{"subject":{"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","status":"active","overall":8.4,"scoreKind":"curated_estimate","confidence":"high","scoreAsOf":"2026-09-14","lastReviewed":"2026-09-14","categoryIds":["cat-inference-apis","cat-vector-memory"],"regions":["global","us"],"pricing":{"normalizedUsdPerMillionTokens":null,"normalizationStatus":"ambiguous","normalizationReason":"multiple_sourced_token_skus","shape":"sourced_rows","filterable":false,"priceSortEligible":true,"priceSortKeyUsdPerMillionInputTokens":0.02,"rows":[{"id":"voyage-voyage-4-large","providerId":"voyage","sku":"voyage-4-large","unit":"usd_per_million_tokens","amountUsd":0.12,"currency":"USD","sourceUrl":"https://docs.voyageai.com/docs/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.12,"normalizationReason":null,"priceSortEligible":true,"qualifier":"Price per million tokens column. Not an input/output split. Free-token allowances were not converted into a rate."},{"id":"voyage-voyage-4","providerId":"voyage","sku":"voyage-4","unit":"usd_per_million_tokens","amountUsd":0.06,"currency":"USD","sourceUrl":"https://docs.voyageai.com/docs/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.06,"normalizationReason":null,"priceSortEligible":true,"qualifier":"Price per million tokens column. Not an input/output split. Free-token allowances were not converted into a rate."},{"id":"voyage-voyage-4-lite","providerId":"voyage","sku":"voyage-4-lite","unit":"usd_per_million_tokens","amountUsd":0.02,"currency":"USD","sourceUrl":"https://docs.voyageai.com/docs/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.02,"normalizationReason":null,"priceSortEligible":true,"qualifier":"Price per million tokens column. Not an input/output split. Free-token allowances were not converted into a rate."},{"id":"voyage-voyage-context-4","providerId":"voyage","sku":"voyage-context-4","unit":"usd_per_million_tokens","amountUsd":0.12,"currency":"USD","sourceUrl":"https://docs.voyageai.com/docs/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.12,"normalizationReason":null,"priceSortEligible":true,"qualifier":"Price per million tokens column. Not an input/output split. Free-token allowances were not converted into a rate."},{"id":"voyage-voyage-code-4","providerId":"voyage","sku":"voyage-code-4","unit":"usd_per_million_tokens","amountUsd":0.12,"currency":"USD","sourceUrl":"https://docs.voyageai.com/docs/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.12,"normalizationReason":null,"priceSortEligible":true,"qualifier":"Price per million tokens column. Not an input/output split. Free-token allowances were not converted into a rate."},{"id":"voyage-rerank-3","providerId":"voyage","sku":"rerank-3","unit":"usd_per_million_tokens","amountUsd":0.05,"currency":"USD","sourceUrl":"https://docs.voyageai.com/docs/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.05,"normalizationReason":null,"priceSortEligible":true,"qualifier":"Price per million tokens column. Not an input/output split. Free-token allowances were not converted into a rate."},{"id":"voyage-rerank-3-lite","providerId":"voyage","sku":"rerank-3-lite","unit":"usd_per_million_tokens","amountUsd":0.02,"currency":"USD","sourceUrl":"https://docs.voyageai.com/docs/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.02,"normalizationReason":null,"priceSortEligible":true,"qualifier":"Price per million tokens column. Not an input/output split. Free-token allowances were not converted into a rate."}],"notesExcerpt":"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 …","notesCheck":{"status":"no_known_contradiction","pairs":[],"review":null,"note":null},"lastReviewed":"2026-09-14","scoreAsOf":"2026-09-14","website":"https://www.voyageai.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."}},"relatedJtbdSlugs":["embeddings","rag-memory","rag-rerank","batch-cheap-embeddings","late-interaction-retrieval"],"alternatives":[{"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","status":"active","overall":8.12,"scoreKind":"curated_estimate","confidence":"high","scoreAsOf":"2026-09-14","deltaOverallVsSubject":-0.28,"roles":["same_jtbd_runner","same_jtbd_pick"],"sharedJtbdSlugs":["embeddings","rag-rerank","batch-cheap-embeddings","late-interaction-retrieval"],"pricing":{"normalizedUsdPerMillionTokens":null,"normalizationStatus":"ambiguous","normalizationReason":"unlabeled_api_unit","shape":"sourced_rows","filterable":false,"priceSortEligible":false,"priceSortKeyUsdPerMillionInputTokens":null,"rows":[{"id":"jina-embeddings-v3-prompt-raw","providerId":"jina","sku":"jina-embeddings-v3","unit":"api_pricing_prompt_field","amountUsd":null,"currency":null,"sourceUrl":"https://api.jina.ai/v1/models","asOf":"2026-10-03","normalizationStatus":"ambiguous","normalizedUsdPerMillionTokens":null,"normalizationReason":"unlabeled_api_unit","priceSortEligible":false,"qualifier":"pricing.prompt is the string 0.00000005. Payload does not say per token or per million. Not multiplied.","raw":{"field":"pricing.prompt","amount":"0.00000005"}},{"id":"jina-embeddings-v5-text-nano-prompt-raw","providerId":"jina","sku":"jina-embeddings-v5-text-nano","unit":"api_pricing_prompt_field","amountUsd":null,"currency":null,"sourceUrl":"https://api.jina.ai/v1/models","asOf":"2026-10-03","normalizationStatus":"ambiguous","normalizedUsdPerMillionTokens":null,"normalizationReason":"unlabeled_api_unit","priceSortEligible":false,"qualifier":"pricing.prompt string 0.00000002. Same unlabeled unit. Not multiplied.","raw":{"field":"pricing.prompt","amount":"0.00000002"}},{"id":"jina-ocr-v1-prompt-raw","providerId":"jina","sku":"jina-ocr-v1","unit":"api_pricing_prompt_field","amountUsd":null,"currency":null,"sourceUrl":"https://api.jina.ai/v1/models","asOf":"2026-10-03","normalizationStatus":"ambiguous","normalizedUsdPerMillionTokens":null,"normalizationReason":"unlabeled_api_unit","priceSortEligible":false,"qualifier":"pricing.prompt 0.0000005 and pricing.completion 0.000002. Unit unlabeled. Not multiplied.","raw":{"field":"pricing.prompt","amount":"0.0000005","completion":"0.000002"}}],"notesExcerpt":"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://j…","notesCheck":{"status":"no_known_contradiction","pairs":[],"review":null,"note":null},"lastReviewed":"2026-09-14","scoreAsOf":"2026-09-14","website":"https://jina.ai","doNotParse":"Do not parse pricingNotes. Use rows only. normalizedUsdPerMillionTokens is a single number only when this provider has exactly one sourced token row. Input/output, context tiers, and non-token units stay null at this level.","gap":"Partial coverage. Providers without a fetched SKU are omitted. See GET /api/pricing."},"decideHint":"/api/decide?jtbd=embeddings","human":"/providers/jina","compare":"/compare/voyage-vs-jina"},{"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","status":"active","overall":7.95,"scoreKind":"curated_estimate","confidence":"high","scoreAsOf":"2026-10-19","deltaOverallVsSubject":-0.45,"roles":["same_jtbd_pick","same_jtbd_runner"],"sharedJtbdSlugs":["embeddings","rag-rerank","batch-cheap-embeddings","late-interaction-retrieval"],"pricing":{"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."},"decideHint":"/api/decide?jtbd=embeddings","human":"/providers/cohere","compare":"/compare/voyage-vs-cohere"},{"id":"supabase-pgvector","slug":"supabase-pgvector","name":"Supabase (pgvector)","tagline":"Depot default for most agent apps under ~25–50M vectors. Don't add Pinecone until Postgres actually hurts.","website":"https://supabase.com","status":"active","overall":8.64,"scoreKind":"curated_estimate","confidence":"high","scoreAsOf":"2026-09-14","deltaOverallVsSubject":0.24,"roles":["same_jtbd_pick"],"sharedJtbdSlugs":["rag-memory"],"pricing":{"normalizedUsdPerMillionTokens":null,"normalizationStatus":"unavailable","normalizationReason":"no_sourced_price","shape":"prose_notes_only","filterable":false,"priceSortEligible":false,"priceSortKeyUsdPerMillionInputTokens":null,"rows":[],"notesExcerpt":"Postgres + pgvector + Auth + Storage; usage on compute/storage; free tier. Vectors hitchhike on Postgres.","notesCheck":{"status":"no_known_contradiction","pairs":[],"review":null,"note":null},"lastReviewed":"2026-09-14","scoreAsOf":"2026-09-14","website":"https://supabase.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":"No sourced price row for this provider. pricingNotes stay prose. See research/gaps.md."},"decideHint":"/api/decide?jtbd=rag-memory","human":"/providers/supabase-pgvector","compare":"/compare/voyage-vs-supabase-pgvector"},{"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","status":"active","overall":8.43,"scoreKind":"curated_estimate","confidence":"high","scoreAsOf":"2026-10-19","deltaOverallVsSubject":0.03,"roles":["same_jtbd_runner"],"sharedJtbdSlugs":["embeddings","batch-cheap-embeddings"],"pricing":{"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."},"decideHint":"/api/decide?jtbd=embeddings","human":"/providers/google-ai","compare":"/compare/voyage-vs-google-ai"},{"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","status":"active","overall":8.22,"scoreKind":"curated_estimate","confidence":"high","scoreAsOf":"2026-09-14","deltaOverallVsSubject":-0.18,"roles":["same_jtbd_runner"],"sharedJtbdSlugs":["embeddings","batch-cheap-embeddings"],"pricing":{"normalizedUsdPerMillionTokens":null,"normalizationStatus":"ambiguous","normalizationReason":"input_output_split_not_a_single_rate","shape":"sourced_rows","filterable":false,"priceSortEligible":true,"priceSortKeyUsdPerMillionInputTokens":0.1,"rows":[{"id":"openai-gpt-6-astra-short-input","providerId":"openai","sku":"gpt-6-astra","unit":"usd_per_million_input_tokens","amountUsd":10,"currency":"USD","sourceUrl":"https://developers.openai.com/api/docs/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":10,"normalizationReason":null,"priceSortEligible":true,"qualifier":"Standard processing, short context. Cached input and cache writes are separate columns and were not used."},{"id":"openai-gpt-6-astra-short-output","providerId":"openai","sku":"gpt-6-astra","unit":"usd_per_million_output_tokens","amountUsd":50,"currency":"USD","sourceUrl":"https://developers.openai.com/api/docs/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":50,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"Standard processing, short context"},{"id":"openai-gpt-6-astra-long-input","providerId":"openai","sku":"gpt-6-astra","unit":"usd_per_million_input_tokens","amountUsd":20,"currency":"USD","sourceUrl":"https://developers.openai.com/api/docs/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":20,"normalizationReason":"context_tier_not_a_single_rate","priceSortEligible":false,"qualifier":"Standard processing, long context. Not selected as the sort key."},{"id":"openai-gpt-6-astra-long-output","providerId":"openai","sku":"gpt-6-astra","unit":"usd_per_million_output_tokens","amountUsd":75,"currency":"USD","sourceUrl":"https://developers.openai.com/api/docs/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":75,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"Standard processing, long context"},{"id":"openai-gpt-61-sol-short-input","providerId":"openai","sku":"gpt-6.1-sol","unit":"usd_per_million_input_tokens","amountUsd":2,"currency":"USD","sourceUrl":"https://developers.openai.com/api/docs/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":2,"normalizationReason":null,"priceSortEligible":true,"qualifier":"Standard processing, short context. Cached input and cache writes are separate columns and were not used."},{"id":"openai-gpt-61-sol-short-output","providerId":"openai","sku":"gpt-6.1-sol","unit":"usd_per_million_output_tokens","amountUsd":10,"currency":"USD","sourceUrl":"https://developers.openai.com/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":"Standard processing, short context"},{"id":"openai-gpt-61-sol-long-input","providerId":"openai","sku":"gpt-6.1-sol","unit":"usd_per_million_input_tokens","amountUsd":4,"currency":"USD","sourceUrl":"https://developers.openai.com/api/docs/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":4,"normalizationReason":"context_tier_not_a_single_rate","priceSortEligible":false,"qualifier":"Standard processing, long context. Not selected as the sort key."},{"id":"openai-gpt-61-sol-long-output","providerId":"openai","sku":"gpt-6.1-sol","unit":"usd_per_million_output_tokens","amountUsd":15,"currency":"USD","sourceUrl":"https://developers.openai.com/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":"Standard processing, long context"},{"id":"openai-gpt-6-luna-short-input","providerId":"openai","sku":"gpt-6-luna","unit":"usd_per_million_input_tokens","amountUsd":0.1,"currency":"USD","sourceUrl":"https://developers.openai.com/api/docs/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.1,"normalizationReason":null,"priceSortEligible":true,"qualifier":"Standard processing, short context. Cached input and cache writes are separate columns and were not used."},{"id":"openai-gpt-6-luna-short-output","providerId":"openai","sku":"gpt-6-luna","unit":"usd_per_million_output_tokens","amountUsd":0.5,"currency":"USD","sourceUrl":"https://developers.openai.com/api/docs/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.5,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"Standard processing, short context"},{"id":"openai-gpt-6-luna-long-input","providerId":"openai","sku":"gpt-6-luna","unit":"usd_per_million_input_tokens","amountUsd":0.2,"currency":"USD","sourceUrl":"https://developers.openai.com/api/docs/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.2,"normalizationReason":"context_tier_not_a_single_rate","priceSortEligible":false,"qualifier":"Standard processing, long context. Not selected as the sort key.","sourceStatus":"unverified","sourceStatusReason":"tier_not_on_rendered_page: on 2026-10-20 the rendered OpenAI pricing page has no long-context tier for gpt-6-luna (no 'long context', no context threshold, no $0.75 anywhere). It shows one Standard row per model: \"gpt-6-luna $0.10 $0.50 $0.01 $0.125 $0.25 (Standard: Input, Output, Cached input, 30m write, 12h write); Batch gpt-6-luna $0.05 $0.25; Fast gpt-6-luna $0.20 $1.00\". The stored long-context $0.2 (usd_per_million_input_tokens) cannot be confirmed; static check status was reconfirmed (false match: $0.20 is the Fast tier input price, not a long-context price). Row kept for history, marked unverified, never ranked. No new long-context amount is invented.","sourceStatusCheckedOn":"2026-10-20"},{"id":"openai-gpt-6-luna-long-output","providerId":"openai","sku":"gpt-6-luna","unit":"usd_per_million_output_tokens","amountUsd":0.75,"currency":"USD","sourceUrl":"https://developers.openai.com/api/docs/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.75,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"Standard processing, long context","sourceStatus":"unverified","sourceStatusReason":"tier_not_on_rendered_page: on 2026-10-20 the rendered OpenAI pricing page has no long-context tier for gpt-6-luna (no 'long context', no context threshold, no $0.75 anywhere). It shows one Standard row per model: \"gpt-6-luna $0.10 $0.50 $0.01 $0.125 $0.25 (Standard: Input, Output, Cached input, 30m write, 12h write); Batch gpt-6-luna $0.05 $0.25; Fast gpt-6-luna $0.20 $1.00\". The stored long-context $0.75 (usd_per_million_output_tokens) cannot be confirmed; static check status was not_found_on_page. Row kept for history, marked unverified, never ranked. No new long-context amount is invented.","sourceStatusCheckedOn":"2026-10-20"}],"notesExcerpt":"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.","notesCheck":{"status":"no_known_contradiction","pairs":[],"review":null,"note":null},"lastReviewed":"2026-09-14","scoreAsOf":"2026-09-14","website":"https://openai.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."},"decideHint":"/api/decide?jtbd=embeddings","human":"/providers/openai","compare":"/compare/voyage-vs-openai"},{"id":"qdrant","slug":"qdrant","name":"Qdrant","tagline":"Depot pick for serious vector workloads with filters. Self-host or Cloud — either way you can leave.","website":"https://qdrant.tech","status":"active","overall":8.59,"scoreKind":"curated_estimate","confidence":"high","scoreAsOf":"2026-10-19","deltaOverallVsSubject":0.19,"roles":["same_jtbd_runner"],"sharedJtbdSlugs":["rag-memory"],"pricing":{"normalizedUsdPerMillionTokens":null,"normalizationStatus":"unavailable","normalizationReason":"no_sourced_price","shape":"prose_notes_only","filterable":false,"priceSortEligible":false,"priceSortKeyUsdPerMillionInputTokens":null,"rows":[],"notesExcerpt":"Rust engine; open-source + Qdrant Cloud; excellent filtered ANN; competitive cloud pricing.","notesCheck":{"status":"no_known_contradiction","pairs":[],"review":null,"note":null},"lastReviewed":"2026-10-19","scoreAsOf":"2026-10-19","website":"https://qdrant.tech","doNotParse":"Do not parse pricingNotes. Use rows only. normalizedUsdPerMillionTokens is a single number only when this provider has exactly one sourced token row. Input/output, context tiers, and non-token units stay null at this level.","gap":"No sourced price row for this provider. pricingNotes stay prose. See research/gaps.md."},"decideHint":"/api/decide?jtbd=rag-memory","human":"/providers/qdrant","compare":"/compare/voyage-vs-qdrant"},{"id":"upstash-redis","slug":"upstash-redis","name":"Upstash Redis","tagline":"Default serverless-edge-redis. Use classic Redis Cloud when you need always-on fat memory / Redis modules…","website":"https://upstash.com/redis","status":"active","overall":8.49,"scoreKind":"curated_estimate","confidence":"high","scoreAsOf":"2026-09-14","deltaOverallVsSubject":0.09,"roles":["same_jtbd_runner"],"sharedJtbdSlugs":["rag-memory"],"pricing":{"normalizedUsdPerMillionTokens":null,"normalizationStatus":"unavailable","normalizationReason":"no_sourced_price","shape":"prose_notes_only","filterable":false,"priceSortEligible":false,"priceSortKeyUsdPerMillionInputTokens":null,"rows":[],"notesExcerpt":"As of 2026-09-14 (upstash.com/pricing/redis): Free 256MB / 500K commands. PAYG $0.2 per 100K commands + $0.25/GB storage; fixed plans from $10/mo. Prod Pack +$200/db. HTTP + TCP; agents can POST https://upstash.com/start-redis for temp DBs. Separate from Upstash QStash/Vector/Box…","notesCheck":{"status":"no_known_contradiction","pairs":[],"review":null,"note":null},"lastReviewed":"2026-09-14","scoreAsOf":"2026-09-14","website":"https://upstash.com/redis","doNotParse":"Do not parse pricingNotes. Use rows only. normalizedUsdPerMillionTokens is a single number only when this provider has exactly one sourced token row. Input/output, context tiers, and non-token units stay null at this level.","gap":"No sourced price row for this provider. pricingNotes stay prose. See research/gaps.md."},"decideHint":"/api/decide?jtbd=rag-memory","human":"/providers/upstash-redis","compare":"/compare/voyage-vs-upstash-redis"},{"id":"typesense-cloud","slug":"typesense-cloud","name":"Typesense Cloud","tagline":"Hybrid search peer when you want Algolia-like DX without per-request fees. Sample $0.03/hr floor pinned…","website":"https://cloud.typesense.org","status":"active","overall":8.29,"scoreKind":"curated_estimate","confidence":"high","scoreAsOf":"2026-09-14","deltaOverallVsSubject":-0.11,"roles":["same_jtbd_runner"],"sharedJtbdSlugs":["late-interaction-retrieval"],"pricing":{"normalizedUsdPerMillionTokens":null,"normalizationStatus":"unavailable","normalizationReason":"no_sourced_price","shape":"prose_notes_only","filterable":false,"priceSortEligible":false,"priceSortKeyUsdPerMillionInputTokens":null,"rows":[],"notesExcerpt":"As of 2026-09-14: Hourly hardware clusters via cloud.typesense.org calculator (no per-search fees). Sample entry SKU ~0.5 GB RAM / 2 burst vCPU ≈ **$0.03/hr** (~$21.60/720h-mo); HA multi-node and higher RAM multiply. Bandwidth ~$0.09–$0.12/GB class on secondary trackers; 10 GB fr…","notesCheck":{"status":"no_known_contradiction","pairs":[],"review":null,"note":null},"lastReviewed":"2026-09-14","scoreAsOf":"2026-09-14","website":"https://cloud.typesense.org","doNotParse":"Do not parse pricingNotes. Use rows only. normalizedUsdPerMillionTokens is a single number only when this provider has exactly one sourced token row. Input/output, context tiers, and non-token units stay null at this level.","gap":"No sourced price row for this provider. pricingNotes stay prose. See research/gaps.md."},"decideHint":"/api/decide?jtbd=late-interaction-retrieval","human":"/providers/typesense-cloud","compare":"/compare/voyage-vs-typesense-cloud"},{"id":"turbopuffer","slug":"turbopuffer","name":"Turbopuffer","tagline":"When your vector bill scares you and much of the corpus is cold, Turbopuffer is the interesting answer.","website":"https://turbopuffer.com","status":"active","overall":8.21,"scoreKind":"curated_estimate","confidence":"high","scoreAsOf":"2026-09-14","deltaOverallVsSubject":-0.19,"roles":["same_jtbd_runner"],"sharedJtbdSlugs":["rag-memory"],"pricing":{"normalizedUsdPerMillionTokens":null,"normalizationStatus":"unavailable","normalizationReason":"no_sourced_price","shape":"prose_notes_only","filterable":false,"priceSortEligible":false,"priceSortKeyUsdPerMillionInputTokens":null,"rows":[],"notesExcerpt":"As of 2026-10-24 (turbopuffer.com/pricing, fetched 2026-10-24): Usage-based with plan minimums: launch '$16/month minimum usage', scale '$256/month minimum usage', enterprise '>= $4,096/month' with '35% usage premium'. 'You'll pay for actual usage beyond the minimum.' 'Unused amo…","notesCheck":{"status":"no_known_contradiction","pairs":[],"review":null,"note":null},"lastReviewed":"2026-09-14","scoreAsOf":"2026-09-14","website":"https://turbopuffer.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":"No sourced price row for this provider. pricingNotes stay prose. See research/gaps.md."},"decideHint":"/api/decide?jtbd=rag-memory","human":"/providers/turbopuffer","compare":"/compare/voyage-vs-turbopuffer"},{"id":"upstash-vector","slug":"upstash-vector","name":"Upstash Vector","tagline":"Prototype/edge RAG peer when you already on Upstash. Prefer Qdrant/Pinecone for serious filtered production…","website":"https://upstash.com/vector","status":"active","overall":8.15,"scoreKind":"curated_estimate","confidence":"high","scoreAsOf":"2026-09-14","deltaOverallVsSubject":-0.25,"roles":["same_jtbd_runner"],"sharedJtbdSlugs":["rag-memory"],"pricing":{"normalizedUsdPerMillionTokens":null,"normalizationStatus":"unavailable","normalizationReason":"no_sourced_price","shape":"prose_notes_only","filterable":false,"priceSortEligible":false,"priceSortKeyUsdPerMillionInputTokens":null,"rows":[],"notesExcerpt":"As of 2026-09-14 (upstash.com/pricing/vector markdown): Free $0 — 200M vectors×dims, 10K queries/day, 1GB. PAYG $0.40 per 100K requests + $0.25/GB storage (≤50GB, 99.9% SLA). Fixed $60/mo (1M queries/day). Pro contact (100B scale). Bandwidth free to 200GB then $0.03/GB.","notesCheck":{"status":"no_known_contradiction","pairs":[],"review":null,"note":null},"lastReviewed":"2026-09-14","scoreAsOf":"2026-09-14","website":"https://upstash.com/vector","doNotParse":"Do not parse pricingNotes. Use rows only. normalizedUsdPerMillionTokens is a single number only when this provider has exactly one sourced token row. Input/output, context tiers, and non-token units stay null at this level.","gap":"No sourced price row for this provider. pricingNotes stay prose. See research/gaps.md."},"decideHint":"/api/decide?jtbd=rag-memory","human":"/providers/upstash-vector","compare":"/compare/voyage-vs-upstash-vector"},{"id":"redis","slug":"redis","name":"Redis","tagline":"Use as agent hot memory/cache, not as your only 100M-vector archive.","website":"https://redis.io","status":"active","overall":8.07,"scoreKind":"curated_estimate","confidence":"high","scoreAsOf":"2026-09-14","deltaOverallVsSubject":-0.33,"roles":["same_jtbd_runner"],"sharedJtbdSlugs":["rag-memory"],"pricing":{"normalizedUsdPerMillionTokens":null,"normalizationStatus":"unavailable","normalizationReason":"no_sourced_price","shape":"prose_notes_only","filterable":false,"priceSortEligible":false,"priceSortKeyUsdPerMillionInputTokens":null,"rows":[],"notesExcerpt":"Redis OSS + Redis Cloud; vector search via Redis Query Engine; pay for memory-centric hosting.","notesCheck":{"status":"no_known_contradiction","pairs":[],"review":null,"note":null},"lastReviewed":"2026-09-14","scoreAsOf":"2026-09-14","website":"https://redis.io","doNotParse":"Do not parse pricingNotes. Use rows only. normalizedUsdPerMillionTokens is a single number only when this provider has exactly one sourced token row. Input/output, context tiers, and non-token units stay null at this level.","gap":"No sourced price row for this provider. pricingNotes stay prose. See research/gaps.md."},"decideHint":"/api/decide?jtbd=rag-memory","human":"/providers/redis","compare":"/compare/voyage-vs-redis"},{"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","status":"active","overall":7.95,"scoreKind":"curated_estimate","confidence":"high","scoreAsOf":"2026-09-14","deltaOverallVsSubject":-0.45,"roles":["same_jtbd_runner"],"sharedJtbdSlugs":["embeddings"],"pricing":{"normalizedUsdPerMillionTokens":null,"normalizationStatus":"unit_mismatch","normalizationReason":"unit_mismatch","shape":"sourced_rows","filterable":false,"priceSortEligible":false,"priceSortKeyUsdPerMillionInputTokens":null,"rows":[{"id":"huggingface-inference-aws-nvidia-t4-x1-usd-per-gpu-hour","providerId":"huggingface-inference","sku":"aws nvidia-t4 x1","unit":"usd_per_gpu_hour","amountUsd":0.5,"currency":"USD","sourceUrl":"https://huggingface.co/docs/inference-endpoints/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"gpu_hour_not_coerced_to_per_million_tokens","priceSortEligible":false,"qualifier":"Dedicated Inference Endpoints hourly rate. Billed per minute. CPU instance table not copied. Deprecated Ice Lake rows omitted. Single-GPU (x1) instance: the instance-hour rate is the GPU-hour rate. Re-checked on the page 2026-10-27."},{"id":"huggingface-inference-aws-nvidia-t4-x4-usd-per-gpu-hour","providerId":"huggingface-inference","sku":"aws nvidia-t4 x4","unit":"usd_per_instance_hour","amountUsd":3,"currency":"USD","sourceUrl":"https://huggingface.co/docs/inference-endpoints/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_instance_hour","priceSortEligible":false,"qualifier":"Dedicated Inference Endpoints hourly rate for the whole aws nvidia-t4 x4 instance (4 GPUs): the GPU Instances table prints 'Hourly rate' per instance next to a separate 'GPUs' column. Instance-hour price, not a per-GPU rate, never divided by 4. Billed per minute. CPU instance table not copied. Deprecated Ice Lake rows omitted. Unit label corrected 2026-10-27 (v0.12.138) from usd_per_gpu_hour; amount unchanged, re-checked on the page 2026-10-27."},{"id":"huggingface-inference-aws-nvidia-l4-x1-usd-per-gpu-hour","providerId":"huggingface-inference","sku":"aws nvidia-l4 x1","unit":"usd_per_gpu_hour","amountUsd":0.8,"currency":"USD","sourceUrl":"https://huggingface.co/docs/inference-endpoints/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"gpu_hour_not_coerced_to_per_million_tokens","priceSortEligible":false,"qualifier":"Dedicated Inference Endpoints hourly rate. Billed per minute. CPU instance table not copied. Deprecated Ice Lake rows omitted. Single-GPU (x1) instance: the instance-hour rate is the GPU-hour rate. Re-checked on the page 2026-10-27."},{"id":"huggingface-inference-aws-nvidia-l4-x4-usd-per-gpu-hour","providerId":"huggingface-inference","sku":"aws nvidia-l4 x4","unit":"usd_per_instance_hour","amountUsd":3.8,"currency":"USD","sourceUrl":"https://huggingface.co/docs/inference-endpoints/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_instance_hour","priceSortEligible":false,"qualifier":"Dedicated Inference Endpoints hourly rate for the whole aws nvidia-l4 x4 instance (4 GPUs): the GPU Instances table prints 'Hourly rate' per instance next to a separate 'GPUs' column. Instance-hour price, not a per-GPU rate, never divided by 4. Billed per minute. CPU instance table not copied. Deprecated Ice Lake rows omitted. Unit label corrected 2026-10-27 (v0.12.138) from usd_per_gpu_hour; amount unchanged, re-checked on the page 2026-10-27."},{"id":"huggingface-inference-aws-nvidia-a10g-x1-usd-per-gpu-hour","providerId":"huggingface-inference","sku":"aws nvidia-a10g x1","unit":"usd_per_gpu_hour","amountUsd":1,"currency":"USD","sourceUrl":"https://huggingface.co/docs/inference-endpoints/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"gpu_hour_not_coerced_to_per_million_tokens","priceSortEligible":false,"qualifier":"Dedicated Inference Endpoints hourly rate. Billed per minute. CPU instance table not copied. Deprecated Ice Lake rows omitted. Single-GPU (x1) instance: the instance-hour rate is the GPU-hour rate. Re-checked on the page 2026-10-27."},{"id":"huggingface-inference-aws-nvidia-a10g-x4-usd-per-gpu-hour","providerId":"huggingface-inference","sku":"aws nvidia-a10g x4","unit":"usd_per_instance_hour","amountUsd":5,"currency":"USD","sourceUrl":"https://huggingface.co/docs/inference-endpoints/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_instance_hour","priceSortEligible":false,"qualifier":"Dedicated Inference Endpoints hourly rate for the whole aws nvidia-a10g x4 instance (4 GPUs): the GPU Instances table prints 'Hourly rate' per instance next to a separate 'GPUs' column. Instance-hour price, not a per-GPU rate, never divided by 4. Billed per minute. CPU instance table not copied. Deprecated Ice Lake rows omitted. Unit label corrected 2026-10-27 (v0.12.138) from usd_per_gpu_hour; amount unchanged, re-checked on the page 2026-10-27."},{"id":"huggingface-inference-aws-nvidia-l40s-x1-usd-per-gpu-hour","providerId":"huggingface-inference","sku":"aws nvidia-l40s x1","unit":"usd_per_gpu_hour","amountUsd":1.8,"currency":"USD","sourceUrl":"https://huggingface.co/docs/inference-endpoints/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"gpu_hour_not_coerced_to_per_million_tokens","priceSortEligible":false,"qualifier":"Dedicated Inference Endpoints hourly rate. Billed per minute. CPU instance table not copied. Deprecated Ice Lake rows omitted. Single-GPU (x1) instance: the instance-hour rate is the GPU-hour rate. Re-checked on the page 2026-10-27."},{"id":"huggingface-inference-aws-nvidia-l40s-x4-usd-per-gpu-hour","providerId":"huggingface-inference","sku":"aws nvidia-l40s x4","unit":"usd_per_instance_hour","amountUsd":8.3,"currency":"USD","sourceUrl":"https://huggingface.co/docs/inference-endpoints/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_instance_hour","priceSortEligible":false,"qualifier":"Dedicated Inference Endpoints hourly rate for the whole aws nvidia-l40s x4 instance (4 GPUs): the GPU Instances table prints 'Hourly rate' per instance next to a separate 'GPUs' column. Instance-hour price, not a per-GPU rate, never divided by 4. Billed per minute. CPU instance table not copied. Deprecated Ice Lake rows omitted. Unit label corrected 2026-10-27 (v0.12.138) from usd_per_gpu_hour; amount unchanged, re-checked on the page 2026-10-27."},{"id":"huggingface-inference-aws-nvidia-l40s-x8-usd-per-gpu-hour","providerId":"huggingface-inference","sku":"aws nvidia-l40s x8","unit":"usd_per_instance_hour","amountUsd":23.5,"currency":"USD","sourceUrl":"https://huggingface.co/docs/inference-endpoints/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_instance_hour","priceSortEligible":false,"qualifier":"Dedicated Inference Endpoints hourly rate for the whole aws nvidia-l40s x8 instance (8 GPUs): the GPU Instances table prints 'Hourly rate' per instance next to a separate 'GPUs' column. Instance-hour price, not a per-GPU rate, never divided by 8. Billed per minute. CPU instance table not copied. Deprecated Ice Lake rows omitted. Unit label corrected 2026-10-27 (v0.12.138) from usd_per_gpu_hour; amount unchanged, re-checked on the page 2026-10-27."},{"id":"huggingface-inference-aws-nvidia-a100-x1-usd-per-gpu-hour","providerId":"huggingface-inference","sku":"aws nvidia-a100 x1","unit":"usd_per_gpu_hour","amountUsd":2.5,"currency":"USD","sourceUrl":"https://huggingface.co/docs/inference-endpoints/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"gpu_hour_not_coerced_to_per_million_tokens","priceSortEligible":false,"qualifier":"Dedicated Inference Endpoints hourly rate. Billed per minute. CPU instance table not copied. Deprecated Ice Lake rows omitted. Single-GPU (x1) instance: the instance-hour rate is the GPU-hour rate. Re-checked on the page 2026-10-27."},{"id":"huggingface-inference-aws-nvidia-a100-x2-usd-per-gpu-hour","providerId":"huggingface-inference","sku":"aws nvidia-a100 x2","unit":"usd_per_instance_hour","amountUsd":5,"currency":"USD","sourceUrl":"https://huggingface.co/docs/inference-endpoints/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_instance_hour","priceSortEligible":false,"qualifier":"Dedicated Inference Endpoints hourly rate for the whole aws nvidia-a100 x2 instance (2 GPUs): the GPU Instances table prints 'Hourly rate' per instance next to a separate 'GPUs' column. Instance-hour price, not a per-GPU rate, never divided by 2. Billed per minute. CPU instance table not copied. Deprecated Ice Lake rows omitted. Unit label corrected 2026-10-27 (v0.12.138) from usd_per_gpu_hour; amount unchanged, re-checked on the page 2026-10-27."},{"id":"huggingface-inference-aws-nvidia-a100-x4-usd-per-gpu-hour","providerId":"huggingface-inference","sku":"aws nvidia-a100 x4","unit":"usd_per_instance_hour","amountUsd":10,"currency":"USD","sourceUrl":"https://huggingface.co/docs/inference-endpoints/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_instance_hour","priceSortEligible":false,"qualifier":"Dedicated Inference Endpoints hourly rate for the whole aws nvidia-a100 x4 instance (4 GPUs): the GPU Instances table prints 'Hourly rate' per instance next to a separate 'GPUs' column. Instance-hour price, not a per-GPU rate, never divided by 4. Billed per minute. CPU instance table not copied. Deprecated Ice Lake rows omitted. Unit label corrected 2026-10-27 (v0.12.138) from usd_per_gpu_hour; amount unchanged, re-checked on the page 2026-10-27."},{"id":"huggingface-inference-aws-nvidia-a100-x8-usd-per-gpu-hour","providerId":"huggingface-inference","sku":"aws nvidia-a100 x8","unit":"usd_per_instance_hour","amountUsd":20,"currency":"USD","sourceUrl":"https://huggingface.co/docs/inference-endpoints/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_instance_hour","priceSortEligible":false,"qualifier":"Dedicated Inference Endpoints hourly rate for the whole aws nvidia-a100 x8 instance (8 GPUs): the GPU Instances table prints 'Hourly rate' per instance next to a separate 'GPUs' column. Instance-hour price, not a per-GPU rate, never divided by 8. Billed per minute. CPU instance table not copied. Deprecated Ice Lake rows omitted. Unit label corrected 2026-10-27 (v0.12.138) from usd_per_gpu_hour; amount unchanged, re-checked on the page 2026-10-27."},{"id":"huggingface-inference-aws-nvidia-h200-x1-usd-per-gpu-hour","providerId":"huggingface-inference","sku":"aws nvidia-h200 x1","unit":"usd_per_gpu_hour","amountUsd":5,"currency":"USD","sourceUrl":"https://huggingface.co/docs/inference-endpoints/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"gpu_hour_not_coerced_to_per_million_tokens","priceSortEligible":false,"qualifier":"Dedicated Inference Endpoints hourly rate. Billed per minute. CPU instance table not copied. Deprecated Ice Lake rows omitted. Single-GPU (x1) instance: the instance-hour rate is the GPU-hour rate. Re-checked on the page 2026-10-27."},{"id":"huggingface-inference-aws-nvidia-h200-x2-usd-per-gpu-hour","providerId":"huggingface-inference","sku":"aws nvidia-h200 x2","unit":"usd_per_instance_hour","amountUsd":10,"currency":"USD","sourceUrl":"https://huggingface.co/docs/inference-endpoints/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_instance_hour","priceSortEligible":false,"qualifier":"Dedicated Inference Endpoints hourly rate for the whole aws nvidia-h200 x2 instance (2 GPUs): the GPU Instances table prints 'Hourly rate' per instance next to a separate 'GPUs' column. Instance-hour price, not a per-GPU rate, never divided by 2. Billed per minute. CPU instance table not copied. Deprecated Ice Lake rows omitted. Unit label corrected 2026-10-27 (v0.12.138) from usd_per_gpu_hour; amount unchanged, re-checked on the page 2026-10-27."},{"id":"huggingface-inference-aws-nvidia-h200-x4-usd-per-gpu-hour","providerId":"huggingface-inference","sku":"aws nvidia-h200 x4","unit":"usd_per_instance_hour","amountUsd":20,"currency":"USD","sourceUrl":"https://huggingface.co/docs/inference-endpoints/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_instance_hour","priceSortEligible":false,"qualifier":"Dedicated Inference Endpoints hourly rate for the whole aws nvidia-h200 x4 instance (4 GPUs): the GPU Instances table prints 'Hourly rate' per instance next to a separate 'GPUs' column. Instance-hour price, not a per-GPU rate, never divided by 4. Billed per minute. CPU instance table not copied. Deprecated Ice Lake rows omitted. Unit label corrected 2026-10-27 (v0.12.138) from usd_per_gpu_hour; amount unchanged, re-checked on the page 2026-10-27."},{"id":"huggingface-inference-aws-nvidia-h200-x8-usd-per-gpu-hour","providerId":"huggingface-inference","sku":"aws nvidia-h200 x8","unit":"usd_per_instance_hour","amountUsd":40,"currency":"USD","sourceUrl":"https://huggingface.co/docs/inference-endpoints/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_instance_hour","priceSortEligible":false,"qualifier":"Dedicated Inference Endpoints hourly rate for the whole aws nvidia-h200 x8 instance (8 GPUs): the GPU Instances table prints 'Hourly rate' per instance next to a separate 'GPUs' column. Instance-hour price, not a per-GPU rate, never divided by 8. Billed per minute. CPU instance table not copied. Deprecated Ice Lake rows omitted. Unit label corrected 2026-10-27 (v0.12.138) from usd_per_gpu_hour; amount unchanged, re-checked on the page 2026-10-27."},{"id":"huggingface-inference-gcp-nvidia-t4-x1-usd-per-gpu-hour","providerId":"huggingface-inference","sku":"gcp nvidia-t4 x1","unit":"usd_per_gpu_hour","amountUsd":0.5,"currency":"USD","sourceUrl":"https://huggingface.co/docs/inference-endpoints/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"gpu_hour_not_coerced_to_per_million_tokens","priceSortEligible":false,"qualifier":"Dedicated Inference Endpoints hourly rate. Billed per minute. CPU instance table not copied. Deprecated Ice Lake rows omitted. Single-GPU (x1) instance: the instance-hour rate is the GPU-hour rate. Re-checked on the page 2026-10-27."},{"id":"huggingface-inference-gcp-nvidia-l4-x1-usd-per-gpu-hour","providerId":"huggingface-inference","sku":"gcp nvidia-l4 x1","unit":"usd_per_gpu_hour","amountUsd":0.7,"currency":"USD","sourceUrl":"https://huggingface.co/docs/inference-endpoints/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"gpu_hour_not_coerced_to_per_million_tokens","priceSortEligible":false,"qualifier":"Dedicated Inference Endpoints hourly rate. Billed per minute. CPU instance table not copied. Deprecated Ice Lake rows omitted. Single-GPU (x1) instance: the instance-hour rate is the GPU-hour rate. Re-checked on the page 2026-10-27."},{"id":"huggingface-inference-gcp-nvidia-l4-x4-usd-per-gpu-hour","providerId":"huggingface-inference","sku":"gcp nvidia-l4 x4","unit":"usd_per_instance_hour","amountUsd":3.8,"currency":"USD","sourceUrl":"https://huggingface.co/docs/inference-endpoints/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_instance_hour","priceSortEligible":false,"qualifier":"Dedicated Inference Endpoints hourly rate for the whole gcp nvidia-l4 x4 instance (4 GPUs): the GPU Instances table prints 'Hourly rate' per instance next to a separate 'GPUs' column. Instance-hour price, not a per-GPU rate, never divided by 4. Billed per minute. CPU instance table not copied. Deprecated Ice Lake rows omitted. Unit label corrected 2026-10-27 (v0.12.138) from usd_per_gpu_hour; amount unchanged, re-checked on the page 2026-10-27."},{"id":"huggingface-inference-gcp-nvidia-a100-x1-usd-per-gpu-hour","providerId":"huggingface-inference","sku":"gcp nvidia-a100 x1","unit":"usd_per_gpu_hour","amountUsd":3.6,"currency":"USD","sourceUrl":"https://huggingface.co/docs/inference-endpoints/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"gpu_hour_not_coerced_to_per_million_tokens","priceSortEligible":false,"qualifier":"Dedicated Inference Endpoints hourly rate. Billed per minute. CPU instance table not copied. Deprecated Ice Lake rows omitted. Single-GPU (x1) instance: the instance-hour rate is the GPU-hour rate. Re-checked on the page 2026-10-27."},{"id":"huggingface-inference-gcp-nvidia-a100-x2-usd-per-gpu-hour","providerId":"huggingface-inference","sku":"gcp nvidia-a100 x2","unit":"usd_per_instance_hour","amountUsd":7.2,"currency":"USD","sourceUrl":"https://huggingface.co/docs/inference-endpoints/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_instance_hour","priceSortEligible":false,"qualifier":"Dedicated Inference Endpoints hourly rate for the whole gcp nvidia-a100 x2 instance (2 GPUs): the GPU Instances table prints 'Hourly rate' per instance next to a separate 'GPUs' column. Instance-hour price, not a per-GPU rate, never divided by 2. Billed per minute. CPU instance table not copied. Deprecated Ice Lake rows omitted. Unit label corrected 2026-10-27 (v0.12.138) from usd_per_gpu_hour; amount unchanged, re-checked on the page 2026-10-27."},{"id":"huggingface-inference-gcp-nvidia-a100-x4-usd-per-gpu-hour","providerId":"huggingface-inference","sku":"gcp nvidia-a100 x4","unit":"usd_per_instance_hour","amountUsd":14.4,"currency":"USD","sourceUrl":"https://huggingface.co/docs/inference-endpoints/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_instance_hour","priceSortEligible":false,"qualifier":"Dedicated Inference Endpoints hourly rate for the whole gcp nvidia-a100 x4 instance (4 GPUs): the GPU Instances table prints 'Hourly rate' per instance next to a separate 'GPUs' column. Instance-hour price, not a per-GPU rate, never divided by 4. Billed per minute. CPU instance table not copied. Deprecated Ice Lake rows omitted. Unit label corrected 2026-10-27 (v0.12.138) from usd_per_gpu_hour; amount unchanged, re-checked on the page 2026-10-27."},{"id":"huggingface-inference-gcp-nvidia-a100-x8-usd-per-gpu-hour","providerId":"huggingface-inference","sku":"gcp nvidia-a100 x8","unit":"usd_per_instance_hour","amountUsd":28.8,"currency":"USD","sourceUrl":"https://huggingface.co/docs/inference-endpoints/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_instance_hour","priceSortEligible":false,"qualifier":"Dedicated Inference Endpoints hourly rate for the whole gcp nvidia-a100 x8 instance (8 GPUs): the GPU Instances table prints 'Hourly rate' per instance next to a separate 'GPUs' column. Instance-hour price, not a per-GPU rate, never divided by 8. Billed per minute. CPU instance table not copied. Deprecated Ice Lake rows omitted. Unit label corrected 2026-10-27 (v0.12.138) from usd_per_gpu_hour; amount unchanged, re-checked on the page 2026-10-27."},{"id":"huggingface-inference-gcp-nvidia-h100-x1-usd-per-gpu-hour","providerId":"huggingface-inference","sku":"gcp nvidia-h100 x1","unit":"usd_per_gpu_hour","amountUsd":10,"currency":"USD","sourceUrl":"https://huggingface.co/docs/inference-endpoints/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"gpu_hour_not_coerced_to_per_million_tokens","priceSortEligible":false,"qualifier":"Dedicated Inference Endpoints hourly rate. Billed per minute. CPU instance table not copied. Deprecated Ice Lake rows omitted. Single-GPU (x1) instance: the instance-hour rate is the GPU-hour rate. Re-checked on the page 2026-10-27."},{"id":"huggingface-inference-gcp-nvidia-h100-x2-usd-per-gpu-hour","providerId":"huggingface-inference","sku":"gcp nvidia-h100 x2","unit":"usd_per_instance_hour","amountUsd":20,"currency":"USD","sourceUrl":"https://huggingface.co/docs/inference-endpoints/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_instance_hour","priceSortEligible":false,"qualifier":"Dedicated Inference Endpoints hourly rate for the whole gcp nvidia-h100 x2 instance (2 GPUs): the GPU Instances table prints 'Hourly rate' per instance next to a separate 'GPUs' column. Instance-hour price, not a per-GPU rate, never divided by 2. Billed per minute. CPU instance table not copied. Deprecated Ice Lake rows omitted. Unit label corrected 2026-10-27 (v0.12.138) from usd_per_gpu_hour; amount unchanged, re-checked on the page 2026-10-27."},{"id":"huggingface-inference-gcp-nvidia-h100-x4-usd-per-gpu-hour","providerId":"huggingface-inference","sku":"gcp nvidia-h100 x4","unit":"usd_per_instance_hour","amountUsd":40,"currency":"USD","sourceUrl":"https://huggingface.co/docs/inference-endpoints/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_instance_hour","priceSortEligible":false,"qualifier":"Dedicated Inference Endpoints hourly rate for the whole gcp nvidia-h100 x4 instance (4 GPUs): the GPU Instances table prints 'Hourly rate' per instance next to a separate 'GPUs' column. Instance-hour price, not a per-GPU rate, never divided by 4. Billed per minute. CPU instance table not copied. Deprecated Ice Lake rows omitted. Unit label corrected 2026-10-27 (v0.12.138) from usd_per_gpu_hour; amount unchanged, re-checked on the page 2026-10-27."},{"id":"huggingface-inference-gcp-nvidia-h100-x8-usd-per-gpu-hour","providerId":"huggingface-inference","sku":"gcp nvidia-h100 x8","unit":"usd_per_instance_hour","amountUsd":80,"currency":"USD","sourceUrl":"https://huggingface.co/docs/inference-endpoints/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_instance_hour","priceSortEligible":false,"qualifier":"Dedicated Inference Endpoints hourly rate for the whole gcp nvidia-h100 x8 instance (8 GPUs): the GPU Instances table prints 'Hourly rate' per instance next to a separate 'GPUs' column. Instance-hour price, not a per-GPU rate, never divided by 8. Billed per minute. CPU instance table not copied. Deprecated Ice Lake rows omitted. Unit label corrected 2026-10-27 (v0.12.138) from usd_per_gpu_hour; amount unchanged, re-checked on the page 2026-10-27."},{"id":"huggingface-inference-aws-inf2-x1-usd-per-hour","providerId":"huggingface-inference","sku":"aws inf2 x1","unit":"usd_per_hour","amountUsd":0.75,"currency":"USD","sourceUrl":"https://huggingface.co/docs/inference-endpoints/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_hour","priceSortEligible":false,"qualifier":"Inferentia2 accelerator hour. Not a token price. Re-checked on the page 2026-10-27."},{"id":"huggingface-inference-gcp-tpu-v5e-1x1-usd-per-hour","providerId":"huggingface-inference","sku":"gcp tpu v5e 1x1","unit":"usd_per_hour","amountUsd":1.2,"currency":"USD","sourceUrl":"https://huggingface.co/docs/inference-endpoints/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_hour","priceSortEligible":false,"qualifier":"TPU v5e accelerator hour. Not a token price. Re-checked on the page 2026-10-27."}],"notesExcerpt":"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:…","notesCheck":{"status":"no_known_contradiction","pairs":[],"review":null,"note":null},"lastReviewed":"2026-09-14","scoreAsOf":"2026-09-14","website":"https://endpoints.huggingface.co","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."},"decideHint":"/api/decide?jtbd=embeddings","human":"/providers/huggingface-inference","compare":"/compare/voyage-vs-huggingface-inference"}],"rankContract":{"style":"editorial_weighted","notAnElo":true,"note":"deltaOverallVsSubject is Depot overall (0–10) minus the subject. It is not Arena Elo and not an Artificial Analysis index."},"freshness":{"scoreAsOfMin":"2026-09-14","scoreAsOfMax":"2026-10-19","contractAsOf":"2026-10-03"},"honesty":["Alternatives are other catalog providers that share a JTBD as pick or runner-up. If fewer than three exist, same-category active providers fill the list and are labeled same_category.","Overall deltas are catalog scores. kind=curated_estimate is not a lab measurement.","Pricing rows are sourced or explicitly null. Do not parse pricingNotes. A single normalized USD figure is set only for a provider with exactly one token row."],"links":{"human":"/alternatives/voyage","machine":"/api/alternatives?provider=voyage","provider":"/api/providers/voyage","canonical":"/api/canonical"}}