-38-flash-output-from-2027-01-01","providerId":"google-ai","sku":"gemini-3.8-flash","unit":"usd_per_million_output_tokens","amountUsd":7.5,"currency":"USD","sourceUrl":"https://ai.google.dev/gemini-api/docs/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":7.5,"normalizationReason":"scheduled_rate_not_yet_effective","priceSortEligible":false,"qualifier":"starting January 1, 2027"},{"id":"google-gemini-31-pro-input-le-200k","providerId":"google-ai","sku":"gemini-3.1-pro-preview","unit":"usd_per_million_input_tokens","amountUsd":2,"currency":"USD","sourceUrl":"https://ai.google.dev/gemini-api/docs/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":2,"normalizationReason":null,"priceSortEligible":true,"qualifier":"Paid tier standard, prompts <= 200k tokens. >200k is $4.00 and is not the sort key."},{"id":"google-gemini-31-pro-input-gt-200k","providerId":"google-ai","sku":"gemini-3.1-pro-preview","unit":"usd_per_million_input_tokens","amountUsd":4,"currency":"USD","sourceUrl":"https://ai.google.dev/gemini-api/docs/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":4,"normalizationReason":"context_tier_not_a_single_rate","priceSortEligible":false,"qualifier":"prompts > 200k tokens"},{"id":"google-gemini-31-pro-output-le-200k","providerId":"google-ai","sku":"gemini-3.1-pro-preview","unit":"usd_per_million_output_tokens","amountUsd":12,"currency":"USD","sourceUrl":"https://ai.google.dev/gemini-api/docs/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":12,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"prompts <= 200k; includes thinking tokens"},{"id":"google-gemini-31-pro-output-gt-200k","providerId":"google-ai","sku":"gemini-3.1-pro-preview","unit":"usd_per_million_output_tokens","amountUsd":18,"currency":"USD","sourceUrl":"https://ai.google.dev/gemini-api/docs/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":18,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"prompts > 200k"},{"id":"google-gemini-3-flash-input-text","providerId":"google-ai","sku":"gemini-3-flash-preview","unit":"usd_per_million_input_tokens","amountUsd":0.5,"currency":"USD","sourceUrl":"https://ai.google.dev/gemini-api/docs/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.5,"normalizationReason":null,"priceSortEligible":true,"qualifier":"text/image/video input. Audio input is $1.00 and was not blended."},{"id":"google-gemini-3-flash-input-audio","providerId":"google-ai","sku":"gemini-3-flash-preview","unit":"usd_per_million_input_tokens","amountUsd":1,"currency":"USD","sourceUrl":"https://ai.google.dev/gemini-api/docs/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":1,"normalizationReason":"modality_split_not_blended","priceSortEligible":false,"qualifier":"audio input"},{"id":"google-gemini-3-flash-output","providerId":"google-ai","sku":"gemini-3-flash-preview","unit":"usd_per_million_output_tokens","amountUsd":3,"currency":"USD","sourceUrl":"https://ai.google.dev/gemini-api/docs/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":3,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"output including thinking tokens"},{"id":"google-gemini-25-pro-input-le-200k","providerId":"google-ai","sku":"gemini-2.5-pro","unit":"usd_per_million_input_tokens","amountUsd":1.25,"currency":"USD","sourceUrl":"https://ai.google.dev/gemini-api/docs/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":1.25,"normalizationReason":null,"priceSortEligible":true,"qualifier":"prompts <= 200k. >200k is $2.50"},{"id":"google-gemini-25-pro-input-gt-200k","providerId":"google-ai","sku":"gemini-2.5-pro","unit":"usd_per_million_input_tokens","amountUsd":2.5,"currency":"USD","sourceUrl":"https://ai.google.dev/gemini-api/docs/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":2.5,"normalizationReason":"context_tier_not_a_single_rate","priceSortEligible":false,"qualifier":"prompts > 200k"},{"id":"google-gemini-25-pro-output-le-200k","providerId":"google-ai","sku":"gemini-2.5-pro","unit":"usd_per_million_output_tokens","amountUsd":10,"currency":"USD","sourceUrl":"https://ai.google.dev/gemini-api/docs/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":10,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"prompts <= 200k"},{"id":"google-gemini-25-pro-output-gt-200k","providerId":"google-ai","sku":"gemini-2.5-pro","unit":"usd_per_million_output_tokens","amountUsd":15,"currency":"USD","sourceUrl":"https://ai.google.dev/gemini-api/docs/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":15,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"prompts > 200k"},{"id":"google-gemini-35-flash-lite-input","providerId":"google-ai","sku":"gemini-3.5-flash-lite","unit":"usd_per_million_input_tokens","amountUsd":0.3,"currency":"USD","sourceUrl":"https://ai.google.dev/gemini-api/docs/pricing","asOf":"2026-10-21","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.3,"normalizationReason":null,"priceSortEligible":true,"qualifier":"Standard tier, paid, text/image/video/audio input."},{"id":"google-gemini-35-flash-lite-output","providerId":"google-ai","sku":"gemini-3.5-flash-lite","unit":"usd_per_million_output_tokens","amountUsd":2.5,"currency":"USD","sourceUrl":"https://ai.google.dev/gemini-api/docs/pricing","asOf":"2026-10-21","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":2.5,"normalizationReason":null,"priceSortEligible":false,"qualifier":"Standard tier, paid, output including thinking tokens."},{"id":"google-gemini-35-flash-lite-batch-input","providerId":"google-ai","sku":"gemini-3.5-flash-lite (Batch)","unit":"usd_per_million_input_tokens","amountUsd":0.15,"currency":"USD","sourceUrl":"https://ai.google.dev/gemini-api/docs/pricing","asOf":"2026-10-21","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.15,"normalizationReason":null,"priceSortEligible":false,"qualifier":"Batch tier (asynchronous), paid input. Not sorted against standard on-demand rows."},{"id":"google-gemini-35-flash-lite-batch-output","providerId":"google-ai","sku":"gemini-3.5-flash-lite (Batch)","unit":"usd_per_million_output_tokens","amountUsd":1.25,"currency":"USD","sourceUrl":"https://ai.google.dev/gemini-api/docs/pricing","asOf":"2026-10-21","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":1.25,"normalizationReason":null,"priceSortEligible":false,"qualifier":"Batch tier, paid output."}],"notesExcerpt":"Gemini 3.x Pro often ~$2/$12 under 200K; Flash tiers much cheaper. 1M context. Vertex for enterprise. Batch half-price common.","notesCheck":{"status":"no_known_contradiction","pairs":[],"review":null,"note":null},"lastReviewed":"2026-10-19","scoreAsOf":"2026-10-19","website":"https://ai.google.dev","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/multimodal","jtbdApi":"/api/jtbds/multimodal","leaderboard":"/api/leaderboards?jtbd=multimodal","methodology":"/api/methodology","badge":"/api/badge?type=depot-pick&jtbd=multimodal","decide":"/api/decide?jtbd=multimodal","humanPage":"/jtbds/multimodal","alternatives":"/api/alternatives?provider=google-ai","canonical":"/api/canonical","quote":"/api/quote?jtbd=multimodal","falsify":"/api/falsify?jtbd=multimodal"},"constraintBundle":{"task":null,"jtbd":"multimodal","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":"google-ai","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=multimodal"},"report":"POST /api/feedback {agentIdentity, outcome: failed|degraded|worked, detail, providerId, jtbdId, failureModeId?, receipt?}"}}