{"subject":{"id":"amazon-bedrock","slug":"amazon-bedrock","name":"Amazon Bedrock","tagline":"Enterprise multi-model switchboard. Great when AWS is mandatory; mediocre when you just want the best Claude…","website":"https://aws.amazon.com/bedrock/","status":"active","overall":7.75,"scoreKind":"curated_estimate","confidence":"high","scoreAsOf":"2026-09-14","lastReviewed":"2026-09-14","categoryIds":["cat-inference-apis"],"regions":["global","us","eu","ap"],"pricing":{"normalizedUsdPerMillionTokens":null,"normalizationStatus":"ambiguous","normalizationReason":"input_output_split_not_a_single_rate","shape":"sourced_rows","filterable":false,"priceSortEligible":true,"priceSortKeyUsdPerMillionInputTokens":0.04,"rows":[{"id":"amazon-bedrock-claude-3-5-sonnet-in","providerId":"amazon-bedrock","sku":"Claude 3.5 Sonnet","unit":"usd_per_million_input_tokens","amountUsd":6,"currency":"USD","sourceUrl":"https://aws.amazon.com/bedrock/pricing/","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":6,"normalizationReason":null,"priceSortEligible":false,"qualifier":"On-demand standard input. Public extended access, effective 1 Dec 2025 (already in effect). Regions: US East N. Virginia, Ohio, Oregon, Frankfurt, Ireland, Zurich, Paris. Batch and cache columns not used. Newer Claude SKUs were not in the fetched HTML.","sourceStatus":"unverified","sourceStatusReason":"sku_not_on_rendered_page: on 2026-10-19 the rendered Anthropic on-demand table (Global cross-region inference, Region US East (Ohio)) lists Claude Haiku 5.5 through Claude Sonnet 4, not Claude 3.5 Sonnet or 3.5 Sonnet v2. The name survives only in an unrendered price template and a prompt-routing paragraph, so no amount could be read. Kept for history, never ranked.","sourceStatusCheckedOn":"2026-10-19"},{"id":"amazon-bedrock-claude-3-5-sonnet-out","providerId":"amazon-bedrock","sku":"Claude 3.5 Sonnet","unit":"usd_per_million_output_tokens","amountUsd":30,"currency":"USD","sourceUrl":"https://aws.amazon.com/bedrock/pricing/","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":30,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"On-demand standard output.","sourceStatus":"unverified","sourceStatusReason":"sku_not_on_rendered_page: on 2026-10-19 the rendered Anthropic on-demand table (Global cross-region inference, Region US East (Ohio)) lists Claude Haiku 5.5 through Claude Sonnet 4, not Claude 3.5 Sonnet or 3.5 Sonnet v2. The name survives only in an unrendered price template and a prompt-routing paragraph, so no amount could be read. Kept for history, never ranked.","sourceStatusCheckedOn":"2026-10-19"},{"id":"amazon-bedrock-claude-3-5-sonnet-v2-in","providerId":"amazon-bedrock","sku":"Claude 3.5 Sonnet v2","unit":"usd_per_million_input_tokens","amountUsd":6,"currency":"USD","sourceUrl":"https://aws.amazon.com/bedrock/pricing/","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":6,"normalizationReason":null,"priceSortEligible":false,"qualifier":"On-demand standard input. Regions: US East N. Virginia, Ohio, Oregon. Cache write/read stored separately.","sourceStatus":"unverified","sourceStatusReason":"sku_not_on_rendered_page: on 2026-10-19 the rendered Anthropic on-demand table (Global cross-region inference, Region US East (Ohio)) lists Claude Haiku 5.5 through Claude Sonnet 4, not Claude 3.5 Sonnet or 3.5 Sonnet v2. The name survives only in an unrendered price template and a prompt-routing paragraph, so no amount could be read. Kept for history, never ranked.","sourceStatusCheckedOn":"2026-10-19"},{"id":"amazon-bedrock-claude-3-5-sonnet-v2-out","providerId":"amazon-bedrock","sku":"Claude 3.5 Sonnet v2","unit":"usd_per_million_output_tokens","amountUsd":30,"currency":"USD","sourceUrl":"https://aws.amazon.com/bedrock/pricing/","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":30,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"On-demand standard output.","sourceStatus":"unverified","sourceStatusReason":"sku_not_on_rendered_page: on 2026-10-19 the rendered Anthropic on-demand table (Global cross-region inference, Region US East (Ohio)) lists Claude Haiku 5.5 through Claude Sonnet 4, not Claude 3.5 Sonnet or 3.5 Sonnet v2. The name survives only in an unrendered price template and a prompt-routing paragraph, so no amount could be read. Kept for history, never ranked.","sourceStatusCheckedOn":"2026-10-19"},{"id":"amazon-bedrock-claude-3-5-sonnet-v2-write","providerId":"amazon-bedrock","sku":"Claude 3.5 Sonnet v2","unit":"usd_per_million_cache_write_tokens","amountUsd":7.5,"currency":"USD","sourceUrl":"https://aws.amazon.com/bedrock/pricing/","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":7.5,"normalizationReason":"cache_write_not_a_single_rate","priceSortEligible":false,"qualifier":"Cache write column. Not the sort key.","sourceStatus":"unverified","sourceStatusReason":"sku_not_on_rendered_page: on 2026-10-19 the rendered Anthropic on-demand table (Global cross-region inference, Region US East (Ohio)) lists Claude Haiku 5.5 through Claude Sonnet 4, not Claude 3.5 Sonnet or 3.5 Sonnet v2. The name survives only in an unrendered price template and a prompt-routing paragraph, so no amount could be read. Kept for history, never ranked.","sourceStatusCheckedOn":"2026-10-19"},{"id":"amazon-bedrock-claude-3-5-sonnet-v2-cached","providerId":"amazon-bedrock","sku":"Claude 3.5 Sonnet v2","unit":"usd_per_million_cached_input_tokens","amountUsd":0.6,"currency":"USD","sourceUrl":"https://aws.amazon.com/bedrock/pricing/","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.6,"normalizationReason":"cached_input_not_a_single_rate","priceSortEligible":false,"qualifier":"Cache read column.","sourceStatus":"unverified","sourceStatusReason":"sku_not_on_rendered_page: on 2026-10-19 the rendered Anthropic on-demand table (Global cross-region inference, Region US East (Ohio)) lists Claude Haiku 5.5 through Claude Sonnet 4, not Claude 3.5 Sonnet or 3.5 Sonnet v2. The name survives only in an unrendered price template and a prompt-routing paragraph, so no amount could be read. Kept for history, never ranked.","sourceStatusCheckedOn":"2026-10-19"},{"id":"amazon-bedrock-deepseek-v3-2-in","providerId":"amazon-bedrock","sku":"DeepSeek v3.2","unit":"usd_per_million_input_tokens","amountUsd":0.62,"currency":"USD","sourceUrl":"https://aws.amazon.com/bedrock/pricing/","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.62,"normalizationReason":null,"priceSortEligible":true,"qualifier":"Standard on-demand. Regions: US East (N. Virginia), US East (Ohio), US West (Oregon)."},{"id":"amazon-bedrock-deepseek-v3-2-out","providerId":"amazon-bedrock","sku":"DeepSeek v3.2","unit":"usd_per_million_output_tokens","amountUsd":1.85,"currency":"USD","sourceUrl":"https://aws.amazon.com/bedrock/pricing/","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":1.85,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"Standard on-demand. Regions: US East (N. Virginia), US East (Ohio), US West (Oregon)."},{"id":"amazon-bedrock-deepseek-v3-2-other-regions-in","providerId":"amazon-bedrock","sku":"DeepSeek v3.2 other regions","unit":"usd_per_million_input_tokens","amountUsd":0.74,"currency":"USD","sourceUrl":"https://aws.amazon.com/bedrock/pricing/","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.74,"normalizationReason":"regional_price_not_collapsed","priceSortEligible":false,"qualifier":"Standard on-demand for Mumbai, Sao Paulo, Jakarta, Tokyo, Stockholm. Not the US sort key."},{"id":"amazon-bedrock-deepseek-v3-2-other-regions-out","providerId":"amazon-bedrock","sku":"DeepSeek v3.2 other regions","unit":"usd_per_million_output_tokens","amountUsd":2.22,"currency":"USD","sourceUrl":"https://aws.amazon.com/bedrock/pricing/","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":2.22,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"Same non-US standard regions."},{"id":"amazon-bedrock-deepseek-v3-1-sydney-standard-in","providerId":"amazon-bedrock","sku":"DeepSeek v3.1 Sydney standard","unit":"usd_per_million_input_tokens","amountUsd":0.5974,"currency":"USD","sourceUrl":"https://aws.amazon.com/bedrock/pricing/","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.5974,"normalizationReason":"regional_price_not_collapsed","priceSortEligible":false,"qualifier":"Standard, Asia Pacific (Sydney) only in the fetched table."},{"id":"amazon-bedrock-deepseek-v3-1-sydney-standard-out","providerId":"amazon-bedrock","sku":"DeepSeek v3.1 Sydney standard","unit":"usd_per_million_output_tokens","amountUsd":1.7304,"currency":"USD","sourceUrl":"https://aws.amazon.com/bedrock/pricing/","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":1.7304,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"Sydney standard output."},{"id":"amazon-bedrock-deepseek-v3-2-sydney-standard-in","providerId":"amazon-bedrock","sku":"DeepSeek v3.2 Sydney standard","unit":"usd_per_million_input_tokens","amountUsd":0.6386,"currency":"USD","sourceUrl":"https://aws.amazon.com/bedrock/pricing/","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.6386,"normalizationReason":"regional_price_not_collapsed","priceSortEligible":false,"qualifier":"Sydney standard. US row is the sort key."},{"id":"amazon-bedrock-deepseek-v3-2-sydney-standard-out","providerId":"amazon-bedrock","sku":"DeepSeek v3.2 Sydney standard","unit":"usd_per_million_output_tokens","amountUsd":1.9055,"currency":"USD","sourceUrl":"https://aws.amazon.com/bedrock/pricing/","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":1.9055,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"Sydney standard output."},{"id":"amazon-bedrock-deepseek-v3-1-sydney-priority-in","providerId":"amazon-bedrock","sku":"DeepSeek v3.1 Sydney priority","unit":"usd_per_million_input_tokens","amountUsd":1.0455,"currency":"USD","sourceUrl":"https://aws.amazon.com/bedrock/pricing/","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":1.0455,"normalizationReason":"service_tier_not_standard","priceSortEligible":false,"qualifier":"Priority tier, Sydney. Not blended with standard or flex."},{"id":"amazon-bedrock-deepseek-v3-1-sydney-priority-out","providerId":"amazon-bedrock","sku":"DeepSeek v3.1 Sydney priority","unit":"usd_per_million_output_tokens","amountUsd":3.0282,"currency":"USD","sourceUrl":"https://aws.amazon.com/bedrock/pricing/","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":3.0282,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"Priority output."},{"id":"amazon-bedrock-deepseek-v3-1-sydney-flex-in","providerId":"amazon-bedrock","sku":"DeepSeek v3.1 Sydney flex","unit":"usd_per_million_input_tokens","amountUsd":0.2987,"currency":"USD","sourceUrl":"https://aws.amazon.com/bedrock/pricing/","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.2987,"normalizationReason":"service_tier_not_standard","priceSortEligible":false,"qualifier":"Flex tier, Sydney. Not blended with standard."},{"id":"amazon-bedrock-deepseek-v3-1-sydney-flex-out","providerId":"amazon-bedrock","sku":"DeepSeek v3.1 Sydney flex","unit":"usd_per_million_output_tokens","amountUsd":0.8652,"currency":"USD","sourceUrl":"https://aws.amazon.com/bedrock/pricing/","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.8652,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"Flex output."},{"id":"amazon-bedrock-gemma-4-31b-in","providerId":"amazon-bedrock","sku":"Gemma 4 31B","unit":"usd_per_million_input_tokens","amountUsd":0.14,"currency":"USD","sourceUrl":"https://aws.amazon.com/bedrock/pricing/","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.14,"normalizationReason":null,"priceSortEligible":true,"qualifier":"Standard on-demand. Regions: US East (N. Virginia), US East (Ohio), US West (Oregon)."},{"id":"amazon-bedrock-gemma-4-31b-out","providerId":"amazon-bedrock","sku":"Gemma 4 31B","unit":"usd_per_million_output_tokens","amountUsd":0.4,"currency":"USD","sourceUrl":"https://aws.amazon.com/bedrock/pricing/","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.4,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"Standard on-demand. Regions: US East (N. Virginia), US East (Ohio), US West (Oregon)."},{"id":"amazon-bedrock-gemma-4-26b-a4b-in","providerId":"amazon-bedrock","sku":"Gemma 4 26B A4B","unit":"usd_per_million_input_tokens","amountUsd":0.13,"currency":"USD","sourceUrl":"https://aws.amazon.com/bedrock/pricing/","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.13,"normalizationReason":null,"priceSortEligible":true,"qualifier":"Standard on-demand. Regions: US East (N. Virginia), US East (Ohio), US West (Oregon)."},{"id":"amazon-bedrock-gemma-4-26b-a4b-out","providerId":"amazon-bedrock","sku":"Gemma 4 26B A4B","unit":"usd_per_million_output_tokens","amountUsd":0.4,"currency":"USD","sourceUrl":"https://aws.amazon.com/bedrock/pricing/","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.4,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"Standard on-demand. Regions: US East (N. Virginia), US East (Ohio), US West (Oregon)."},{"id":"amazon-bedrock-gemma-4-e2b-in","providerId":"amazon-bedrock","sku":"Gemma 4 E2B","unit":"usd_per_million_input_tokens","amountUsd":0.04,"currency":"USD","sourceUrl":"https://aws.amazon.com/bedrock/pricing/","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.04,"normalizationReason":null,"priceSortEligible":true,"qualifier":"Standard on-demand. Regions: US East (N. Virginia), US East (Ohio), US West (Oregon)."},{"id":"amazon-bedrock-gemma-4-e2b-out","providerId":"amazon-bedrock","sku":"Gemma 4 E2B","unit":"usd_per_million_output_tokens","amountUsd":0.08,"currency":"USD","sourceUrl":"https://aws.amazon.com/bedrock/pricing/","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.08,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"Standard on-demand. Regions: US East (N. Virginia), US East (Ohio), US West (Oregon)."},{"id":"amazon-bedrock-gemma-3-4b-in","providerId":"amazon-bedrock","sku":"Gemma 3 4B","unit":"usd_per_million_input_tokens","amountUsd":0.04,"currency":"USD","sourceUrl":"https://aws.amazon.com/bedrock/pricing/","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.04,"normalizationReason":null,"priceSortEligible":true,"qualifier":"Standard on-demand. Regions: US East (N. Virginia), US East (Ohio), US West (Oregon)."},{"id":"amazon-bedrock-gemma-3-4b-out","providerId":"amazon-bedrock","sku":"Gemma 3 4B","unit":"usd_per_million_output_tokens","amountUsd":0.08,"currency":"USD","sourceUrl":"https://aws.amazon.com/bedrock/pricing/","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.08,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"Standard on-demand. Regions: US East (N. Virginia), US East (Ohio), US West (Oregon)."},{"id":"amazon-bedrock-gemma-3-12b-in","providerId":"amazon-bedrock","sku":"Gemma 3 12B","unit":"usd_per_million_input_tokens","amountUsd":0.09,"currency":"USD","sourceUrl":"https://aws.amazon.com/bedrock/pricing/","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.09,"normalizationReason":null,"priceSortEligible":true,"qualifier":"Standard on-demand. Regions: US East (N. Virginia), US East (Ohio), US West (Oregon)."},{"id":"amazon-bedrock-gemma-3-12b-out","providerId":"amazon-bedrock","sku":"Gemma 3 12B","unit":"usd_per_million_output_tokens","amountUsd":0.29,"currency":"USD","sourceUrl":"https://aws.amazon.com/bedrock/pricing/","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.29,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"Standard on-demand. Regions: US East (N. Virginia), US East (Ohio), US West (Oregon)."},{"id":"amazon-bedrock-gemma-3-27b-in","providerId":"amazon-bedrock","sku":"Gemma 3 27B","unit":"usd_per_million_input_tokens","amountUsd":0.23,"currency":"USD","sourceUrl":"https://aws.amazon.com/bedrock/pricing/","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.23,"normalizationReason":null,"priceSortEligible":true,"qualifier":"Standard on-demand. Regions: US East (N. Virginia), US East (Ohio), US West (Oregon)."},{"id":"amazon-bedrock-gemma-3-27b-out","providerId":"amazon-bedrock","sku":"Gemma 3 27B","unit":"usd_per_million_output_tokens","amountUsd":0.38,"currency":"USD","sourceUrl":"https://aws.amazon.com/bedrock/pricing/","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.38,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"Standard on-demand. Regions: US East (N. Virginia), US East (Ohio), US West (Oregon)."},{"id":"amazon-bedrock-gemma-4-31b-frankfurt-in","providerId":"amazon-bedrock","sku":"Gemma 4 31B Frankfurt","unit":"usd_per_million_input_tokens","amountUsd":0.17,"currency":"USD","sourceUrl":"https://aws.amazon.com/bedrock/pricing/","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.17,"normalizationReason":"regional_price_not_collapsed","priceSortEligible":false,"qualifier":"Europe (Frankfurt)"},{"id":"amazon-bedrock-gemma-4-31b-frankfurt-out","providerId":"amazon-bedrock","sku":"Gemma 4 31B Frankfurt","unit":"usd_per_million_output_tokens","amountUsd":0.48,"currency":"USD","sourceUrl":"https://aws.amazon.com/bedrock/pricing/","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.48,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"Europe (Frankfurt)"},{"id":"amazon-bedrock-gemma-4-26b-a4b-frankfurt-in","providerId":"amazon-bedrock","sku":"Gemma 4 26B A4B Frankfurt","unit":"usd_per_million_input_tokens","amountUsd":0.16,"currency":"USD","sourceUrl":"https://aws.amazon.com/bedrock/pricing/","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.16,"normalizationReason":"regional_price_not_collapsed","priceSortEligible":false,"qualifier":"Europe (Frankfurt)"},{"id":"amazon-bedrock-gemma-4-26b-a4b-frankfurt-out","providerId":"amazon-bedrock","sku":"Gemma 4 26B A4B Frankfurt","unit":"usd_per_million_output_tokens","amountUsd":0.48,"currency":"USD","sourceUrl":"https://aws.amazon.com/bedrock/pricing/","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.48,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"Europe (Frankfurt)"},{"id":"amazon-bedrock-gemma-4-e2b-frankfurt-in","providerId":"amazon-bedrock","sku":"Gemma 4 E2B Frankfurt","unit":"usd_per_million_input_tokens","amountUsd":0.05,"currency":"USD","sourceUrl":"https://aws.amazon.com/bedrock/pricing/","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.05,"normalizationReason":"regional_price_not_collapsed","priceSortEligible":false,"qualifier":"Europe (Frankfurt)"},{"id":"amazon-bedrock-gemma-4-e2b-frankfurt-out","providerId":"amazon-bedrock","sku":"Gemma 4 E2B Frankfurt","unit":"usd_per_million_output_tokens","amountUsd":0.1,"currency":"USD","sourceUrl":"https://aws.amazon.com/bedrock/pricing/","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.1,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"Europe (Frankfurt)"},{"id":"amazon-bedrock-gemma-3-4b-mumbai-ireland-milan-in","providerId":"amazon-bedrock","sku":"Gemma 3 4B Mumbai Ireland Milan","unit":"usd_per_million_input_tokens","amountUsd":0.05,"currency":"USD","sourceUrl":"https://aws.amazon.com/bedrock/pricing/","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.05,"normalizationReason":"regional_price_not_collapsed","priceSortEligible":false,"qualifier":"Asia Pacific (Mumbai), Europe (Ireland), Europe (Milan)"},{"id":"amazon-bedrock-gemma-3-4b-mumbai-ireland-milan-out","providerId":"amazon-bedrock","sku":"Gemma 3 4B Mumbai Ireland Milan","unit":"usd_per_million_output_tokens","amountUsd":0.09,"currency":"USD","sourceUrl":"https://aws.amazon.com/bedrock/pricing/","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.09,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"Asia Pacific (Mumbai), Europe (Ireland), Europe (Milan)"},{"id":"amazon-bedrock-gemma-3-12b-mumbai-ireland-milan-in","providerId":"amazon-bedrock","sku":"Gemma 3 12B Mumbai Ireland Milan","unit":"usd_per_million_input_tokens","amountUsd":0.11,"currency":"USD","sourceUrl":"https://aws.amazon.com/bedrock/pricing/","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.11,"normalizationReason":"regional_price_not_collapsed","priceSortEligible":false,"qualifier":"Asia Pacific (Mumbai), Europe (Ireland), Europe (Milan)"},{"id":"amazon-bedrock-gemma-3-12b-mumbai-ireland-milan-out","providerId":"amazon-bedrock","sku":"Gemma 3 12B Mumbai Ireland Milan","unit":"usd_per_million_output_tokens","amountUsd":0.34,"currency":"USD","sourceUrl":"https://aws.amazon.com/bedrock/pricing/","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.34,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"Asia Pacific (Mumbai), Europe (Ireland), Europe (Milan)"},{"id":"amazon-bedrock-gemma-3-27b-mumbai-ireland-milan-in","providerId":"amazon-bedrock","sku":"Gemma 3 27B Mumbai Ireland Milan","unit":"usd_per_million_input_tokens","amountUsd":0.27,"currency":"USD","sourceUrl":"https://aws.amazon.com/bedrock/pricing/","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.27,"normalizationReason":"regional_price_not_collapsed","priceSortEligible":false,"qualifier":"Asia Pacific (Mumbai), Europe (Ireland), Europe (Milan)"},{"id":"amazon-bedrock-gemma-3-27b-mumbai-ireland-milan-out","providerId":"amazon-bedrock","sku":"Gemma 3 27B Mumbai Ireland Milan","unit":"usd_per_million_output_tokens","amountUsd":0.45,"currency":"USD","sourceUrl":"https://aws.amazon.com/bedrock/pricing/","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.45,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"Asia Pacific (Mumbai), Europe (Ireland), Europe (Milan)"},{"id":"amazon-bedrock-gemma-3-4b-sao-paulo-tokyo-in","providerId":"amazon-bedrock","sku":"Gemma 3 4B Sao Paulo Tokyo","unit":"usd_per_million_input_tokens","amountUsd":0.05,"currency":"USD","sourceUrl":"https://aws.amazon.com/bedrock/pricing/","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.05,"normalizationReason":"regional_price_not_collapsed","priceSortEligible":false,"qualifier":"South America (Sao Paulo) and Asia Pacific (Tokyo)"},{"id":"amazon-bedrock-gemma-3-4b-sao-paulo-tokyo-out","providerId":"amazon-bedrock","sku":"Gemma 3 4B Sao Paulo Tokyo","unit":"usd_per_million_output_tokens","amountUsd":0.1,"currency":"USD","sourceUrl":"https://aws.amazon.com/bedrock/pricing/","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.1,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"South America (Sao Paulo) and Asia Pacific (Tokyo)"},{"id":"amazon-bedrock-gemma-3-12b-sao-paulo-tokyo-in","providerId":"amazon-bedrock","sku":"Gemma 3 12B Sao Paulo Tokyo","unit":"usd_per_million_input_tokens","amountUsd":0.11,"currency":"USD","sourceUrl":"https://aws.amazon.com/bedrock/pricing/","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.11,"normalizationReason":"regional_price_not_collapsed","priceSortEligible":false,"qualifier":"South America (Sao Paulo) and Asia Pacific (Tokyo)"},{"id":"amazon-bedrock-gemma-3-12b-sao-paulo-tokyo-out","providerId":"amazon-bedrock","sku":"Gemma 3 12B Sao Paulo Tokyo","unit":"usd_per_million_output_tokens","amountUsd":0.35,"currency":"USD","sourceUrl":"https://aws.amazon.com/bedrock/pricing/","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.35,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"South America (Sao Paulo) and Asia Pacific (Tokyo)"},{"id":"amazon-bedrock-gemma-3-27b-sao-paulo-tokyo-in","providerId":"amazon-bedrock","sku":"Gemma 3 27B Sao Paulo Tokyo","unit":"usd_per_million_input_tokens","amountUsd":0.27,"currency":"USD","sourceUrl":"https://aws.amazon.com/bedrock/pricing/","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.27,"normalizationReason":"regional_price_not_collapsed","priceSortEligible":false,"qualifier":"South America (Sao Paulo) and Asia Pacific (Tokyo)"},{"id":"amazon-bedrock-gemma-3-27b-sao-paulo-tokyo-out","providerId":"amazon-bedrock","sku":"Gemma 3 27B Sao Paulo Tokyo","unit":"usd_per_million_output_tokens","amountUsd":0.45,"currency":"USD","sourceUrl":"https://aws.amazon.com/bedrock/pricing/","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.45,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"South America (Sao Paulo) and Asia Pacific (Tokyo)"},{"id":"amazon-bedrock-llama-2-chat-13b-in","providerId":"amazon-bedrock","sku":"Llama 2 Chat (13B)","unit":"usd_per_million_input_tokens","amountUsd":0.75,"currency":"USD","sourceUrl":"https://aws.amazon.com/bedrock/pricing/","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.75,"normalizationReason":null,"priceSortEligible":true,"qualifier":"On-demand. Region: US East (N. Virginia) and US West (Oregon). Llama 4/3.3/3.2/3.1 price cells were not in the fetched HTML."},{"id":"amazon-bedrock-llama-2-chat-13b-out","providerId":"amazon-bedrock","sku":"Llama 2 Chat (13B)","unit":"usd_per_million_output_tokens","amountUsd":1,"currency":"USD","sourceUrl":"https://aws.amazon.com/bedrock/pricing/","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":1,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"On-demand output."},{"id":"amazon-bedrock-llama-2-chat-70b-in","providerId":"amazon-bedrock","sku":"Llama 2 Chat (70B)","unit":"usd_per_million_input_tokens","amountUsd":1.95,"currency":"USD","sourceUrl":"https://aws.amazon.com/bedrock/pricing/","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":1.95,"normalizationReason":null,"priceSortEligible":true,"qualifier":"On-demand US East/West."},{"id":"amazon-bedrock-llama-2-chat-70b-out","providerId":"amazon-bedrock","sku":"Llama 2 Chat (70B)","unit":"usd_per_million_output_tokens","amountUsd":2.56,"currency":"USD","sourceUrl":"https://aws.amazon.com/bedrock/pricing/","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":2.56,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"On-demand output."},{"id":"amazon-bedrock-rerank-3-5-usd-per-1k-queries","providerId":"amazon-bedrock","sku":"Rerank 3.5","unit":"usd_per_1k_queries","amountUsd":2,"currency":"USD","sourceUrl":"https://aws.amazon.com/bedrock/pricing/","asOf":"2026-10-03","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_1k_queries","priceSortEligible":false,"qualifier":"Cohere on-demand. A query can contain up to 100 document chunks."},{"id":"amazon-bedrock-llama-2-pretrained-13b-train","providerId":"amazon-bedrock","sku":"Llama 2 Pretrained (13B)","unit":"usd_per_million_train_tokens","amountUsd":1.49,"currency":"USD","sourceUrl":"https://aws.amazon.com/bedrock/pricing/","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":1.49,"normalizationReason":"train_tokens_not_inference_sort","priceSortEligible":false,"qualifier":"Customization table, price to train 1M tokens. Storage and provisioned inference on the same row were not folded in."},{"id":"amazon-bedrock-llama-2-pretrained-70b-train","providerId":"amazon-bedrock","sku":"Llama 2 Pretrained (70B)","unit":"usd_per_million_train_tokens","amountUsd":7.99,"currency":"USD","sourceUrl":"https://aws.amazon.com/bedrock/pricing/","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":7.99,"normalizationReason":"train_tokens_not_inference_sort","priceSortEligible":false,"qualifier":"Customization table, price to train 1M tokens."},{"id":"amazon-bedrock-llama-2-pretrained-13b-storage-usd-per-custom-model-month","providerId":"amazon-bedrock","sku":"Llama 2 Pretrained (13B) storage","unit":"usd_per_custom_model_month","amountUsd":1.95,"currency":"USD","sourceUrl":"https://aws.amazon.com/bedrock/pricing/","asOf":"2026-10-03","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_month","priceSortEligible":false,"qualifier":"Price to store each custom model per month."},{"id":"amazon-bedrock-llama-2-custom-inference-model-unit-usd-per-model-unit-hour","providerId":"amazon-bedrock","sku":"Llama 2 custom inference model unit","unit":"usd_per_model_unit_hour","amountUsd":23.5,"currency":"USD","sourceUrl":"https://aws.amazon.com/bedrock/pricing/","asOf":"2026-10-03","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_model_unit_hour","priceSortEligible":false,"qualifier":"No-commit provisioned throughput, per model unit hour. Not a GPU-hour and not coerced to tokens. Same $23.50 shown for 13B and 70B on this table."},{"id":"amazon-bedrock-claude-sonnet-5-5-in","providerId":"amazon-bedrock","sku":"Claude Sonnet 5.5","unit":"usd_per_million_input_tokens","amountUsd":2,"currency":"USD","sourceUrl":"https://aws.amazon.com/bedrock/pricing/","asOf":"2026-10-19","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":2,"normalizationReason":null,"priceSortEligible":true,"qualifier":"Input. Rendered Anthropic on-demand table under 'Global Cross-region Inference', Region US East (Ohio) (page default), 2026-10-19. Batch, cache columns and other regions not used."},{"id":"amazon-bedrock-claude-sonnet-5-5-out","providerId":"amazon-bedrock","sku":"Claude Sonnet 5.5","unit":"usd_per_million_output_tokens","amountUsd":10,"currency":"USD","sourceUrl":"https://aws.amazon.com/bedrock/pricing/","asOf":"2026-10-19","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":10,"normalizationReason":null,"priceSortEligible":false,"qualifier":"Output. Rendered Anthropic on-demand table under 'Global Cross-region Inference', Region US East (Ohio) (page default), 2026-10-19. Batch, cache columns and other regions not used."},{"id":"amazon-bedrock-claude-opus-5-5-in","providerId":"amazon-bedrock","sku":"Claude Opus 5.5","unit":"usd_per_million_input_tokens","amountUsd":4,"currency":"USD","sourceUrl":"https://aws.amazon.com/bedrock/pricing/","asOf":"2026-10-19","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":4,"normalizationReason":null,"priceSortEligible":true,"qualifier":"Input. Rendered Anthropic on-demand table under 'Global Cross-region Inference', Region US East (Ohio) (page default), 2026-10-19. Batch, cache columns and other regions not used."},{"id":"amazon-bedrock-claude-opus-5-5-out","providerId":"amazon-bedrock","sku":"Claude Opus 5.5","unit":"usd_per_million_output_tokens","amountUsd":20,"currency":"USD","sourceUrl":"https://aws.amazon.com/bedrock/pricing/","asOf":"2026-10-19","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":20,"normalizationReason":null,"priceSortEligible":false,"qualifier":"Output. Rendered Anthropic on-demand table under 'Global Cross-region Inference', Region US East (Ohio) (page default), 2026-10-19. Batch, cache columns and other regions not used."},{"id":"amazon-bedrock-claude-haiku-5-5-in","providerId":"amazon-bedrock","sku":"Claude Haiku 5.5","unit":"usd_per_million_input_tokens","amountUsd":0.1,"currency":"USD","sourceUrl":"https://aws.amazon.com/bedrock/pricing/","asOf":"2026-10-19","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.1,"normalizationReason":null,"priceSortEligible":true,"qualifier":"Input. Rendered Anthropic on-demand table under 'Global Cross-region Inference', Region US East (Ohio) (page default), 2026-10-19. Batch, cache columns and other regions not used."},{"id":"amazon-bedrock-claude-haiku-5-5-out","providerId":"amazon-bedrock","sku":"Claude Haiku 5.5","unit":"usd_per_million_output_tokens","amountUsd":0.5,"currency":"USD","sourceUrl":"https://aws.amazon.com/bedrock/pricing/","asOf":"2026-10-19","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.5,"normalizationReason":null,"priceSortEligible":false,"qualifier":"Output. Rendered Anthropic on-demand table under 'Global Cross-region Inference', Region US East (Ohio) (page default), 2026-10-19. Batch, cache columns and other regions not used."}],"notesExcerpt":"Pay-per-token for Claude, Llama, Amazon, Cohere, etc.; Provisioned Throughput for steady load. AWS marketplace billing.","notesCheck":{"status":"no_known_contradiction","pairs":[],"review":null,"note":null},"lastReviewed":"2026-09-14","scoreAsOf":"2026-09-14","website":"https://aws.amazon.com/bedrock/","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":["multi-model-router","enterprise-llm","rag-enterprise","lakehouse-llm","confidential-tee-inference","prompt-caching-optimization","hipaa-baa-llm","air-gapped-model-serve"],"alternatives":[{"id":"anthropic","slug":"anthropic","name":"Anthropic","tagline":"Depot default for serious coding and production agents. Prefer Sonnet for cost/quality; reserve Opus for hard…","website":"https://www.anthropic.com","status":"active","overall":8.42,"scoreKind":"curated_estimate","confidence":"high","scoreAsOf":"2026-10-19","deltaOverallVsSubject":0.67,"roles":["same_jtbd_runner","same_jtbd_pick"],"sharedJtbdSlugs":["enterprise-llm","prompt-caching-optimization","hipaa-baa-llm"],"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":"anthropic-fable-51-input","providerId":"anthropic","sku":"Fable 5.1","unit":"usd_per_million_input_tokens","amountUsd":10,"currency":"USD","sourceUrl":"https://claude.com/pricing","asOf":"2026-10-27","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":10,"normalizationReason":null,"priceSortEligible":true,"qualifier":"standard input; cache read/write on the same card were not folded in"},{"id":"anthropic-fable-51-output","providerId":"anthropic","sku":"Fable 5.1","unit":"usd_per_million_output_tokens","amountUsd":50,"currency":"USD","sourceUrl":"https://claude.com/pricing","asOf":"2026-10-27","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":50,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"standard output"},{"id":"anthropic-opus-55-input","providerId":"anthropic","sku":"Opus 5.5","unit":"usd_per_million_input_tokens","amountUsd":4,"currency":"USD","sourceUrl":"https://claude.com/pricing","asOf":"2026-10-27","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":4,"normalizationReason":null,"priceSortEligible":true,"qualifier":"standard input; cache read/write on the same card were not folded in"},{"id":"anthropic-opus-55-output","providerId":"anthropic","sku":"Opus 5.5","unit":"usd_per_million_output_tokens","amountUsd":20,"currency":"USD","sourceUrl":"https://claude.com/pricing","asOf":"2026-10-27","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":20,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"standard output"},{"id":"anthropic-sonnet-55-input","providerId":"anthropic","sku":"Sonnet 5.5","unit":"usd_per_million_input_tokens","amountUsd":2,"currency":"USD","sourceUrl":"https://claude.com/pricing","asOf":"2026-10-27","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":2,"normalizationReason":null,"priceSortEligible":true,"qualifier":"standard input; cache read/write on the same card were not folded in"},{"id":"anthropic-sonnet-55-output","providerId":"anthropic","sku":"Sonnet 5.5","unit":"usd_per_million_output_tokens","amountUsd":10,"currency":"USD","sourceUrl":"https://claude.com/pricing","asOf":"2026-10-27","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":10,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"standard output"},{"id":"anthropic-haiku-45-input","providerId":"anthropic","sku":"Haiku 4.5","unit":"usd_per_million_input_tokens","amountUsd":1,"currency":"USD","sourceUrl":"https://claude.com/pricing","asOf":"2026-10-27","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":1,"normalizationReason":null,"priceSortEligible":true,"qualifier":"standard input; cache read/write on the same card were not folded in","lifecycle":"legacy","lifecycleSourceUrl":"https://platform.claude.com/docs/en/about-claude/models/overview","lifecycleAsOf":"2026-10-21"},{"id":"anthropic-haiku-45-output","providerId":"anthropic","sku":"Haiku 4.5","unit":"usd_per_million_output_tokens","amountUsd":5,"currency":"USD","sourceUrl":"https://claude.com/pricing","asOf":"2026-10-27","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":5,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"standard output","lifecycle":"legacy","lifecycleSourceUrl":"https://platform.claude.com/docs/en/about-claude/models/overview","lifecycleAsOf":"2026-10-21"},{"id":"anthropic-web-search","providerId":"anthropic","sku":"Web search","unit":"usd_per_1k_searches","amountUsd":10,"currency":"USD","sourceUrl":"https://claude.com/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_1k_searches","priceSortEligible":false,"qualifier":"page says does not include input and output tokens"},{"id":"anthropic-code-exec-hour","providerId":"anthropic","sku":"Code execution additional hours","unit":"usd_per_hour","amountUsd":0.05,"currency":"USD","sourceUrl":"https://claude.com/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_hour","priceSortEligible":false,"qualifier":"per hour per container"},{"id":"anthropic-managed-agents-session-hour","providerId":"anthropic","sku":"Managed Agents session runtime","unit":"usd_per_session_hour","amountUsd":0.08,"currency":"USD","sourceUrl":"https://claude.com/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_session_hour","priceSortEligible":false,"qualifier":"Managed Agents card ('$0.08 per session-hour for active runtime'; 'Standard token rates apply.'), added 2026-10-27 (v0.12.149) as a reviewed addition. The platform pricing docs table says 'Session runtime $0.08 USD per session-hour', metered on 'running status duration' ('Runtime is measured to the millisecond and accrues only while the session's status is running'). Token usage is billed separately at standard rates and is not included. Not coerced to per-hour, per-container-hour or to $/1M; never blended with anthropic-code-exec-hour."},{"id":"anthropic-haiku-55-input-le-100k","providerId":"anthropic","sku":"Haiku 5.5 (prompts up to 100K tokens)","unit":"usd_per_million_input_tokens","amountUsd":0.1,"currency":"USD","sourceUrl":"https://platform.claude.com/docs/en/about-claude/pricing","asOf":"2026-10-27","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.1,"normalizationReason":null,"priceSortEligible":true,"qualifier":"Base input, prompts up to 100,000 tokens (docs pricing table). Cache write 5m $0.125, cache hit $0.01 not folded in. The claude.com/pricing card agrees as of 2026-10-27 (the 2026-10-21 card/docs mismatch is resolved)."},{"id":"anthropic-haiku-55-output-le-100k","providerId":"anthropic","sku":"Haiku 5.5 (prompts up to 100K tokens)","unit":"usd_per_million_output_tokens","amountUsd":0.5,"currency":"USD","sourceUrl":"https://platform.claude.com/docs/en/about-claude/pricing","asOf":"2026-10-27","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.5,"normalizationReason":null,"priceSortEligible":false,"qualifier":"Output, prompts up to 100,000 tokens (docs pricing table)."},{"id":"anthropic-haiku-55-input-gt-100k","providerId":"anthropic","sku":"Haiku 5.5 (prompts over 100K tokens)","unit":"usd_per_million_input_tokens","amountUsd":0.5,"currency":"USD","sourceUrl":"https://platform.claude.com/docs/en/about-claude/pricing","asOf":"2026-10-27","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.5,"normalizationReason":null,"priceSortEligible":false,"qualifier":"Base input, prompts over 100,000 tokens (whole request priced at this rate, including cache reads/writes in the count). Cache write 5m $0.625, cache hit $0.05 not folded in."},{"id":"anthropic-haiku-55-output-gt-100k","providerId":"anthropic","sku":"Haiku 5.5 (prompts over 100K tokens)","unit":"usd_per_million_output_tokens","amountUsd":2.5,"currency":"USD","sourceUrl":"https://platform.claude.com/docs/en/about-claude/pricing","asOf":"2026-10-27","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":2.5,"normalizationReason":null,"priceSortEligible":false,"qualifier":"Output, prompts over 100,000 tokens."}],"notesExcerpt":"Sonnet 5 ~$2/$10 per 1M; Opus ~$5/$25; Haiku 4.5 ~$1/$5; Fable higher. Prompt caching + batch. Managed Agents session-hour fees. US-only inference ~1.1x.","notesCheck":{"status":"no_known_contradiction","pairs":[],"review":null,"note":null},"lastReviewed":"2026-10-19","scoreAsOf":"2026-10-19","website":"https://www.anthropic.com","doNotParse":"Do not parse pricingNotes. Use rows only. normalizedUsdPerMillionTokens is a single number only when this provider has exactly one sourced token row. Input/output, context tiers, and non-token units stay null at this level.","gap":"Partial coverage. Providers without a fetched SKU are omitted. See GET /api/pricing."},"decideHint":"/api/decide?jtbd=enterprise-llm","human":"/providers/anthropic","compare":"/compare/amazon-bedrock-vs-anthropic"},{"id":"openrouter","slug":"openrouter","name":"OpenRouter","tagline":"Best multi-model router for agents that need failover and experimentation. Pin providers in production; don’t…","website":"https://openrouter.ai","status":"active","overall":8,"scoreKind":"curated_estimate","confidence":"high","scoreAsOf":"2026-09-14","deltaOverallVsSubject":0.25,"roles":["same_jtbd_pick"],"sharedJtbdSlugs":["multi-model-router"],"pricing":{"normalizedUsdPerMillionTokens":null,"normalizationStatus":"ambiguous","normalizationReason":"input_output_split_not_a_single_rate","shape":"sourced_rows","filterable":false,"priceSortEligible":true,"priceSortKeyUsdPerMillionInputTokens":2,"rows":[{"id":"openrouter-claude-sonnet-55-input","providerId":"openrouter","sku":"anthropic/claude-sonnet-5.5","unit":"usd_per_million_input_tokens","amountUsd":2,"currency":"USD","sourceUrl":"https://openrouter.ai/api/v1/models","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":2,"normalizationReason":"per_token_field_times_1e6","priceSortEligible":true,"qualifier":"OpenRouter pass-through field, not copied onto the anthropic provider. pricing.prompt raw 0.000002. Docs: cost per input token, USD.","raw":{"field":"pricing.prompt","amount":"0.000002","unit":"usd_per_token","unitSourceUrl":"https://openrouter.ai/docs/guides/overview/models"}},{"id":"openrouter-claude-sonnet-55-output","providerId":"openrouter","sku":"anthropic/claude-sonnet-5.5","unit":"usd_per_million_output_tokens","amountUsd":10,"currency":"USD","sourceUrl":"https://openrouter.ai/api/v1/models","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":10,"normalizationReason":"per_token_field_times_1e6","priceSortEligible":false,"qualifier":"pricing.completion raw 0.00001","raw":{"field":"pricing.completion","amount":"0.00001","unit":"usd_per_token","unitSourceUrl":"https://openrouter.ai/docs/guides/overview/models"}},{"id":"openrouter-grok-47-input","providerId":"openrouter","sku":"x-ai/grok-4.7","unit":"usd_per_million_input_tokens","amountUsd":2,"currency":"USD","sourceUrl":"https://openrouter.ai/api/v1/models","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":2,"normalizationReason":"per_token_field_times_1e6","priceSortEligible":true,"qualifier":"Base prompt field only. Response also has overrides at min_prompt_tokens 200000 (prompt 0.000004). Not blended.","raw":{"field":"pricing.prompt","amount":"0.000002","unit":"usd_per_token","unitSourceUrl":"https://openrouter.ai/docs/guides/overview/models"}},{"id":"openrouter-grok-47-output","providerId":"openrouter","sku":"x-ai/grok-4.7","unit":"usd_per_million_output_tokens","amountUsd":6,"currency":"USD","sourceUrl":"https://openrouter.ai/api/v1/models","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":6,"normalizationReason":"per_token_field_times_1e6","priceSortEligible":false,"qualifier":"pricing.completion raw 0.000006","raw":{"field":"pricing.completion","amount":"0.000006","unit":"usd_per_token","unitSourceUrl":"https://openrouter.ai/docs/guides/overview/models"}}],"notesExcerpt":"As of 2026-09-14: Multi-provider LLM router with OpenAI-compatible API; pass-through model pricing plus small platform fee. Best for prototyping multi-model and failover; production should pin critical paths to direct providers.","notesCheck":{"status":"no_known_contradiction","pairs":[],"review":null,"note":null},"lastReviewed":"2026-09-14","scoreAsOf":"2026-09-14","website":"https://openrouter.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=multi-model-router","human":"/providers/openrouter","compare":"/compare/amazon-bedrock-vs-openrouter"},{"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":0.2,"roles":["same_jtbd_pick"],"sharedJtbdSlugs":["rag-enterprise"],"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=rag-enterprise","human":"/providers/cohere","compare":"/compare/amazon-bedrock-vs-cohere"},{"id":"nvidia-nim","slug":"nvidia-nim","name":"NVIDIA NIM / NGC","tagline":"Choose when you self-host inference on NVIDIA GPUs and want blessed containers. For serverless tokens use…","website":"https://www.nvidia.com/en-us/ai/","status":"active","overall":7.66,"scoreKind":"curated_estimate","confidence":"medium","scoreAsOf":"2026-10-19","deltaOverallVsSubject":-0.09,"roles":["same_jtbd_pick"],"sharedJtbdSlugs":["air-gapped-model-serve"],"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 (nvidia.com/en-us/ai-data-science/products/nim-microservices, fetched 2026-10-24; NVIDIA publishes no NIM price page, and this product page states no price figures, so production licence price stays null — 'Contact Sales'): hosted prototyping 'Start Prototyping f…","notesCheck":{"status":"no_known_contradiction","pairs":[],"review":null,"note":null},"lastReviewed":"2026-10-19","scoreAsOf":"2026-10-19","website":"https://www.nvidia.com/en-us/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":"No sourced price row for this provider. pricingNotes stay prose. See research/gaps.md."},"decideHint":"/api/decide?jtbd=air-gapped-model-serve","human":"/providers/nvidia-nim","compare":"/compare/amazon-bedrock-vs-nvidia-nim"},{"id":"chutes","slug":"chutes","name":"Chutes","tagline":"Budget open-model overflow with a now-pinned public TEE matrix. Depot open-model production pick stays…","website":"https://chutes.ai","status":"active","overall":7.29,"scoreKind":"curated_estimate","confidence":"high","scoreAsOf":"2026-09-14","deltaOverallVsSubject":-0.46,"roles":["same_jtbd_pick"],"sharedJtbdSlugs":["confidential-tee-inference"],"pricing":{"normalizedUsdPerMillionTokens":null,"normalizationStatus":"ambiguous","normalizationReason":"input_output_split_not_a_single_rate","shape":"sourced_rows","filterable":false,"priceSortEligible":true,"priceSortKeyUsdPerMillionInputTokens":0.039,"rows":[{"id":"chutes-mistral-nemo-instruct-2407-unsloth-mistral-nemo-instruct-2407-tee-in","providerId":"chutes","sku":"Mistral-Nemo-Instruct-2407 (unsloth/Mistral-Nemo-Instruct-2407-TEE)","unit":"usd_per_million_input_tokens","amountUsd":0.0245,"currency":"USD","sourceUrl":"https://chutes.ai/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.0245,"normalizationReason":null,"priceSortEligible":false,"qualifier":"Public TEE inference, USD per 1M tokens. Workload estimate on the same card was not used. TAO column not used. Not on chutes.ai/pricing 2026-10-27 (v0.12.141): the Model pricing table no longer lists this model; amount kept from 2026-10-03, not reconfirmed (asOf unchanged).","sourceStatus":"unverified","sourceStatusReason":"model_not_on_source_page: on 2026-10-27 the Model pricing table lists gemma-4-31B-turbo, Qwen3.8-27B, Qwen3.6-27B, DeepSeek-V4-Flash-0731, Kimi K2.6, Qwen 3.5, DeepSeek-V3.2, GLM-5.1, GLM-5.2 and Kimi-K3 (re-checked twice, also absent in the 2026-10-27 06:06 ET fetch); Mistral-Nemo-Instruct-2407 is no longer on https://chutes.ai/pricing (no occurrence of the name anywhere in the page text). Kept for history, never ranked.","sourceStatusCheckedOn":"2026-10-27"},{"id":"chutes-mistral-nemo-instruct-2407-unsloth-mistral-nemo-instruct-2407-tee-out","providerId":"chutes","sku":"Mistral-Nemo-Instruct-2407 (unsloth/Mistral-Nemo-Instruct-2407-TEE)","unit":"usd_per_million_output_tokens","amountUsd":0.0978,"currency":"USD","sourceUrl":"https://chutes.ai/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.0978,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"Public TEE inference output per 1M tokens. Not on chutes.ai/pricing 2026-10-27 (v0.12.141): the Model pricing table no longer lists this model; amount kept from 2026-10-03, not reconfirmed (asOf unchanged).","sourceStatus":"unverified","sourceStatusReason":"model_not_on_source_page: on 2026-10-27 the Model pricing table lists gemma-4-31B-turbo, Qwen3.8-27B, Qwen3.6-27B, DeepSeek-V4-Flash-0731, Kimi K2.6, Qwen 3.5, DeepSeek-V3.2, GLM-5.1, GLM-5.2 and Kimi-K3 (re-checked twice, also absent in the 2026-10-27 06:06 ET fetch); Mistral-Nemo-Instruct-2407 is no longer on https://chutes.ai/pricing (no occurrence of the name anywhere in the page text). Kept for history, never ranked.","sourceStatusCheckedOn":"2026-10-27"},{"id":"chutes-nemotron-3-nano-omni-30b-nemotron-3-nano-omni-30b-tee-in","providerId":"chutes","sku":"Nemotron-3-Nano-Omni-30B (Nemotron-3-Nano-Omni-30B-TEE)","unit":"usd_per_million_input_tokens","amountUsd":0.0245,"currency":"USD","sourceUrl":"https://chutes.ai/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.0245,"normalizationReason":null,"priceSortEligible":false,"qualifier":"Public TEE inference, USD per 1M tokens. Workload estimate on the same card was not used. TAO column not used. Not on chutes.ai/pricing 2026-10-27 (v0.12.141): the Model pricing table no longer lists this model; amount kept from 2026-10-03, not reconfirmed (asOf unchanged).","sourceStatus":"unverified","sourceStatusReason":"model_not_on_source_page: on 2026-10-27 the Model pricing table lists gemma-4-31B-turbo, Qwen3.8-27B, Qwen3.6-27B, DeepSeek-V4-Flash-0731, Kimi K2.6, Qwen 3.5, DeepSeek-V3.2, GLM-5.1, GLM-5.2 and Kimi-K3 (re-checked twice, also absent in the 2026-10-27 06:06 ET fetch); Nemotron-3-Nano-Omni-30B is no longer on https://chutes.ai/pricing (no occurrence of the name anywhere in the page text). Kept for history, never ranked.","sourceStatusCheckedOn":"2026-10-27"},{"id":"chutes-nemotron-3-nano-omni-30b-nemotron-3-nano-omni-30b-tee-out","providerId":"chutes","sku":"Nemotron-3-Nano-Omni-30B (Nemotron-3-Nano-Omni-30B-TEE)","unit":"usd_per_million_output_tokens","amountUsd":0.0978,"currency":"USD","sourceUrl":"https://chutes.ai/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.0978,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"Public TEE inference output per 1M tokens. Not on chutes.ai/pricing 2026-10-27 (v0.12.141): the Model pricing table no longer lists this model; amount kept from 2026-10-03, not reconfirmed (asOf unchanged).","sourceStatus":"unverified","sourceStatusReason":"model_not_on_source_page: on 2026-10-27 the Model pricing table lists gemma-4-31B-turbo, Qwen3.8-27B, Qwen3.6-27B, DeepSeek-V4-Flash-0731, Kimi K2.6, Qwen 3.5, DeepSeek-V3.2, GLM-5.1, GLM-5.2 and Kimi-K3 (re-checked twice, also absent in the 2026-10-27 06:06 ET fetch); Nemotron-3-Nano-Omni-30B is no longer on https://chutes.ai/pricing (no occurrence of the name anywhere in the page text). Kept for history, never ranked.","sourceStatusCheckedOn":"2026-10-27"},{"id":"chutes-qwen3-32b-qwen-qwen3-32b-tee-in","providerId":"chutes","sku":"Qwen3-32B (Qwen/Qwen3-32B-TEE)","unit":"usd_per_million_input_tokens","amountUsd":0.104,"currency":"USD","sourceUrl":"https://chutes.ai/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.104,"normalizationReason":null,"priceSortEligible":false,"qualifier":"Public TEE inference, USD per 1M tokens. Workload estimate on the same card was not used. TAO column not used. Not on chutes.ai/pricing 2026-10-27 (v0.12.141): the Model pricing table no longer lists this model; amount kept from 2026-10-03, not reconfirmed (asOf unchanged).","sourceStatus":"unverified","sourceStatusReason":"model_not_on_source_page: on 2026-10-27 the Model pricing table lists gemma-4-31B-turbo, Qwen3.8-27B, Qwen3.6-27B, DeepSeek-V4-Flash-0731, Kimi K2.6, Qwen 3.5, DeepSeek-V3.2, GLM-5.1, GLM-5.2 and Kimi-K3 (re-checked twice, also absent in the 2026-10-27 06:06 ET fetch); Qwen3-32B is no longer on https://chutes.ai/pricing (no occurrence of the name anywhere in the page text). Kept for history, never ranked.","sourceStatusCheckedOn":"2026-10-27"},{"id":"chutes-qwen3-32b-qwen-qwen3-32b-tee-out","providerId":"chutes","sku":"Qwen3-32B (Qwen/Qwen3-32B-TEE)","unit":"usd_per_million_output_tokens","amountUsd":0.416,"currency":"USD","sourceUrl":"https://chutes.ai/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.416,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"Public TEE inference output per 1M tokens. Not on chutes.ai/pricing 2026-10-27 (v0.12.141): the Model pricing table no longer lists this model; amount kept from 2026-10-03, not reconfirmed (asOf unchanged).","sourceStatus":"unverified","sourceStatusReason":"model_not_on_source_page: on 2026-10-27 the Model pricing table lists gemma-4-31B-turbo, Qwen3.8-27B, Qwen3.6-27B, DeepSeek-V4-Flash-0731, Kimi K2.6, Qwen 3.5, DeepSeek-V3.2, GLM-5.1, GLM-5.2 and Kimi-K3 (re-checked twice, also absent in the 2026-10-27 06:06 ET fetch); Qwen3-32B is no longer on https://chutes.ai/pricing (no occurrence of the name anywhere in the page text). Kept for history, never ranked.","sourceStatusCheckedOn":"2026-10-27"},{"id":"chutes-gemma-4-31b-turbo-google-gemma-4-31b-turbo-tee-in","providerId":"chutes","sku":"gemma-4-31B-turbo (google/gemma-4-31B-turbo-TEE)","unit":"usd_per_million_input_tokens","amountUsd":0.12,"currency":"USD","sourceUrl":"https://chutes.ai/pricing","asOf":"2026-10-27","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.12,"normalizationReason":null,"priceSortEligible":true,"qualifier":"Public TEE inference, USD per 1M tokens. Workload estimate on the same card was not used. TAO column not used. Reconfirmed 2026-10-27 (v0.12.141). The page says per-model rates are 'pulled live from our pricing API'; cached-input rate on the same card not stored."},{"id":"chutes-gemma-4-31b-turbo-google-gemma-4-31b-turbo-tee-out","providerId":"chutes","sku":"gemma-4-31B-turbo (google/gemma-4-31B-turbo-TEE)","unit":"usd_per_million_output_tokens","amountUsd":0.37,"currency":"USD","sourceUrl":"https://chutes.ai/pricing","asOf":"2026-10-27","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.37,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"Public TEE inference output per 1M tokens. Reconfirmed 2026-10-27 (v0.12.141). The page says per-model rates are 'pulled live from our pricing API'; cached-input rate on the same card not stored."},{"id":"chutes-qwen3-235b-a22b-thinking-2507-qwen-qwen3-235b-a22b-thinking-2507-tee-in","providerId":"chutes","sku":"Qwen3-235B-A22B-Thinking-2507 (Qwen/Qwen3-235B-A22B-Thinking-2507-TEE)","unit":"usd_per_million_input_tokens","amountUsd":0.2989,"currency":"USD","sourceUrl":"https://chutes.ai/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.2989,"normalizationReason":null,"priceSortEligible":false,"qualifier":"Public TEE inference, USD per 1M tokens. Workload estimate on the same card was not used. TAO column not used. Not on chutes.ai/pricing 2026-10-27 (v0.12.141): the Model pricing table no longer lists this model; amount kept from 2026-10-03, not reconfirmed (asOf unchanged).","sourceStatus":"unverified","sourceStatusReason":"model_not_on_source_page: on 2026-10-27 the Model pricing table lists gemma-4-31B-turbo, Qwen3.8-27B, Qwen3.6-27B, DeepSeek-V4-Flash-0731, Kimi K2.6, Qwen 3.5, DeepSeek-V3.2, GLM-5.1, GLM-5.2 and Kimi-K3 (re-checked twice, also absent in the 2026-10-27 06:06 ET fetch); Qwen3-235B-A22B-Thinking-2507 is no longer on https://chutes.ai/pricing (no occurrence of the name anywhere in the page text). Kept for history, never ranked.","sourceStatusCheckedOn":"2026-10-27"},{"id":"chutes-qwen3-235b-a22b-thinking-2507-qwen-qwen3-235b-a22b-thinking-2507-tee-out","providerId":"chutes","sku":"Qwen3-235B-A22B-Thinking-2507 (Qwen/Qwen3-235B-A22B-Thinking-2507-TEE)","unit":"usd_per_million_output_tokens","amountUsd":1.1957,"currency":"USD","sourceUrl":"https://chutes.ai/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":1.1957,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"Public TEE inference output per 1M tokens. Not on chutes.ai/pricing 2026-10-27 (v0.12.141): the Model pricing table no longer lists this model; amount kept from 2026-10-03, not reconfirmed (asOf unchanged).","sourceStatus":"unverified","sourceStatusReason":"model_not_on_source_page: on 2026-10-27 the Model pricing table lists gemma-4-31B-turbo, Qwen3.8-27B, Qwen3.6-27B, DeepSeek-V4-Flash-0731, Kimi K2.6, Qwen 3.5, DeepSeek-V3.2, GLM-5.1, GLM-5.2 and Kimi-K3 (re-checked twice, also absent in the 2026-10-27 06:06 ET fetch); Qwen3-235B-A22B-Thinking-2507 is no longer on https://chutes.ai/pricing (no occurrence of the name anywhere in the page text). Kept for history, never ranked.","sourceStatusCheckedOn":"2026-10-27"},{"id":"chutes-qwen3-8-27b-qwen-qwen3-8-27b-tee-in","providerId":"chutes","sku":"Qwen3.8-27B (Qwen/Qwen3.8-27B-TEE)","unit":"usd_per_million_input_tokens","amountUsd":0.039,"currency":"USD","sourceUrl":"https://chutes.ai/pricing","asOf":"2026-10-27","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.039,"normalizationReason":null,"priceSortEligible":true,"qualifier":"Public TEE inference, USD per 1M tokens. Workload estimate on the same card was not used. TAO column not used. Reconfirmed 2026-10-27 (v0.12.141). The page says per-model rates are 'pulled live from our pricing API'; cached-input rate on the same card not stored."},{"id":"chutes-qwen3-8-27b-qwen-qwen3-8-27b-tee-out","providerId":"chutes","sku":"Qwen3.8-27B (Qwen/Qwen3.8-27B-TEE)","unit":"usd_per_million_output_tokens","amountUsd":1.25,"currency":"USD","sourceUrl":"https://chutes.ai/pricing","asOf":"2026-10-27","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":1.25,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"Public TEE inference output per 1M tokens. Reconfirmed 2026-10-27 (v0.12.141). The page says per-model rates are 'pulled live from our pricing API'; cached-input rate on the same card not stored."},{"id":"chutes-qwen3-6-27b-qwen-qwen3-6-27b-tee-in","providerId":"chutes","sku":"Qwen3.6-27B (Qwen/Qwen3.6-27B-TEE)","unit":"usd_per_million_input_tokens","amountUsd":0.25,"currency":"USD","sourceUrl":"https://chutes.ai/pricing","asOf":"2026-10-27","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.25,"normalizationReason":null,"priceSortEligible":true,"qualifier":"Public TEE inference, USD per 1M tokens. Workload estimate on the same card was not used. TAO column not used. Reconfirmed 2026-10-27 (v0.12.141). The page says per-model rates are 'pulled live from our pricing API'; cached-input rate on the same card not stored."},{"id":"chutes-qwen3-6-27b-qwen-qwen3-6-27b-tee-out","providerId":"chutes","sku":"Qwen3.6-27B (Qwen/Qwen3.6-27B-TEE)","unit":"usd_per_million_output_tokens","amountUsd":2,"currency":"USD","sourceUrl":"https://chutes.ai/pricing","asOf":"2026-10-27","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":2,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"Public TEE inference output per 1M tokens. Reconfirmed 2026-10-27 (v0.12.141). The page says per-model rates are 'pulled live from our pricing API'; cached-input rate on the same card not stored."},{"id":"chutes-deepseek-v4-flash-0731-deepseek-ai-deepseek-v4-flash-0731-tee-in","providerId":"chutes","sku":"DeepSeek-V4-Flash-0731 (deepseek-ai/DeepSeek-V4-Flash-0731-TEE)","unit":"usd_per_million_input_tokens","amountUsd":0.44,"currency":"USD","sourceUrl":"https://chutes.ai/pricing","asOf":"2026-10-27","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.44,"normalizationReason":null,"priceSortEligible":true,"qualifier":"Public TEE inference, USD per 1M tokens. Workload estimate on the same card was not used. TAO column not used. Reconfirmed 2026-10-27 (v0.12.141). The page says per-model rates are 'pulled live from our pricing API'; cached-input rate on the same card not stored."},{"id":"chutes-deepseek-v4-flash-0731-deepseek-ai-deepseek-v4-flash-0731-tee-out","providerId":"chutes","sku":"DeepSeek-V4-Flash-0731 (deepseek-ai/DeepSeek-V4-Flash-0731-TEE)","unit":"usd_per_million_output_tokens","amountUsd":1.32,"currency":"USD","sourceUrl":"https://chutes.ai/pricing","asOf":"2026-10-27","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":1.32,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"Public TEE inference output per 1M tokens. Reconfirmed 2026-10-27 (v0.12.141). The page says per-model rates are 'pulled live from our pricing API'; cached-input rate on the same card not stored."},{"id":"chutes-qwen-3-5-qwen-qwen3-5-397b-a17b-tee-in","providerId":"chutes","sku":"Qwen 3.5 (Qwen/Qwen3.5-397B-A17B-TEE)","unit":"usd_per_million_input_tokens","amountUsd":0.45,"currency":"USD","sourceUrl":"https://chutes.ai/pricing","asOf":"2026-10-27","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.45,"normalizationReason":null,"priceSortEligible":true,"qualifier":"Public TEE inference, USD per 1M tokens. Workload estimate on the same card was not used. TAO column not used. Reconfirmed 2026-10-27 (v0.12.141). The page says per-model rates are 'pulled live from our pricing API'; cached-input rate on the same card not stored."},{"id":"chutes-qwen-3-5-qwen-qwen3-5-397b-a17b-tee-out","providerId":"chutes","sku":"Qwen 3.5 (Qwen/Qwen3.5-397B-A17B-TEE)","unit":"usd_per_million_output_tokens","amountUsd":3,"currency":"USD","sourceUrl":"https://chutes.ai/pricing","asOf":"2026-10-27","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":3,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"Public TEE inference output per 1M tokens. Reconfirmed 2026-10-27 (v0.12.141). The page says per-model rates are 'pulled live from our pricing API'; cached-input rate on the same card not stored."},{"id":"chutes-kimi-k2-6-moonshotai-kimi-k2-6-tee-in","providerId":"chutes","sku":"Kimi K2.6 (moonshotai/Kimi-K2.6-TEE)","unit":"usd_per_million_input_tokens","amountUsd":0.39,"currency":"USD","sourceUrl":"https://chutes.ai/pricing","asOf":"2026-10-27","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.39,"normalizationReason":null,"priceSortEligible":true,"qualifier":"Public TEE inference, USD per 1M tokens. Workload estimate on the same card was not used. TAO column not used. Re-priced 2026-10-27 (v0.12.141): 0.45 -> 0.39 USD per 1M input tokens from the page's Model pricing table. The page says per-model rates are 'pulled live from our pricing API', so they can move; cached-input rate on the same card not stored."},{"id":"chutes-kimi-k2-6-moonshotai-kimi-k2-6-tee-out","providerId":"chutes","sku":"Kimi K2.6 (moonshotai/Kimi-K2.6-TEE)","unit":"usd_per_million_output_tokens","amountUsd":1.8,"currency":"USD","sourceUrl":"https://chutes.ai/pricing","asOf":"2026-10-27","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":1.8,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"Public TEE inference output per 1M tokens. Re-priced 2026-10-27 (v0.12.141): 1.95 -> 1.8 USD per 1M output tokens from the page's Model pricing table. The page says per-model rates are 'pulled live from our pricing API', so they can move; cached-input rate on the same card not stored."},{"id":"chutes-deepseek-v3-2-deepseek-ai-deepseek-v3-2-tee-in","providerId":"chutes","sku":"DeepSeek-V3.2 (deepseek-ai/DeepSeek-V3.2-TEE)","unit":"usd_per_million_input_tokens","amountUsd":1,"currency":"USD","sourceUrl":"https://chutes.ai/pricing","asOf":"2026-10-27","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":1,"normalizationReason":null,"priceSortEligible":true,"qualifier":"Public TEE inference, USD per 1M tokens. Workload estimate on the same card was not used. TAO column not used. Reconfirmed 2026-10-27 (v0.12.141). The page says per-model rates are 'pulled live from our pricing API'; cached-input rate on the same card not stored."},{"id":"chutes-deepseek-v3-2-deepseek-ai-deepseek-v3-2-tee-out","providerId":"chutes","sku":"DeepSeek-V3.2 (deepseek-ai/DeepSeek-V3.2-TEE)","unit":"usd_per_million_output_tokens","amountUsd":1,"currency":"USD","sourceUrl":"https://chutes.ai/pricing","asOf":"2026-10-27","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":1,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"Public TEE inference output per 1M tokens. Reconfirmed 2026-10-27 (v0.12.141). The page says per-model rates are 'pulled live from our pricing API'; cached-input rate on the same card not stored."},{"id":"chutes-glm-5-1-zai-org-glm-5-1-tee-in","providerId":"chutes","sku":"GLM-5.1 (zai-org/GLM-5.1-TEE)","unit":"usd_per_million_input_tokens","amountUsd":0.9,"currency":"USD","sourceUrl":"https://chutes.ai/pricing","asOf":"2026-10-27","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.9,"normalizationReason":null,"priceSortEligible":true,"qualifier":"Public TEE inference, USD per 1M tokens. Workload estimate on the same card was not used. TAO column not used. Re-priced 2026-10-27 (v0.12.141): 0.98 -> 0.9 USD per 1M input tokens from the page's Model pricing table. The page says per-model rates are 'pulled live from our pricing API', so they can move; cached-input rate on the same card not stored."},{"id":"chutes-glm-5-1-zai-org-glm-5-1-tee-out","providerId":"chutes","sku":"GLM-5.1 (zai-org/GLM-5.1-TEE)","unit":"usd_per_million_output_tokens","amountUsd":2.9,"currency":"USD","sourceUrl":"https://chutes.ai/pricing","asOf":"2026-10-27","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":2.9,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"Public TEE inference output per 1M tokens. Re-priced 2026-10-27 (v0.12.141): 3.08 -> 2.9 USD per 1M output tokens from the page's Model pricing table. The page says per-model rates are 'pulled live from our pricing API', so they can move; cached-input rate on the same card not stored."},{"id":"chutes-glm-5-2-zai-org-glm-5-2-tee-in","providerId":"chutes","sku":"GLM-5.2 (zai-org/GLM-5.2-TEE)","unit":"usd_per_million_input_tokens","amountUsd":1.25,"currency":"USD","sourceUrl":"https://chutes.ai/pricing","asOf":"2026-10-27","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":1.25,"normalizationReason":null,"priceSortEligible":true,"qualifier":"Public TEE inference, USD per 1M tokens. Workload estimate on the same card was not used. TAO column not used. Reconfirmed 2026-10-27 (v0.12.141). The page says per-model rates are 'pulled live from our pricing API'; cached-input rate on the same card not stored."},{"id":"chutes-glm-5-2-zai-org-glm-5-2-tee-out","providerId":"chutes","sku":"GLM-5.2 (zai-org/GLM-5.2-TEE)","unit":"usd_per_million_output_tokens","amountUsd":3.95,"currency":"USD","sourceUrl":"https://chutes.ai/pricing","asOf":"2026-10-27","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":3.95,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"Public TEE inference output per 1M tokens. Reconfirmed 2026-10-27 (v0.12.141). The page says per-model rates are 'pulled live from our pricing API'; cached-input rate on the same card not stored."},{"id":"chutes-kimi-k3-moonshotai-kimi-k3-tee-in","providerId":"chutes","sku":"Kimi-K3 (moonshotai/Kimi-K3-TEE)","unit":"usd_per_million_input_tokens","amountUsd":1.85,"currency":"USD","sourceUrl":"https://chutes.ai/pricing","asOf":"2026-10-27","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":1.85,"normalizationReason":null,"priceSortEligible":true,"qualifier":"Public TEE inference, USD per 1M tokens. Workload estimate on the same card was not used. TAO column not used. Reconfirmed 2026-10-27 (v0.12.141). The page says per-model rates are 'pulled live from our pricing API'; cached-input rate on the same card not stored."},{"id":"chutes-kimi-k3-moonshotai-kimi-k3-tee-out","providerId":"chutes","sku":"Kimi-K3 (moonshotai/Kimi-K3-TEE)","unit":"usd_per_million_output_tokens","amountUsd":9.5,"currency":"USD","sourceUrl":"https://chutes.ai/pricing","asOf":"2026-10-27","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":9.5,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"Public TEE inference output per 1M tokens. Reconfirmed 2026-10-27 (v0.12.141). The page says per-model rates are 'pulled live from our pricing API'; cached-input rate on the same card not stored."},{"id":"chutes-rtx-pro-6000-96gb-usd-per-gpu-hour","providerId":"chutes","sku":"RTX Pro 6000 96GB","unit":"usd_per_gpu_hour","amountUsd":1.8,"currency":"USD","sourceUrl":"https://chutes.ai/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"gpu_hour_not_coerced_to_per_million_tokens","priceSortEligible":false,"qualifier":"Self-serve TEE GPU hourly rate. Not converted from per-second. Reconfirmed 2026-10-27 (v0.12.140): page adds a 'One-time deployment fee $5.40 = 3× hourly rate' (not stored as a row) and 'Billed by the second at the GPU's hourly rate'."},{"id":"chutes-private-chute-deployment-fee-usd-one-time","providerId":"chutes","sku":"Private chute deployment fee","unit":"usd_one_time","amountUsd":5.4,"currency":"USD","sourceUrl":"https://chutes.ai/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_one_time_fee","priceSortEligible":false,"qualifier":"Page states one-time fee equals 3× the $1.80 hourly rate ($5.40) for this GPU class. Reconfirmed 2026-10-27 (v0.12.141): page prints 'One-time deployment fee $5.40 = 3× hourly rate' next to the $1.80 / hour RTX Pro 6000 96 GB self-serve TEE rate."},{"id":"chutes-plus-usd-per-month","providerId":"chutes","sku":"Plus","unit":"usd_per_month","amountUsd":10,"currency":"USD","sourceUrl":"https://chutes.ai/pricing","asOf":"2026-10-03","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_month","priceSortEligible":false,"qualifier":"Optional plan. 6% off PAYG was not applied to token rows. chutes.ai/pricing 2026-10-27 (v0.12.141) FAQ: 'Monthly plans are no longer sold on chutes.ai' (existing plans run to the end of the current billing period, then usage is pay-as-you-go); amount kept from 2026-10-03, not reconfirmed (asOf unchanged).","sourceStatus":"unverified","sourceStatusReason":"plan_no_longer_sold: on 2026-10-27 the https://chutes.ai/pricing FAQ says 'Monthly plans are no longer sold on chutes.ai. If you already have one, it stays active until the end of your current billing period' (re-checked twice, same as the 2026-10-27 06:06 ET fetch); the page shows no Plus plan or $10 amount. Kept for history, never ranked.","sourceStatusCheckedOn":"2026-10-27"},{"id":"chutes-pro-usd-per-month","providerId":"chutes","sku":"Pro","unit":"usd_per_month","amountUsd":20,"currency":"USD","sourceUrl":"https://chutes.ai/pricing","asOf":"2026-10-03","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_month","priceSortEligible":false,"qualifier":"Optional plan. 10% off PAYG was not applied to token rows. chutes.ai/pricing 2026-10-27 (v0.12.141) FAQ: 'Monthly plans are no longer sold on chutes.ai' (existing plans run to the end of the current billing period, then usage is pay-as-you-go); amount kept from 2026-10-03, not reconfirmed (asOf unchanged).","sourceStatus":"unverified","sourceStatusReason":"plan_no_longer_sold: on 2026-10-27 the https://chutes.ai/pricing FAQ says 'Monthly plans are no longer sold on chutes.ai. If you already have one, it stays active until the end of your current billing period' (re-checked twice, same as the 2026-10-27 06:06 ET fetch); the page shows no Pro plan or $20 amount. Kept for history, never ranked.","sourceStatusCheckedOn":"2026-10-27"}],"notesExcerpt":"As of 2026-10-27 (chutes.ai/pricing, fetched twice 2026-10-27): Public TEE inference PAYG per 1M tokens, input/output (the page says per-model rates are 'pulled live from our pricing API'): gemma-4-31B-turbo $0.12/$0.37; Qwen3.8-27B $0.039/$1.25; Qwen3.6-27B $0.25/$2.00; DeepSeek…","notesCheck":{"status":"no_known_contradiction","pairs":[],"review":null,"note":null},"lastReviewed":"2026-09-14","scoreAsOf":"2026-09-14","website":"https://chutes.ai","doNotParse":"Do not parse pricingNotes. Use rows only. normalizedUsdPerMillionTokens is a single number only when this provider has exactly one sourced token row. Input/output, context tiers, and non-token units stay null at this level.","gap":"Partial coverage. Providers without a fetched SKU are omitted. See GET /api/pricing."},"decideHint":"/api/decide?jtbd=confidential-tee-inference","human":"/providers/chutes","compare":"/compare/amazon-bedrock-vs-chutes"},{"id":"databricks-mosaic","slug":"databricks-mosaic","name":"Databricks Mosaic AI","tagline":"Pick only when your data/platform already is Databricks. Otherwise Bedrock/Vertex or direct APIs.","website":"https://www.databricks.com/product/machine-learning","status":"active","overall":7.11,"scoreKind":"curated_estimate","confidence":"medium","scoreAsOf":"2026-09-14","deltaOverallVsSubject":-0.64,"roles":["same_jtbd_pick"],"sharedJtbdSlugs":["lakehouse-llm"],"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: Lakehouse-native model training/serving billed via Databricks DBUs + cloud compute. Foundation Model Serving and Mosaic tooling sit inside Databricks contracts — not indie per-token pricing. Strong if data already lives in Databricks.","notesCheck":{"status":"no_known_contradiction","pairs":[],"review":null,"note":null},"lastReviewed":"2026-09-14","scoreAsOf":"2026-09-14","website":"https://www.databricks.com/product/machine-learning","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=lakehouse-llm","human":"/providers/databricks-mosaic","compare":"/compare/amazon-bedrock-vs-databricks-mosaic"},{"id":"vertex-ai","slug":"vertex-ai","name":"Google Vertex AI","tagline":"Enterprise Gemini path. Use AI Studio for prototypes, Vertex when security review starts asking questions.","website":"https://cloud.google.com/vertex-ai","status":"active","overall":7.96,"scoreKind":"curated_estimate","confidence":"high","scoreAsOf":"2026-09-14","deltaOverallVsSubject":0.21,"roles":["same_jtbd_runner"],"sharedJtbdSlugs":["multi-model-router","enterprise-llm","lakehouse-llm","hipaa-baa-llm"],"pricing":{"normalizedUsdPerMillionTokens":null,"normalizationStatus":"ambiguous","normalizationReason":"input_output_split_not_a_single_rate","shape":"sourced_rows","filterable":false,"priceSortEligible":true,"priceSortKeyUsdPerMillionInputTokens":0.25,"rows":[{"id":"vertex-ai-gemini-3-8-flash-in","providerId":"vertex-ai","sku":"Gemini 3.8 Flash","unit":"usd_per_million_input_tokens","amountUsd":0.75,"currency":"USD","sourceUrl":"https://cloud.google.com/vertex-ai/generative-ai/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.75,"normalizationReason":null,"priceSortEligible":true,"qualifier":"Global, input text/image/video/audio, <=200k and the >200k column is the same $0.75 on this row. Introductory price through December 31, 2026. Non-global $0.825 not used as the sort key."},{"id":"vertex-ai-gemini-3-8-flash-non-global-in","providerId":"vertex-ai","sku":"Gemini 3.8 Flash non-global","unit":"usd_per_million_input_tokens","amountUsd":0.825,"currency":"USD","sourceUrl":"https://cloud.google.com/vertex-ai/generative-ai/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.825,"normalizationReason":"regional_price_not_collapsed","priceSortEligible":false,"qualifier":"Non-global introductory input through December 31, 2026."},{"id":"vertex-ai-gemini-3-8-flash-out","providerId":"vertex-ai","sku":"Gemini 3.8 Flash","unit":"usd_per_million_output_tokens","amountUsd":3.75,"currency":"USD","sourceUrl":"https://cloud.google.com/vertex-ai/generative-ai/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":3.75,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"Global text output, introductory through December 31, 2026."},{"id":"vertex-ai-gemini-3-8-flash-scheduled-2027-01-01-in","providerId":"vertex-ai","sku":"Gemini 3.8 Flash scheduled 2027-01-01","unit":"usd_per_million_input_tokens","amountUsd":1.5,"currency":"USD","sourceUrl":"https://cloud.google.com/vertex-ai/generative-ai/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":1.5,"normalizationReason":"scheduled_rate_not_yet_effective","priceSortEligible":false,"qualifier":"Standard price starting January 1, 2027. Not today's rate."},{"id":"vertex-ai-gemini-3-8-flash-scheduled-2027-01-01-out","providerId":"vertex-ai","sku":"Gemini 3.8 Flash scheduled 2027-01-01","unit":"usd_per_million_output_tokens","amountUsd":7.5,"currency":"USD","sourceUrl":"https://cloud.google.com/vertex-ai/generative-ai/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":7.5,"normalizationReason":"scheduled_rate_not_yet_effective","priceSortEligible":false,"qualifier":"Standard output starting January 1, 2027."},{"id":"vertex-ai-gemini-3-7-flash-in","providerId":"vertex-ai","sku":"Gemini 3.7 Flash","unit":"usd_per_million_input_tokens","amountUsd":0.75,"currency":"USD","sourceUrl":"https://cloud.google.com/vertex-ai/generative-ai/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.75,"normalizationReason":null,"priceSortEligible":true,"qualifier":"Global, input text/image/video/audio, <=200k and the >200k column is the same $0.75 on this row. Introductory price through December 31, 2026. Non-global $0.825 not used as the sort key."},{"id":"vertex-ai-gemini-3-7-flash-non-global-in","providerId":"vertex-ai","sku":"Gemini 3.7 Flash non-global","unit":"usd_per_million_input_tokens","amountUsd":0.825,"currency":"USD","sourceUrl":"https://cloud.google.com/vertex-ai/generative-ai/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.825,"normalizationReason":"regional_price_not_collapsed","priceSortEligible":false,"qualifier":"Non-global introductory input through December 31, 2026."},{"id":"vertex-ai-gemini-3-7-flash-out","providerId":"vertex-ai","sku":"Gemini 3.7 Flash","unit":"usd_per_million_output_tokens","amountUsd":3.75,"currency":"USD","sourceUrl":"https://cloud.google.com/vertex-ai/generative-ai/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":3.75,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"Global text output, introductory through December 31, 2026."},{"id":"vertex-ai-gemini-3-7-flash-scheduled-2027-01-01-in","providerId":"vertex-ai","sku":"Gemini 3.7 Flash scheduled 2027-01-01","unit":"usd_per_million_input_tokens","amountUsd":1.5,"currency":"USD","sourceUrl":"https://cloud.google.com/vertex-ai/generative-ai/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":1.5,"normalizationReason":"scheduled_rate_not_yet_effective","priceSortEligible":false,"qualifier":"Standard price starting January 1, 2027. Not today's rate."},{"id":"vertex-ai-gemini-3-7-flash-scheduled-2027-01-01-out","providerId":"vertex-ai","sku":"Gemini 3.7 Flash scheduled 2027-01-01","unit":"usd_per_million_output_tokens","amountUsd":7.5,"currency":"USD","sourceUrl":"https://cloud.google.com/vertex-ai/generative-ai/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":7.5,"normalizationReason":"scheduled_rate_not_yet_effective","priceSortEligible":false,"qualifier":"Standard output starting January 1, 2027."},{"id":"vertex-ai-gemini-3-6-flash-in","providerId":"vertex-ai","sku":"Gemini 3.6 Flash","unit":"usd_per_million_input_tokens","amountUsd":0.75,"currency":"USD","sourceUrl":"https://cloud.google.com/vertex-ai/generative-ai/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.75,"normalizationReason":null,"priceSortEligible":true,"qualifier":"Global, input text/image/video/audio, <=200k and the >200k column is the same $0.75 on this row. Introductory price through December 31, 2026. Non-global $0.825 not used as the sort key."},{"id":"vertex-ai-gemini-3-6-flash-non-global-in","providerId":"vertex-ai","sku":"Gemini 3.6 Flash non-global","unit":"usd_per_million_input_tokens","amountUsd":0.825,"currency":"USD","sourceUrl":"https://cloud.google.com/vertex-ai/generative-ai/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.825,"normalizationReason":"regional_price_not_collapsed","priceSortEligible":false,"qualifier":"Non-global introductory input through December 31, 2026."},{"id":"vertex-ai-gemini-3-6-flash-out","providerId":"vertex-ai","sku":"Gemini 3.6 Flash","unit":"usd_per_million_output_tokens","amountUsd":3.75,"currency":"USD","sourceUrl":"https://cloud.google.com/vertex-ai/generative-ai/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":3.75,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"Global text output, introductory through December 31, 2026."},{"id":"vertex-ai-gemini-3-6-flash-scheduled-2027-01-01-in","providerId":"vertex-ai","sku":"Gemini 3.6 Flash scheduled 2027-01-01","unit":"usd_per_million_input_tokens","amountUsd":1.5,"currency":"USD","sourceUrl":"https://cloud.google.com/vertex-ai/generative-ai/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":1.5,"normalizationReason":"scheduled_rate_not_yet_effective","priceSortEligible":false,"qualifier":"Standard price starting January 1, 2027. Not today's rate."},{"id":"vertex-ai-gemini-3-6-flash-scheduled-2027-01-01-out","providerId":"vertex-ai","sku":"Gemini 3.6 Flash scheduled 2027-01-01","unit":"usd_per_million_output_tokens","amountUsd":7.5,"currency":"USD","sourceUrl":"https://cloud.google.com/vertex-ai/generative-ai/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":7.5,"normalizationReason":"scheduled_rate_not_yet_effective","priceSortEligible":false,"qualifier":"Standard output starting January 1, 2027."},{"id":"vertex-ai-gemini-3-1-pro-preview-in","providerId":"vertex-ai","sku":"Gemini 3.1 Pro Preview","unit":"usd_per_million_input_tokens","amountUsd":2,"currency":"USD","sourceUrl":"https://cloud.google.com/vertex-ai/generative-ai/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":2,"normalizationReason":null,"priceSortEligible":true,"qualifier":"Global input text/image/video/audio, <=200k tokens. >200k is $4 and is a separate row."},{"id":"vertex-ai-gemini-3-1-pro-preview-long-context-in","providerId":"vertex-ai","sku":"Gemini 3.1 Pro Preview long context","unit":"usd_per_million_input_tokens","amountUsd":4,"currency":"USD","sourceUrl":"https://cloud.google.com/vertex-ai/generative-ai/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":4,"normalizationReason":"context_tier_not_a_single_rate","priceSortEligible":false,"qualifier":"Global input >200k tokens."},{"id":"vertex-ai-gemini-3-1-pro-preview-cached","providerId":"vertex-ai","sku":"Gemini 3.1 Pro Preview","unit":"usd_per_million_cached_input_tokens","amountUsd":0.2,"currency":"USD","sourceUrl":"https://cloud.google.com/vertex-ai/generative-ai/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.2,"normalizationReason":"cached_input_not_a_single_rate","priceSortEligible":false,"qualifier":"Global cached input <=200k."},{"id":"vertex-ai-gemini-3-1-pro-preview-out","providerId":"vertex-ai","sku":"Gemini 3.1 Pro Preview","unit":"usd_per_million_output_tokens","amountUsd":12,"currency":"USD","sourceUrl":"https://cloud.google.com/vertex-ai/generative-ai/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":12,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"Global text output <=200k. >200k output is $18 and was not blended."},{"id":"vertex-ai-gemini-3-8-flash-cyber-in","providerId":"vertex-ai","sku":"Gemini 3.8 Flash Cyber","unit":"usd_per_million_input_tokens","amountUsd":1.5,"currency":"USD","sourceUrl":"https://cloud.google.com/vertex-ai/generative-ai/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":1.5,"normalizationReason":null,"priceSortEligible":true,"qualifier":"Global input, <=200k. Non-global $1.65 not used as the sort key."},{"id":"vertex-ai-gemini-3-8-flash-cyber-out","providerId":"vertex-ai","sku":"Gemini 3.8 Flash Cyber","unit":"usd_per_million_output_tokens","amountUsd":7.5,"currency":"USD","sourceUrl":"https://cloud.google.com/vertex-ai/generative-ai/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":7.5,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"Global text output."},{"id":"vertex-ai-gemini-3-flash-preview-in","providerId":"vertex-ai","sku":"Gemini 3 Flash Preview","unit":"usd_per_million_input_tokens","amountUsd":0.5,"currency":"USD","sourceUrl":"https://cloud.google.com/vertex-ai/generative-ai/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.5,"normalizationReason":null,"priceSortEligible":true,"qualifier":"Global input text/image/video <=200k. Audio input is a separate row."},{"id":"vertex-ai-gemini-3-flash-preview-audio-in","providerId":"vertex-ai","sku":"Gemini 3 Flash Preview audio","unit":"usd_per_million_input_tokens","amountUsd":1,"currency":"USD","sourceUrl":"https://cloud.google.com/vertex-ai/generative-ai/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":1,"normalizationReason":"modality_split_not_blended","priceSortEligible":false,"qualifier":"Global audio input. Not blended with text."},{"id":"vertex-ai-gemini-3-5-flash-in","providerId":"vertex-ai","sku":"Gemini 3.5 Flash","unit":"usd_per_million_input_tokens","amountUsd":1.5,"currency":"USD","sourceUrl":"https://cloud.google.com/vertex-ai/generative-ai/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":1.5,"normalizationReason":null,"priceSortEligible":true,"qualifier":"Global input, <=200k. Non-global $1.65 not the sort key."},{"id":"vertex-ai-gemini-3-5-flash-out","providerId":"vertex-ai","sku":"Gemini 3.5 Flash","unit":"usd_per_million_output_tokens","amountUsd":9,"currency":"USD","sourceUrl":"https://cloud.google.com/vertex-ai/generative-ai/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":9,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"Global text output."},{"id":"vertex-ai-gemini-3-5-flash-lite-in","providerId":"vertex-ai","sku":"Gemini 3.5 Flash-Lite","unit":"usd_per_million_input_tokens","amountUsd":0.3,"currency":"USD","sourceUrl":"https://cloud.google.com/vertex-ai/generative-ai/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.3,"normalizationReason":null,"priceSortEligible":true,"qualifier":"Global input, <=200k."},{"id":"vertex-ai-gemini-3-5-flash-lite-out","providerId":"vertex-ai","sku":"Gemini 3.5 Flash-Lite","unit":"usd_per_million_output_tokens","amountUsd":2.5,"currency":"USD","sourceUrl":"https://cloud.google.com/vertex-ai/generative-ai/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":2.5,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"Global text output."},{"id":"vertex-ai-gemini-3-1-flash-lite-in","providerId":"vertex-ai","sku":"Gemini 3.1 Flash-Lite","unit":"usd_per_million_input_tokens","amountUsd":0.25,"currency":"USD","sourceUrl":"https://cloud.google.com/vertex-ai/generative-ai/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.25,"normalizationReason":null,"priceSortEligible":true,"qualifier":"Global input text/image/video, <=200k. Audio is separate."},{"id":"vertex-ai-gemini-3-1-flash-lite-audio-in","providerId":"vertex-ai","sku":"Gemini 3.1 Flash-Lite audio","unit":"usd_per_million_input_tokens","amountUsd":0.5,"currency":"USD","sourceUrl":"https://cloud.google.com/vertex-ai/generative-ai/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.5,"normalizationReason":"modality_split_not_blended","priceSortEligible":false,"qualifier":"Global audio input."},{"id":"vertex-ai-gemini-3-1-flash-lite-out","providerId":"vertex-ai","sku":"Gemini 3.1 Flash-Lite","unit":"usd_per_million_output_tokens","amountUsd":1.5,"currency":"USD","sourceUrl":"https://cloud.google.com/vertex-ai/generative-ai/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":1.5,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"Global text output."},{"id":"vertex-ai-gemini-3-1-flash-lite-cached","providerId":"vertex-ai","sku":"Gemini 3.1 Flash-Lite","unit":"usd_per_million_cached_input_tokens","amountUsd":0.025,"currency":"USD","sourceUrl":"https://cloud.google.com/vertex-ai/generative-ai/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.025,"normalizationReason":"cached_input_not_a_single_rate","priceSortEligible":false,"qualifier":"Global cached input <=200k."},{"id":"vertex-ai-gemini-3-8-live-api-text-in","providerId":"vertex-ai","sku":"Gemini 3.8 Live API text","unit":"usd_per_million_input_tokens","amountUsd":0.75,"currency":"USD","sourceUrl":"https://cloud.google.com/vertex-ai/generative-ai/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.75,"normalizationReason":"modality_split_not_blended","priceSortEligible":false,"qualifier":"Non-global text input. Audio and video inputs are separate rows."},{"id":"vertex-ai-gemini-3-8-live-api-text-out","providerId":"vertex-ai","sku":"Gemini 3.8 Live API text","unit":"usd_per_million_output_tokens","amountUsd":4.5,"currency":"USD","sourceUrl":"https://cloud.google.com/vertex-ai/generative-ai/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":4.5,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"Non-global text output."}],"notesExcerpt":"As of 2026-09-14: Google Cloud Vertex AI model garden + Gemini; billed in GCP currency with enterprise controls, VPC-SC, and committed use discounts. Prefer Google AI Studio/API for indie DX; Vertex for enterprise residency/IAM.","notesCheck":{"status":"no_known_contradiction","pairs":[],"review":null,"note":null},"lastReviewed":"2026-09-14","scoreAsOf":"2026-09-14","website":"https://cloud.google.com/vertex-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=multi-model-router","human":"/providers/vertex-ai","compare":"/compare/amazon-bedrock-vs-vertex-ai"},{"id":"azure-openai","slug":"azure-openai","name":"Azure OpenAI","tagline":"Pick when IT already standardized on Azure and needs VNET/private endpoints. Otherwise go direct OpenAI and…","website":"https://azure.microsoft.com/products/ai-services/openai-service","status":"active","overall":7.62,"scoreKind":"curated_estimate","confidence":"high","scoreAsOf":"2026-09-14","deltaOverallVsSubject":-0.13,"roles":["same_jtbd_runner"],"sharedJtbdSlugs":["enterprise-llm","confidential-tee-inference","hipaa-baa-llm","air-gapped-model-serve"],"pricing":{"normalizedUsdPerMillionTokens":null,"normalizationStatus":"unavailable","normalizationReason":"no_sourced_price","shape":"prose_notes_only","filterable":false,"priceSortEligible":false,"priceSortKeyUsdPerMillionInputTokens":null,"rows":[],"notesExcerpt":"OpenAI models via Azure with regional deployment; enterprise agreements, PTUs, and Microsoft billing. Often premium vs direct OpenAI.","notesCheck":{"status":"no_known_contradiction","pairs":[],"review":null,"note":null},"lastReviewed":"2026-09-14","scoreAsOf":"2026-09-14","website":"https://azure.microsoft.com/products/ai-services/openai-service","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=enterprise-llm","human":"/providers/azure-openai","compare":"/compare/amazon-bedrock-vs-azure-openai"},{"id":"portkey","slug":"portkey","name":"Portkey","tagline":"Depot pick for production AI gateway (fallbacks, virtual keys, budgets). OpenRouter when you want a model…","website":"https://portkey.ai","status":"active","overall":8.31,"scoreKind":"curated_estimate","confidence":"high","scoreAsOf":"2026-09-14","deltaOverallVsSubject":0.56,"roles":["same_jtbd_runner"],"sharedJtbdSlugs":["multi-model-router","prompt-caching-optimization"],"pricing":{"normalizedUsdPerMillionTokens":null,"normalizationStatus":"unit_mismatch","normalizationReason":"unit_mismatch","shape":"sourced_rows","filterable":false,"priceSortEligible":false,"priceSortKeyUsdPerMillionInputTokens":null,"rows":[{"id":"portkey-production-usd-per-month","providerId":"portkey","sku":"Production","unit":"usd_per_month","amountUsd":49,"currency":"USD","sourceUrl":"https://portkey.ai/pricing","asOf":"2026-10-03","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_month","priceSortEligible":false,"qualifier":"Gateway plan. 100k recorded logs, then +$9 per additional 100k requests. Not a model token rate. Enterprise is custom and was omitted."}],"notesExcerpt":"As of 2026-09-14 (portkey.ai/pricing): Developer free forever (10k logs/mo, 3-day log / 30-day metrics retention). Production $49/mo (100k logs, +$9/100k overage, 30/90-day retention, guardrails, RBAC). Enterprise custom (10M+ logs, VPC, HIPAA/BAA, private cloud). OSS self-host g…","notesCheck":{"status":"no_known_contradiction","pairs":[],"review":null,"note":null},"lastReviewed":"2026-09-14","scoreAsOf":"2026-09-14","website":"https://portkey.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=multi-model-router","human":"/providers/portkey","compare":"/compare/amazon-bedrock-vs-portkey"},{"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":0.68,"roles":["same_jtbd_runner"],"sharedJtbdSlugs":["prompt-caching-optimization"],"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=prompt-caching-optimization","human":"/providers/google-ai","compare":"/compare/amazon-bedrock-vs-google-ai"},{"id":"fireworks","slug":"fireworks","name":"Fireworks AI","tagline":"Top pick for production open-model serving with real DX. Prefer over random GPU DIY when you want tokens not…","website":"https://fireworks.ai","status":"active","overall":8.35,"scoreKind":"curated_estimate","confidence":"high","scoreAsOf":"2026-09-14","deltaOverallVsSubject":0.6,"roles":["same_jtbd_runner"],"sharedJtbdSlugs":["confidential-tee-inference"],"pricing":{"normalizedUsdPerMillionTokens":null,"normalizationStatus":"ambiguous","normalizationReason":"multiple_sourced_token_skus","shape":"sourced_rows","filterable":false,"priceSortEligible":false,"priceSortKeyUsdPerMillionInputTokens":null,"rows":[{"id":"fireworks-embed-to-150m","providerId":"fireworks","sku":"Embeddings up to 150M params","unit":"usd_per_million_input_tokens","amountUsd":0.008,"currency":"USD","sourceUrl":"https://fireworks.ai/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.008,"normalizationReason":"embedding_sku_excluded_from_provider_sort","priceSortEligible":false,"qualifier":"parameter-count bucket, not a named chat model"},{"id":"fireworks-embed-150-350m","providerId":"fireworks","sku":"Embeddings 150M-350M params","unit":"usd_per_million_input_tokens","amountUsd":0.016,"currency":"USD","sourceUrl":"https://fireworks.ai/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.016,"normalizationReason":"embedding_sku_excluded_from_provider_sort","priceSortEligible":false,"qualifier":"parameter-count bucket"},{"id":"fireworks-embed-qwen3-8b","providerId":"fireworks","sku":"Qwen3 8B","unit":"usd_per_million_input_tokens","amountUsd":0.1,"currency":"USD","sourceUrl":"https://fireworks.ai/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.1,"normalizationReason":"embedding_sku_excluded_from_provider_sort","priceSortEligible":false,"qualifier":"listed in the embeddings section after the parameter buckets"},{"id":"fireworks-train-lora-sft-to-16b","providerId":"fireworks","sku":"Managed training LoRA SFT up to 16B","unit":"usd_per_million_train_tokens","amountUsd":0.5,"currency":"USD","sourceUrl":"https://fireworks.ai/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.5,"normalizationReason":"training_token_price_not_inference","priceSortEligible":false,"qualifier":"per 1M training tokens"},{"id":"fireworks-gpu-h100","providerId":"fireworks","sku":"H100 80 GB","unit":"usd_per_gpu_hour","amountUsd":8,"currency":"USD","sourceUrl":"https://fireworks.ai/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_gpu_hour","priceSortEligible":false,"qualifier":"on-demand deployments; per-minute column also shown and not converted; reconfirmed 2026-10-27 (v0.12.139): page says 'Region-restricted deployments are priced at a 1.5x premium' (not stored as a separate row)"},{"id":"fireworks-gpu-h200","providerId":"fireworks","sku":"H200 141 GB","unit":"usd_per_gpu_hour","amountUsd":8,"currency":"USD","sourceUrl":"https://fireworks.ai/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_gpu_hour","priceSortEligible":false,"qualifier":"on-demand deployments; per-minute column also shown and not converted; reconfirmed 2026-10-27 (v0.12.139): page says 'Region-restricted deployments are priced at a 1.5x premium' (not stored as a separate row)"},{"id":"fireworks-gpu-b200","providerId":"fireworks","sku":"B200 180 GB","unit":"usd_per_gpu_hour","amountUsd":13,"currency":"USD","sourceUrl":"https://fireworks.ai/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_gpu_hour","priceSortEligible":false,"qualifier":"on-demand deployments; per-minute column also shown and not converted; reconfirmed 2026-10-27 (v0.12.139): page says 'Region-restricted deployments are priced at a 1.5x premium' (not stored as a separate row)"},{"id":"fireworks-gpu-b300","providerId":"fireworks","sku":"B300 288 GB","unit":"usd_per_gpu_hour","amountUsd":15,"currency":"USD","sourceUrl":"https://fireworks.ai/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_gpu_hour","priceSortEligible":false,"qualifier":"on-demand deployments; per-minute column also shown and not converted; reconfirmed 2026-10-27 (v0.12.139): page says 'Region-restricted deployments are priced at a 1.5x premium' (not stored as a separate row)"},{"id":"fireworks-gpu-gb300","providerId":"fireworks","sku":"GB300 288 GB","unit":"usd_per_gpu_hour","amountUsd":20,"currency":"USD","sourceUrl":"https://fireworks.ai/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_gpu_hour","priceSortEligible":false,"qualifier":"on-demand deployments; per-minute column also shown and not converted; reconfirmed 2026-10-27 (v0.12.139): page says 'Region-restricted deployments are priced at a 1.5x premium' (not stored as a separate row)"},{"id":"fireworks-serverless-chat-unavailable","providerId":"fireworks","sku":"serverless chat models","unit":"usd_per_million_input_tokens","amountUsd":null,"currency":"USD","sourceUrl":"https://fireworks.ai/pricing","asOf":"2026-10-03","normalizationStatus":"ambiguous","normalizedUsdPerMillionTokens":null,"normalizationReason":"page_points_elsewhere_for_serverless_chat_matrix","priceSortEligible":false,"qualifier":"fireworks.ai/pricing says to visit full pricing documentation for Standard/Priority/Fast serverless token rates. Those figures were not on this page and were not guessed."}],"notesExcerpt":"Serverless per-token + on-demand GPU; day-0 OSS model support; post-training stack. Free credits often available.","notesCheck":{"status":"no_known_contradiction","pairs":[],"review":null,"note":null},"lastReviewed":"2026-09-14","scoreAsOf":"2026-09-14","website":"https://fireworks.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=confidential-tee-inference","human":"/providers/fireworks","compare":"/compare/amazon-bedrock-vs-fireworks"},{"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":0.47,"roles":["same_jtbd_runner"],"sharedJtbdSlugs":["prompt-caching-optimization"],"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=prompt-caching-optimization","human":"/providers/openai","compare":"/compare/amazon-bedrock-vs-openai"}],"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/amazon-bedrock","machine":"/api/alternatives?provider=amazon-bedrock","provider":"/api/providers/amazon-bedrock","canonical":"/api/canonical"}}