{"jtbd":{"id":"embeddings","slug":"embeddings","name":"Embeddings for RAG","shortName":"Embeddings for RAG","problemStatement":"High-quality embeddings (+ optional rerank) for retrieval pipelines."},"pick":{"id":"cohere","slug":"cohere","name":"Cohere","tagline":"Use for retrieval stacks (embed+rerank), not as your primary agent brain. Quietly excellent at enterprise RAG.","website":"https://cohere.com","overall":7.89,"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":7.89,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-03","editorialPriorAsOf":"2026-10-19","pricingNotes":"Command/Rerank/Embed families; competitive enterprise RAG pricing; private deployment options.","scores":{"capabilityFit":7.8,"pricePerformance":8,"latencyReliability":8.4,"developerDx":7.8,"privacyPosture":8.6,"lockInRisk":4.5,"maturity":8.8,"overall":7.89,"kind":"curated_estimate","confidence":"high","asOf":"2026-10-19"}},"runnersUp":[{"id":"voyage","slug":"voyage","name":"Voyage AI","tagline":"Depot pick for RAG rerank. Keep Cohere as general embeddings default (enterprise + multilingual maturity)…","website":"https://www.voyageai.com","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":"2026-09-14","pricingNotes":"As of 2026-09-14 (docs.voyageai.com/docs/pricing): voyage-4-lite $0.02/1M, voyage-4 $0.06, voyage-4-large / voyage-context-4 / voyage-code-4 $0.12 (200M free tokens on those families). rerank-3 $0.05/1M and rerank-3-lite $0.02/1M (200M free). Batch API 33% off, 12h window; Files storage $0.05/GB-mo. MongoDB-owned; also sold via Atlas automated embedding.","scores":{"capabilityFit":9.2,"pricePerformance":8.8,"latencyReliability":8.4,"developerDx":8.6,"privacyPosture":7.8,"lockInRisk":4.2,"maturity":7.8,"overall":8.37,"kind":"curated_estimate","confidence":"high","asOf":"2026-09-14"}},{"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":8.33,"scoreBand":{"low":7.7,"mid":8.3,"high":8.9,"halfWidth":0.6,"basis":"editorial_prior","display":"7.7–8.9 (editorial prior)"},"scoreLayers":{"editorialPrior":8.33,"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":8.33,"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":8.32,"scoreBand":{"low":7.7,"mid":8.3,"high":8.9,"halfWidth":0.6,"basis":"editorial_prior","display":"7.7–8.9 (editorial prior)"},"scoreLayers":{"editorialPrior":8.32,"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":8.32,"kind":"curated_estimate","confidence":"high","asOf":"2026-10-19"}},{"id":"jina","slug":"jina","name":"Jina AI","tagline":"Promoted high after pinning official models API token matrix ($0.05/1M). Best as EU-friendly all-in-one…","website":"https://jina.ai","overall":8.15,"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":8.15,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-03","editorialPriorAsOf":"2026-09-14","pricingNotes":"As of 2026-10-25 (GET api.jina.ai/v1/models): embeddings/rerank/reader-lm priced at pricing.prompt=0.00000005 → $0.05/1M tokens (jina-embeddings-v3/v4, jina-reranker-v3/v3.5, ReaderLM-v2, clip/colbert). jina-ocr-v1 $0.50/$2.00 per 1M prompt/completion. As of 2026-10-25 (https://jina.ai/embeddings/ FAQ): 'New users get an auto-generated API key with free tokens usable across any of our models.' The page states no free-token amount, so none is given here. Models API is source of record for prices. Same FAQ (2026-10-25): 'jina-embeddings-v4 is built on the Qwen2-VL base model, released under the Qwen Research License, which permits research and non-commercial use only. We therefore cannot license it commercially and provide it free of charge via the API instead.' and 'It is not suitable for production workloads'. The models API still lists jina-ai/jina-embeddings-v4 at pricing.prompt 0.00000005; Depot keeps the models-API figure (not re-priced here).","scores":{"capabilityFit":8.2,"pricePerformance":8.6,"latencyReliability":7.8,"developerDx":8.8,"privacyPosture":8.2,"lockInRisk":3.5,"maturity":7.6,"overall":8.15,"kind":"curated_estimate","confidence":"high","asOf":"2026-09-14"}},{"id":"huggingface-inference","slug":"huggingface-inference","name":"Hugging Face Inference","tagline":"Perfect for Hub-native workflows and custom models. For hard production latency, graduate to…","website":"https://endpoints.huggingface.co","overall":8.02,"scoreBand":{"low":7.4,"mid":8,"high":8.6,"halfWidth":0.6,"basis":"editorial_prior","display":"7.4–8.6 (editorial prior)"},"scoreLayers":{"editorialPrior":8.02,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","pricingNotes":"Inference Providers (pay-as-you-go access to partner inference providers plus Hugging Face's own hf-inference provider) + dedicated Inference Endpoints ('Pay for what you use, per minute' per https://endpoints.huggingface.co, fetched 2026-10-25; instance rates are the price rows: single-GPU x1 rows per GPU-hour, multi-GPU x2/x4/x8 rows per instance-hour (usd_per_instance_hour since v0.12.138, re-checked 2026-10-27 on https://huggingface.co/docs/inference-endpoints/pricing), never divided per GPU). The 'Serverless Inference API' name is retired: https://huggingface.co/docs/inference-providers/pricing (fetched 2026-10-25) says hf-inference 'used to be called “Inference API (serverless)” prior to Inference Providers' and 'just pay for what you use, with no markup from Hugging Face.' Monthly credits: 'Free Users None - yes (credits purchase required)'; PRO users and Team/Enterprise organizations get included monthly credits. Hub-centric. No price changed here; any price change goes through the reviewed --catalog step.","scores":{"capabilityFit":8.4,"pricePerformance":7.2,"latencyReliability":7.4,"developerDx":8.6,"privacyPosture":7.8,"lockInRisk":3.5,"maturity":9.2,"overall":8.02,"kind":"curated_estimate","confidence":"high","asOf":"2026-09-14"}}],"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":7.89,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"whyPickOverHigherScore":{"pickId":"cohere","pickName":"Cohere","pickScore":7.89,"highestScoredCandidateId":"voyage","highestScoredCandidateName":"Voyage AI","highestScore":8.37,"pickHasLowerCompositeScore":true,"delta":-0.48,"pickLeadsOnDimensions":["privacyPosture (8.6 vs 7.8)","maturity (8.8 vs 7.8)"],"explanation":"Cohere (7.89) is the editorial pick for Embeddings for RAG over higher-composite Voyage AI (8.37) because composite scores are provider-wide priors while Cohere wins on privacyPosture (8.6 vs 7.8), maturity (8.8 vs 7.8): Capability for retrieval quality + pricePerf. Cohere remains general default (enterprise + multilingual). Voyage when nDCG/lite $0.02 SKU wins the bake-off; Jina when you also want Reader/rerank in one EU API."},"cheapest":{"providerId":"cloudflare-workers-ai","providerName":"Cloudflare Workers AI","skuId":"cloudflare-workers-ai-cf-baai-bge-m3-in","item":"@cf/baai/bge-m3","plan":"@cf/baai/bge-m3 — Embeddings section","unit":"usd_per_million_input_tokens","amountUsd":0.012,"isFloorPrice":true,"floorWarning":"Provider-wide floor SKU; may not be the flagship model scored for this JTBD.","skuCountInUnit":50,"isDepotPick":false,"sourceUrl":"https://developers.cloudflare.com/workers-ai/platform/pricing/","asOf":"2026-10-03","verifiedAsOf":"2026-10-27"},"recommendedWorkloadQuote":{"providerId":"cohere","providerName":"Cohere","skuId":"cohere-command-light-legacy-input","item":"Command-light (legacy)","plan":"Command-light (legacy) — legacy","unit":"usd_per_million_input_tokens","amountUsd":0.3,"outputSkuId":"cohere-command-light-legacy-output","outputItem":"Command-light (legacy)","outputAmountUsd":0.6,"outputUnit":"usd_per_million_output_tokens","sourceUrl":"https://cohere.com/pricing","asOf":"2026-10-03","pricingLastVerifiedAt":"2026-10-03","isFlagshipForJob":false,"differsFromFloorCheapest":false,"representativeQuote":{"skuId":"cohere-command-light-legacy-input","item":"Command-light (legacy)","plan":"Command-light (legacy) — legacy","amountUsd":0.3,"inputOrUnitUsd":0.3,"unit":"usd_per_million_input_tokens","outputUsd":0.6,"outputUnit":"usd_per_million_output_tokens","sourceUrl":"https://cohere.com/pricing","asOf":"2026-10-03"},"estimatedTaskCost":{"tasks":1000,"retryAndToolOverheadMultiplier":1.15,"retryToolOverheadMultiplier":1.15,"inputTokensPerTask":4000,"outputTokensPerTask":1000,"baseCostPer1kTasksUsd":1.8,"totalUsd":2.07,"estimatedTotalUsd":2.07,"perTaskUsd":0.00207,"estimatedCostPerTaskUsd":0.00207,"formula":"((4,000 in * $0.3/1M + 1,000 out * $0.6/1M) * 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":"cohere-command-light-legacy-input","item":"Command-light (legacy)","plan":"Command-light (legacy) — legacy","amountUsd":0.3,"inputOrUnitUsd":0.3,"unit":"usd_per_million_input_tokens","outputUsd":0.6,"outputUnit":"usd_per_million_output_tokens","sourceUrl":"https://cohere.com/pricing","asOf":"2026-10-03"},"estimatedTaskCost":{"tasks":1000,"retryAndToolOverheadMultiplier":1.15,"retryToolOverheadMultiplier":1.15,"inputTokensPerTask":4000,"outputTokensPerTask":1000,"baseCostPer1kTasksUsd":1.8,"totalUsd":2.07,"estimatedTotalUsd":2.07,"perTaskUsd":0.00207,"estimatedCostPerTaskUsd":0.00207,"formula":"((4,000 in * $0.3/1M + 1,000 out * $0.6/1M) * 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":"bge-m3","name":"BGE-M3","kind":"open_weights","jtbdIds":["embeddings","batch-cheap-embeddings"],"whatYouGet":"Downloadable BAAI BGE-M3 embedding weights.","cost":"oss","license":"MIT","sourceUrl":"https://huggingface.co/BAAI/bge-m3/raw/main/README.md","notes":"Model card front matter fetched 2026-10-03 says license: mit. A separate LICENSE file was 404. README re-fetched twice 2026-10-25 (HTTP 200, byte-identical): front matter 'license: mit'; raw/main/LICENSE still 404 (twice).","providerId":null,"limits":null,"asOf":"2026-10-25","freeType":"open_weights","substitutable":true},{"id":"cloudflare-workers-ai-embeddings","name":"Cloudflare Workers AI embeddings","kind":"free_embedding","providerId":"cloudflare-workers-ai","jtbdIds":["embeddings","batch-cheap-embeddings"],"whatYouGet":"Embedding models on Workers AI, including bge-m3 and qwen3-embedding-0.6b, draw from the same 10,000 neurons/day. No separate free token cap is stated.","cost":"free","limits":{"sharedNeuronsPerDay":10000,"separateTokenCap":null},"sourceUrl":"https://developers.cloudflare.com/workers-ai/platform/pricing/","notes":"Fetched twice 2026-10-25 about 10 s apart without logging in (HTTP 200, no redirect, identical HTML; the page shows 'Last updated Oct 20, 2026'). 'Our free allocation allows anyone to use a total of 10,000 Neurons per day at no charge.' The 'Embeddings model pricing' table lists @cf/baai/bge-small-en-v1.5, bge-base-en-v1.5, bge-large-en-v1.5, bge-m3, @cf/pfnet/plamo-embedding-1b and @cf/qwen/qwen3-embedding-0.6b, e.g. '@cf/baai/bge-m3 $0.012 per M input tokens 1075 neurons per M input tokens'. Those are the paid unit prices billed in neurons above the allocation, not a free token cap; the page states no separate free embedding cap.","license":null,"asOf":"2026-10-25","freeType":"free_embedding","substitutable":true},{"id":"cohere-trial-embed","name":"Cohere trial key, embed","kind":"free_embedding","providerId":"cohere","jtbdIds":["embeddings"],"whatYouGet":"Trial-key Embed rate limits. Still inside the trial key's 1,000 API calls a month.","cost":"free","limits":{"apiCallsPerMonth":1000,"embedInputsPerMinute":2000,"embedImageInputsPerMinute":5,"monthlyCapSharedAcrossTrialKey":true},"sourceUrl":"https://docs.cohere.com/docs/rate-limits","notes":"Page fetched twice 2026-10-25 about 10 s apart without logging in (HTTP 200, no redirect, identical HTML; response header 'last-modified: Fri, 23 Oct 2026 21:27:48 GMT'; the page itself shows no last-updated date). 'Trial keys (and prod keys on newer Chat model variants) are limited to 1,000 API calls a month.' Other API Endpoints table (Trial rate limit, then Production rate limit): 'Embed 2,000 inputs / min 2,000 inputs / min'; 'Embed (Images) 5 inputs / min 400 inputs / min'. The production Embed text limit is the same 2,000 inputs/min; the monthly 1,000-call cap is the trial-key constraint. Not a forever unlimited embed tier. Values unchanged from 2026-10-03.","license":null,"asOf":"2026-10-25","freeType":"free_embedding","substitutable":true},{"id":"gemini-embedding-2-free-tier","name":"Gemini Embedding 2 free tier","kind":"free_embedding","providerId":"google-ai","jtbdIds":["embeddings","batch-cheap-embeddings"],"whatYouGet":"gemini-embedding-2 standard text, image, audio, and video input marked Free of charge.","cost":"free_tier_unspecified","sourceUrl":"https://ai.google.dev/gemini-api/docs/pricing","notes":"Pricing page fetched twice 2026-10-24 (identical text; page footer 'Last updated 2026-10-22 UTC'): gemini-embedding-2 is 'Our first multimodal embedding model, mapping text, images, video, audio, and PDFs into a unified embedding space.' Its Standard Free Tier cells for Text, Image, Audio and Video input price read 'Free of charge'; the Batch free-tier cells read 'Not available'. No numeric free-tier quota is on the pricing page. https://ai.google.dev/gemini-api/docs/rate-limits (fetched twice 2026-10-24, identical text, 'Last updated 2026-10-15 UTC') publishes no free-tier RPM, TPM or RPD and says 'View your active rate limits in AI Studio', so limits stay null. Re-checked 2026-10-26 (v0.12.131): stored quotes still match. https://ai.google.dev/gemini-api/docs/pricing and https://ai.google.dev/gemini-api/docs/rate-limits were each fetched twice (~10 s apart, plain curl, no login, following redirects): HTTP 200, no redirect, HTML differs only inside inline scripts, tag-stripped text identical; both footers now read 'Last updated 2026-10-26 UTC'. Every quote above string-matched the whitespace-normalized text except the older footer stamps, which are fetch-date stamps, not row values; values unchanged (Depot data decision to re-date only, approvalRef 'Ethan delegation 2026-10-21 19:41 ET t55u', decidedBy Agent Depo).","limits":null,"license":null,"asOf":"2026-10-26","freeType":"free_embedding","substitutable":true},{"id":"jina-embeddings-v3-weights","name":"jina-embeddings-v3","kind":"open_weights","jtbdIds":["embeddings"],"whatYouGet":"Downloadable jina-embeddings-v3 weights. The model card license is CC-BY-NC-4.0, which is non-commercial.","cost":"free","license":"CC-BY-NC-4.0","sourceUrl":"https://huggingface.co/jinaai/jina-embeddings-v3/raw/main/README.md","notes":"Model card front matter fetched 2026-10-03 says license: cc-by-nc-4.0. Not Apache and not a commercial grant. README re-fetched twice 2026-10-25 (HTTP 200, byte-identical): front matter 'license: cc-by-nc-4.0'; raw/main/LICENSE 404 (twice).","providerId":null,"limits":null,"asOf":"2026-10-25","freeType":"open_weights","substitutable":true},{"id":"jina-free-embeddings","name":"Jina free API key embeddings","kind":"free_embedding","providerId":"jina","jtbdIds":["embeddings"],"whatYouGet":"Embedding API with a free API key at the free-key rate limit.","cost":"free","limits":{"requestsPerMinute":100,"tokensPerMinute":100000,"ipRequestsPer60Seconds":10000},"sourceUrl":"https://jina.ai/embeddings/","notes":"Page fetched twice 2026-10-25 about 10 s apart without logging in (HTTP 200, no redirect, identical HTML; response header 'last-modified: Thu, 22 Oct 2026 01:48:53 GMT'; the page itself shows no last-updated date). FAQ: 'Rate limits depend on your API key type: Free: 100 RPM, 100K TPM'. Rate table, Embedding API row, w/ Free API Key column: '100 RPM & 100,000 TPM' (the w/o API Key column shows a block icon). FAQ: 'There is an additional IP-based limit of 10,000 requests per 60 seconds to prevent abuse.' FAQ: 'New users get an auto-generated API key with free tokens usable across any of our models.' and 'No, our API keys do not have an expiration date.' The page states no free token amount, so no token balance is stored (a 10 million token grant is not on the page). Paid and Premium columns are not the free tier and were not copied. Values unchanged from 2026-10-03.","license":null,"asOf":"2026-10-25","freeType":"free_embedding","substitutable":true},{"id":"qwen3-embedding-0-6b","name":"Qwen3-Embedding-0.6B","kind":"open_weights","jtbdIds":["embeddings","batch-cheap-embeddings"],"whatYouGet":"Downloadable Qwen3 embedding 0.6B weights.","cost":"oss","license":"Apache-2.0","sourceUrl":"https://huggingface.co/Qwen/Qwen3-Embedding-0.6B/raw/main/README.md","notes":"Model card front matter fetched 2026-10-03 says license: apache-2.0. A separate LICENSE file was 404. README re-fetched twice 2026-10-25 (HTTP 200, byte-identical): front matter 'license: apache-2.0'; raw/main/LICENSE still 404 (twice).","providerId":null,"limits":null,"asOf":"2026-10-25","freeType":"open_weights","substitutable":true}],"referenceDocs":[],"falsification":{"jtbdId":"embeddings","jtbdName":"Embeddings for RAG","currentPickId":"cohere","currentPickScore":7.89,"challengerId":"voyage","challengerScore":8.37,"currentScoreGap":0.48,"minVerifiedOutcomes":10,"requiredOutcomeMargin":0.63,"requiredSuccessRateDelta":0.15,"maxPickPriceIncreasePct":25,"whatWouldChangePick":["Voyage AI (voyage) outperforms Cohere (cohere) by >= 0.63 outcome points (or >= 15% worked-rate delta) across >= 10 Countersign-verified production outcomes.","A verified price increase > 25% on Cohere's representative SKU for embeddings without a corresponding capability gain.","Live caller rail exhaustion (?exhausted=cohere) 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":"voyage","minVerifiedOutcomes":10,"requiredOutcomeMargin":0.63,"requiredWorkedRateDelta":0.15},{"kind":"verified_price_increase","providerId":"cohere","maxPriceIncreasePct":25},{"kind":"live_rail_exhaustion_or_degradation","providerId":"cohere","immediateOverrideUrl":"/api/decide?jtbd=embeddings&exhausted=cohere"}],"submissionSpec":{"falsifyEndpoint":"/api/falsify?jtbd=embeddings","outcomesEndpoint":"POST /api/feedback","correctionsEndpoint":"POST /api/corrections","payloadTemplate":{"agentIdentity":"agent:<your-agent-id>","jtbdId":"embeddings","providerId":"voyage","outcome":"worked","detail":"Comparative production evaluation on embeddings (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":["Voyage AI (voyage) outperforms Cohere (cohere) by >= 0.63 outcome points (or >= 15% worked-rate delta) across >= 10 Countersign-verified production outcomes.","A verified price increase > 25% on Cohere's representative SKU for embeddings without a corresponding capability gain.","Live caller rail exhaustion (?exhausted=cohere) or sustained >= 30% degraded/failed rate in verified production outcomes."],"routePlan":{"jtbdId":"embeddings","primary":{"providerId":"cohere","name":"Cohere","overall":7.89,"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":7.89,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-03","editorialPriorAsOf":"2026-10-19","role":"primary","reason":"Editorial Depot Pick for Embeddings for RAG; healthy/eligible under caller constraints."},"fallback":[{"providerId":"voyage","name":"Voyage AI","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":"2026-09-14","role":"fallback","reason":"Ranked fallback route for Embeddings for RAG."},{"providerId":"openai","name":"OpenAI","overall":8.33,"scoreBand":{"low":7.7,"mid":8.3,"high":8.9,"halfWidth":0.6,"basis":"editorial_prior","display":"7.7–8.9 (editorial prior)"},"scoreLayers":{"editorialPrior":8.33,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","role":"fallback","reason":"Ranked fallback route for Embeddings for RAG."},{"providerId":"google-ai","name":"Google AI (Gemini)","overall":8.32,"scoreBand":{"low":7.7,"mid":8.3,"high":8.9,"halfWidth":0.6,"basis":"editorial_prior","display":"7.7–8.9 (editorial prior)"},"scoreLayers":{"editorialPrior":8.32,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-10-19","role":"fallback","reason":"Ranked fallback route for Embeddings for RAG."},{"providerId":"jina","name":"Jina AI","overall":8.15,"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":8.15,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-03","editorialPriorAsOf":"2026-09-14","role":"fallback","reason":"Ranked fallback route for Embeddings for RAG."},{"providerId":"huggingface-inference","name":"Hugging Face Inference","overall":8.02,"scoreBand":{"low":7.4,"mid":8,"high":8.6,"halfWidth":0.6,"basis":"editorial_prior","display":"7.4–8.6 (editorial prior)"},"scoreLayers":{"editorialPrior":8.02,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","role":"fallback","reason":"Ranked fallback route for Embeddings for RAG."}],"disqualified":[],"expectedRegret":{"scoreDeltaVsUnconstrainedPick":0,"unconstrainedPickId":"cohere","activePrimaryId":"cohere","summary":"0.00 score regret: unconstrained editorial pick satisfies all caller constraints."},"evidenceAgeDays":{"editorialScoreAgeDays":8,"pricingVerifiedAgeDays":24,"editorialPriorAsOf":"2026-10-19","pricingLastVerifiedAt":"2026-10-03"},"confidenceBand":{"low":7.3,"mid":7.9,"high":8.5,"halfWidth":0.6,"basis":"editorial_prior","display":"7.3–8.5 (editorial prior)"},"constraintsApplied":false,"constraintBundle":{"task":null,"jtbd":"embeddings","quotaExhausted":[],"degraded":[],"healthy":[],"budgetUsd":null,"maxLatencyMs":null,"region":null,"privacy":null,"exit":[],"existing":[]}},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-10-19","tie":false,"scoreGap":-0.48,"decidingFactor":null,"tieNote":null,"rationale":"Capability for retrieval quality + pricePerf. Cohere remains general default (enterprise + multilingual). Voyage when nDCG/lite $0.02 SKU wins the bake-off; Jina when you also want Reader/rerank in one EU API.","whenNotTopPick":"Already standardized on OpenAI embeddings operationally; retrieval-quality bake-off winner is Voyage; need local/open embed models on HF/Fireworks; want URL-to-markdown + embeddings together — Jina.","skipTopPick":false,"skipReason":null,"matchedConstraints":[],"pricingSummary":"Command/Rerank/Embed families; competitive enterprise RAG pricing; private deployment options.","cite":"Depot Pick for embeddings: cohere (asOf 2026-10-19). See GET /api/jtbds/embeddings + GET /api/methodology.","nextActions":[{"step":1,"title":"Inspect full JTBD + embeds","href":"/api/jtbds/embeddings?embed=providers","why":"Confirm pick, runners-up, and methodology notes."},{"step":2,"title":"Quote sourced SKUs","href":"/api/quote?jtbd=embeddings","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/cohere","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=embeddings","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":"Already standardized on OpenAI embeddings operationally; retrieval-quality bake-off winner is Voyage; need local/open embed models on HF/Fireworks; want URL-to-markdown + embeddings together — Jina.","source":"editorial `whenNotTopPick` (data/jtbds.json)"},"whenNotToUseReason":null,"runnerUp":{"providerId":"voyage","name":"Voyage AI","overallForJob":8.37,"pickOverallForJob":7.89,"beatsPickOn":["capabilityFit","pricePerformance","developerDx","lockInRisk"],"source":"first resolvable entry of the job's editorially ranked `runnersUpIds`; scores are stored job-weighted scores"},"runnerUpReason":null,"lockIn":{"pickLockInRisk":4.5,"runnerUpLockInRisk":4.2,"scale":"0–10 stored curated estimate; higher = more lock-in (worse)","pickExitSignals":[],"runnerUpExitSignals":[],"pickNotes":[],"selfHostFallback":[{"id":"bge-m3","name":"BGE-M3","license":"MIT","sourceUrl":"https://huggingface.co/BAAI/bge-m3/raw/main/README.md"},{"id":"qwen3-embedding-0-6b","name":"Qwen3-Embedding-0.6B","license":"Apache-2.0","sourceUrl":"https://huggingface.co/Qwen/Qwen3-Embedding-0.6B/raw/main/README.md"},{"id":"jina-embeddings-v3-weights","name":"jina-embeddings-v3","license":"CC-BY-NC-4.0","sourceUrl":"https://huggingface.co/jinaai/jina-embeddings-v3/raw/main/README.md"}],"migration":"Runner-up Voyage AI has lower stored lock-in risk (4.2 vs 4.5, 0–10, higher = more lock-in). Self-host fallback listed for this job: BGE-M3, Qwen3-Embedding-0.6B, jina-embeddings-v3.","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 (v0.12.148), Depot Pick for embeddings: cohere, scores as of 2026-10-19, retrieved 2026-10-27. https://getagentdepot.com/jtbds/embeddings","markdown":"[Agent Provider Depot](https://getagentdepot.com/jtbds/embeddings) (v0.12.148) — Depot Pick for `embeddings`: **cohere** (scores as of 2026-10-19, retrieved 2026-10-27)","fields":{"publisher":"Agent Provider Depot","version":"0.12.148","role":"depot_pick","jtbdId":"embeddings","providerId":"cohere","scoreAsOf":"2026-10-19","retrievedOn":"2026-10-27","page":"https://getagentdepot.com/jtbds/embeddings","api":"https://getagentdepot.com/api/decide?jtbd=embeddings"},"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":4,"pricingRowsReconfirmed":0,"note":"A source re-check confirms the page is reachable and, for pricing rows, that the stored amount and SKU name appear on it. It does not re-derive or change the score.","reason":null}},"scoreAsOf":"2026-10-19","editorialPriorAsOf":"2026-10-19","pricingLastVerifiedAt":"2026-10-27","pickLastReviewed":"2026-10-19","runnersUpScoreAsOf":["2026-09-14","2026-09-14","2026-10-19","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":false,"priceSortKeyUsdPerMillionInputTokens":null,"rows":[{"id":"cohere-command-legacy-input","providerId":"cohere","sku":"Command (legacy)","unit":"usd_per_million_input_tokens","amountUsd":1,"currency":"USD","sourceUrl":"https://cohere.com/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":1,"normalizationReason":"legacy_sku_not_current_matrix","priceSortEligible":false,"qualifier":"Page section: pricing for legacy models, for existing customers. Current Embed/Command matrix was not on the extracted page."},{"id":"cohere-command-legacy-output","providerId":"cohere","sku":"Command (legacy)","unit":"usd_per_million_output_tokens","amountUsd":2,"currency":"USD","sourceUrl":"https://cohere.com/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":2,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"legacy"},{"id":"cohere-command-light-legacy-input","providerId":"cohere","sku":"Command-light (legacy)","unit":"usd_per_million_input_tokens","amountUsd":0.3,"currency":"USD","sourceUrl":"https://cohere.com/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.3,"normalizationReason":"legacy_sku_not_current_matrix","priceSortEligible":false,"qualifier":"legacy"},{"id":"cohere-command-light-legacy-output","providerId":"cohere","sku":"Command-light (legacy)","unit":"usd_per_million_output_tokens","amountUsd":0.6,"currency":"USD","sourceUrl":"https://cohere.com/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.6,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"legacy"}],"notesExcerpt":"Command/Rerank/Embed families; competitive enterprise RAG pricing; private deployment options.","notesCheck":{"status":"no_known_contradiction","pairs":[],"review":null,"note":null},"lastReviewed":"2026-10-19","scoreAsOf":"2026-10-19","website":"https://cohere.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/embeddings","jtbdApi":"/api/jtbds/embeddings","leaderboard":"/api/leaderboards?jtbd=embeddings","methodology":"/api/methodology","badge":"/api/badge?type=depot-pick&jtbd=embeddings","decide":"/api/decide?jtbd=embeddings","humanPage":"/jtbds/embeddings","alternatives":"/api/alternatives?provider=cohere","canonical":"/api/canonical","quote":"/api/quote?jtbd=embeddings","falsify":"/api/falsify?jtbd=embeddings"},"constraintBundle":{"task":null,"jtbd":"embeddings","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":"cohere","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=embeddings"},"report":"POST /api/feedback {agentIdentity, outcome: failed|degraded|worked, detail, providerId, jtbdId, failureModeId?, receipt?}"}}