{"id":"model.deepseek.deepseek-v4-flash","name":"DeepSeek V4 Flash","family":"DeepSeek V4","type":"frontier","modalities":["text"],"capabilities":["agent","tool_calls","vision"],"openness":{"weights":"open_weights","code":null,"data":null,"license":null,"deployment":null,"api":"API"},"keySpecs":{"contextWindowTokens":1000000,"extendedContextWindowTokens":null,"totalParameters":null,"activeParameters":null,"architectureType":null,"baseModel":null,"inputPriceUsdPerMtok":0.3,"outputPriceUsdPerMtok":1.2,"concurrencyLimitRequests":null},"organization":{"id":"org.deepseek","name":"DeepSeek","websiteUrl":"https://www.deepseek.com"},"brand":{"id":"brand.deepseek","name":"DeepSeek","websiteUrl":"https://www.deepseek.com"},"product":{"id":"product.deepseek.api","name":"DeepSeek API","websiteUrl":"https://api-docs.deepseek.com/quick_start/pricing/"},"origin":"domestic","versions":[{"id":"version.deepseek.deepseek-v4-flash","name":"DeepSeek-V4-Flash-0731","externalModelId":"deepseek-v4-flash","kind":"snapshot","releaseDate":"2026-07-31","datePrecision":"day","publicAvailableAt":null,"lifecycleStatus":"superseded","knowledgeCutoff":null,"claims":[{"id":"claim.version.deepseek.deepseek-v4-flash.input-cache-hit-price","fieldKey":"cached_input_price_usd_per_mtok","value":{"unit":"USD/MTok","value":0.0028},"rawValue":"$0.0028","ingestionOrigin":"curated_official","unit":"USD/MTok","condition":"Cache hit","status":"approved","confidence":"high","reviewedBy":"system:manual-source-revalidation","reviewedAt":"2026-08-07 06:31:03.075292+08","effectiveFrom":null,"effectiveTo":null,"source":{"id":"source.deepseek.pricing","title":"DeepSeek API 模型与价格","url":"https://api-docs.deepseek.com/zh-cn/quick_start/pricing","accessedAt":"2026-10-18 00:00:00+08","robotsStatus":"allowed","collectionEligibility":"eligible","collectionCheckedAt":"2026-10-18 00:00:00+08"},"evidence":{"id":"evidence.deepseek.pricing-table","locator":"Model pricing and capabilities table","excerpt":"DeepSeek-V4-Flash-0731 and DeepSeek-V4-Pro: 1M context, maximum 384K output, thinking/non-thinking modes, JSON output, tool calls, API support, token prices, and concurrency limits."}},{"id":"claim.version.deepseek.deepseek-v4-flash.concurrency","fieldKey":"concurrency_limit","value":{"unit":"requests","value":2500},"rawValue":"2500","ingestionOrigin":"curated_official","unit":"requests","condition":null,"status":"approved","confidence":"high","reviewedBy":"system:manual-source-revalidation","reviewedAt":"2026-08-07 06:31:03.075292+08","effectiveFrom":null,"effectiveTo":null,"source":{"id":"source.deepseek.pricing","title":"DeepSeek API 模型与价格","url":"https://api-docs.deepseek.com/zh-cn/quick_start/pricing","accessedAt":"2026-10-18 00:00:00+08","robotsStatus":"allowed","collectionEligibility":"eligible","collectionCheckedAt":"2026-10-18 00:00:00+08"},"evidence":{"id":"evidence.deepseek.pricing-table","locator":"Model pricing and capabilities table","excerpt":"DeepSeek-V4-Flash-0731 and DeepSeek-V4-Pro: 1M context, maximum 384K output, thinking/non-thinking modes, JSON output, tool calls, API support, token prices, and concurrency limits."}},{"id":"claim.version.deepseek.deepseek-v4-flash.context","fieldKey":"context_window_tokens","value":{"unit":"tokens","value":1000000},"rawValue":"1M","ingestionOrigin":"curated_official","unit":"tokens","condition":null,"status":"approved","confidence":"high","reviewedBy":"system:manual-source-revalidation","reviewedAt":"2026-08-07 06:31:03.075292+08","effectiveFrom":null,"effectiveTo":null,"source":{"id":"source.deepseek.pricing","title":"DeepSeek API 模型与价格","url":"https://api-docs.deepseek.com/zh-cn/quick_start/pricing","accessedAt":"2026-10-18 00:00:00+08","robotsStatus":"allowed","collectionEligibility":"eligible","collectionCheckedAt":"2026-10-18 00:00:00+08"},"evidence":{"id":"evidence.deepseek.pricing-table","locator":"Model pricing and capabilities table","excerpt":"DeepSeek-V4-Flash-0731 and DeepSeek-V4-Pro: 1M context, maximum 384K output, thinking/non-thinking modes, JSON output, tool calls, API support, token prices, and concurrency limits."}},{"id":"claim.version.deepseek.deepseek-v4-flash.input-cache-miss-price","fieldKey":"input_price_usd_per_mtok","value":{"unit":"USD/MTok","value":0.14},"rawValue":"$0.14","ingestionOrigin":"curated_official","unit":"USD/MTok","condition":"Cache miss","status":"approved","confidence":"high","reviewedBy":"system:manual-source-revalidation","reviewedAt":"2026-08-07 06:31:03.075292+08","effectiveFrom":null,"effectiveTo":null,"source":{"id":"source.deepseek.pricing","title":"DeepSeek API 模型与价格","url":"https://api-docs.deepseek.com/zh-cn/quick_start/pricing","accessedAt":"2026-10-18 00:00:00+08","robotsStatus":"allowed","collectionEligibility":"eligible","collectionCheckedAt":"2026-10-18 00:00:00+08"},"evidence":{"id":"evidence.deepseek.pricing-table","locator":"Model pricing and capabilities table","excerpt":"DeepSeek-V4-Flash-0731 and DeepSeek-V4-Pro: 1M context, maximum 384K output, thinking/non-thinking modes, JSON output, tool calls, API support, token prices, and concurrency limits."}},{"id":"claim.version.deepseek.deepseek-v4-flash.json-output","fieldKey":"json_output","value":{"value":true},"rawValue":"Supported","ingestionOrigin":"curated_official","unit":null,"condition":null,"status":"approved","confidence":"high","reviewedBy":"system:manual-source-revalidation","reviewedAt":"2026-08-07 06:31:03.075292+08","effectiveFrom":null,"effectiveTo":null,"source":{"id":"source.deepseek.pricing","title":"DeepSeek API 模型与价格","url":"https://api-docs.deepseek.com/zh-cn/quick_start/pricing","accessedAt":"2026-10-18 00:00:00+08","robotsStatus":"allowed","collectionEligibility":"eligible","collectionCheckedAt":"2026-10-18 00:00:00+08"},"evidence":{"id":"evidence.deepseek.pricing-table","locator":"Model pricing and capabilities table","excerpt":"DeepSeek-V4-Flash-0731 and DeepSeek-V4-Pro: 1M context, maximum 384K output, thinking/non-thinking modes, JSON output, tool calls, API support, token prices, and concurrency limits."}},{"id":"claim.version.deepseek.deepseek-v4-flash.max-output","fieldKey":"max_output_tokens","value":{"unit":"tokens","value":384000},"rawValue":"MAXIMUM: 384K","ingestionOrigin":"curated_official","unit":"tokens","condition":null,"status":"approved","confidence":"high","reviewedBy":"system:manual-source-revalidation","reviewedAt":"2026-08-07 06:31:03.075292+08","effectiveFrom":null,"effectiveTo":null,"source":{"id":"source.deepseek.pricing","title":"DeepSeek API 模型与价格","url":"https://api-docs.deepseek.com/zh-cn/quick_start/pricing","accessedAt":"2026-10-18 00:00:00+08","robotsStatus":"allowed","collectionEligibility":"eligible","collectionCheckedAt":"2026-10-18 00:00:00+08"},"evidence":{"id":"evidence.deepseek.pricing-table","locator":"Model pricing and capabilities table","excerpt":"DeepSeek-V4-Flash-0731 and DeepSeek-V4-Pro: 1M context, maximum 384K output, thinking/non-thinking modes, JSON output, tool calls, API support, token prices, and concurrency limits."}},{"id":"claim.version.deepseek.deepseek-v4-flash.output-price","fieldKey":"output_price_usd_per_mtok","value":{"unit":"USD/MTok","value":0.28},"rawValue":"$0.28","ingestionOrigin":"curated_official","unit":"USD/MTok","condition":null,"status":"approved","confidence":"high","reviewedBy":"system:manual-source-revalidation","reviewedAt":"2026-08-07 06:31:03.075292+08","effectiveFrom":null,"effectiveTo":null,"source":{"id":"source.deepseek.pricing","title":"DeepSeek API 模型与价格","url":"https://api-docs.deepseek.com/zh-cn/quick_start/pricing","accessedAt":"2026-10-18 00:00:00+08","robotsStatus":"allowed","collectionEligibility":"eligible","collectionCheckedAt":"2026-10-18 00:00:00+08"},"evidence":{"id":"evidence.deepseek.pricing-table","locator":"Model pricing and capabilities table","excerpt":"DeepSeek-V4-Flash-0731 and DeepSeek-V4-Pro: 1M context, maximum 384K output, thinking/non-thinking modes, JSON output, tool calls, API support, token prices, and concurrency limits."}},{"id":"claim.version.deepseek.deepseek-v4-flash.peak-offpeak-pricing","fieldKey":"peak_offpeak_pricing","value":{"status":"announced_not_effective","multiplier":2,"peak_hours_beijing":["09:00-12:00","14:00-18:00"]},"rawValue":"Planned peak/off-peak policy; peak 2x","ingestionOrigin":"curated_official","unit":null,"condition":"The official page says the effective date is subject to a future announcement. Do not apply this multiplier to current prices.","status":"approved","confidence":"high","reviewedBy":"system:manual-source-revalidation","reviewedAt":"2026-08-07 06:31:03.075292+08","effectiveFrom":null,"effectiveTo":null,"source":{"id":"source.deepseek.pricing","title":"DeepSeek API 模型与价格","url":"https://api-docs.deepseek.com/zh-cn/quick_start/pricing","accessedAt":"2026-10-18 00:00:00+08","robotsStatus":"allowed","collectionEligibility":"eligible","collectionCheckedAt":"2026-10-18 00:00:00+08"},"evidence":{"id":"evidence.deepseek.pricing.peak-offpeak-policy","locator":"Pricing page peak/off-peak notice","excerpt":"DeepSeek states that the API will soon adopt a peak/off-peak pricing policy, with peak hours charged at 2x regular prices for all billing items; the effective date is subject to an official announcement. Peak hours are listed as 09:00-12:00 and 14:00-18:00 Beijing Time (UTC+8)."}},{"id":"claim.version.deepseek.deepseek-v4-flash.thinking-modes","fieldKey":"thinking_modes","value":["thinking","non-thinking"],"rawValue":"Supports both thinking and non-thinking modes","ingestionOrigin":"curated_official","unit":null,"condition":null,"status":"approved","confidence":"high","reviewedBy":"system:manual-source-revalidation","reviewedAt":"2026-08-07 06:31:03.075292+08","effectiveFrom":null,"effectiveTo":null,"source":{"id":"source.deepseek.pricing","title":"DeepSeek API 模型与价格","url":"https://api-docs.deepseek.com/zh-cn/quick_start/pricing","accessedAt":"2026-10-18 00:00:00+08","robotsStatus":"allowed","collectionEligibility":"eligible","collectionCheckedAt":"2026-10-18 00:00:00+08"},"evidence":{"id":"evidence.deepseek.pricing-table","locator":"Model pricing and capabilities table","excerpt":"DeepSeek-V4-Flash-0731 and DeepSeek-V4-Pro: 1M context, maximum 384K output, thinking/non-thinking modes, JSON output, tool calls, API support, token prices, and concurrency limits."}},{"id":"claim.version.deepseek.deepseek-v4-flash.tool-calls","fieldKey":"tool_calls","value":{"value":true},"rawValue":"Supported","ingestionOrigin":"curated_official","unit":null,"condition":null,"status":"approved","confidence":"high","reviewedBy":"system:manual-source-revalidation","reviewedAt":"2026-08-07 06:31:03.075292+08","effectiveFrom":null,"effectiveTo":null,"source":{"id":"source.deepseek.pricing","title":"DeepSeek API 模型与价格","url":"https://api-docs.deepseek.com/zh-cn/quick_start/pricing","accessedAt":"2026-10-18 00:00:00+08","robotsStatus":"allowed","collectionEligibility":"eligible","collectionCheckedAt":"2026-10-18 00:00:00+08"},"evidence":{"id":"evidence.deepseek.pricing-table","locator":"Model pricing and capabilities table","excerpt":"DeepSeek-V4-Flash-0731 and DeepSeek-V4-Pro: 1M context, maximum 384K output, thinking/non-thinking modes, JSON output, tool calls, API support, token prices, and concurrency limits."}}],"benchmarks":[]},{"id":"version.deepseek.deepseek-v4-1-flash-1017","name":"DeepSeek-V4.1-Flash-1017","externalModelId":"deepseek-flash","kind":"date","releaseDate":"2026-10-17","datePrecision":"day","publicAvailableAt":null,"lifecycleStatus":"active","knowledgeCutoff":null,"claims":[{"id":"claim.version.deepseek.deepseek-v4-1-flash.api-id","fieldKey":"api_id","value":{"value":"deepseek-flash"},"rawValue":null,"ingestionOrigin":"curated_official","unit":null,"condition":"Recorded on 2026-10-20; the pricing page states 'Use deepseek-flash as the model name' and that legacy names such as deepseek-v4-flash are mapped to this version.","status":"approved","confidence":"high","reviewedBy":"system:curated-publisher","reviewedAt":"2026-10-20 13:25:48.651124+08","effectiveFrom":null,"effectiveTo":null,"source":{"id":"source.deepseek.pricing-en","title":"DeepSeek API Models & Pricing (English)","url":"https://api-docs.deepseek.com/quick_start/pricing","accessedAt":"2026-10-20 10:52:07.759524+08","robotsStatus":"allowed","collectionEligibility":"eligible","collectionCheckedAt":"2026-10-20 10:52:07.759524+08"},"evidence":{"id":"evidence.deepseek.v4-1-flash.pricing-usd.2026-10-20","locator":"DeepSeek API Models & Pricing, model details and pricing table, column deepseek-flash","excerpt":"Model details for deepseek-flash: model version DeepSeek-V4.1-Flash-1017; supports both non-thinking and thinking modes; context length 1M; max output 384K; features include JSON output, tool calls, Responses API, Anthropic API, chat prefix completion (beta), FIM completion (beta) and vision. Pricing per 1M tokens in USD: cache-hit input off-peak $0.003 and peak $0.006; cache-miss input off-peak $0.15 and peak $0.3; output off-peak $0.6 and peak $1.2; concurrency limit 2500. Notes state that deepseek-flash is the model name, off-peak rates are half of peak rates, peak hours are 01:00-04:00 and 06:00-10:00 UTC Monday through Friday excluding Chinese public holidays, and the legacy name deepseek-v4-flash is still accepted but its model has been retired and is served by DeepSeek-V4.1-Flash-1017 at the Flash price."}},{"id":"claim.version.deepseek.deepseek-v4-1-flash.capability","fieldKey":"capability_tags","value":{"value":["agent","vision","tool_calls"]},"rawValue":null,"ingestionOrigin":"curated_official","unit":null,"condition":"Set on 2026-10-20 from the pricing page feature table: vision is supported for deepseek-flash, tool calls and Responses API are supported, and the model supports thinking and non-thinking modes.","status":"approved","confidence":"high","reviewedBy":"system:curated-publisher","reviewedAt":"2026-10-20 13:25:48.651124+08","effectiveFrom":null,"effectiveTo":null,"source":{"id":"source.deepseek.pricing-en","title":"DeepSeek API Models & Pricing (English)","url":"https://api-docs.deepseek.com/quick_start/pricing","accessedAt":"2026-10-20 10:52:07.759524+08","robotsStatus":"allowed","collectionEligibility":"eligible","collectionCheckedAt":"2026-10-20 10:52:07.759524+08"},"evidence":{"id":"evidence.deepseek.v4-1-flash.pricing-usd.2026-10-20","locator":"DeepSeek API Models & Pricing, model details and pricing table, column deepseek-flash","excerpt":"Model details for deepseek-flash: model version DeepSeek-V4.1-Flash-1017; supports both non-thinking and thinking modes; context length 1M; max output 384K; features include JSON output, tool calls, Responses API, Anthropic API, chat prefix completion (beta), FIM completion (beta) and vision. Pricing per 1M tokens in USD: cache-hit input off-peak $0.003 and peak $0.006; cache-miss input off-peak $0.15 and peak $0.3; output off-peak $0.6 and peak $1.2; concurrency limit 2500. Notes state that deepseek-flash is the model name, off-peak rates are half of peak rates, peak hours are 01:00-04:00 and 06:00-10:00 UTC Monday through Friday excluding Chinese public holidays, and the legacy name deepseek-v4-flash is still accepted but its model has been retired and is served by DeepSeek-V4.1-Flash-1017 at the Flash price."}},{"id":"claim.version.deepseek.deepseek-v4-1-flash.context","fieldKey":"context_window_tokens","value":{"unit":"tokens","value":1000000},"rawValue":null,"ingestionOrigin":"curated_official","unit":"tokens","condition":"Recorded on 2026-10-20 from the pricing page model details: context length 1M.","status":"approved","confidence":"high","reviewedBy":"system:curated-publisher","reviewedAt":"2026-10-20 13:25:48.651124+08","effectiveFrom":null,"effectiveTo":null,"source":{"id":"source.deepseek.pricing-en","title":"DeepSeek API Models & Pricing (English)","url":"https://api-docs.deepseek.com/quick_start/pricing","accessedAt":"2026-10-20 10:52:07.759524+08","robotsStatus":"allowed","collectionEligibility":"eligible","collectionCheckedAt":"2026-10-20 10:52:07.759524+08"},"evidence":{"id":"evidence.deepseek.v4-1-flash.pricing-usd.2026-10-20","locator":"DeepSeek API Models & Pricing, model details and pricing table, column deepseek-flash","excerpt":"Model details for deepseek-flash: model version DeepSeek-V4.1-Flash-1017; supports both non-thinking and thinking modes; context length 1M; max output 384K; features include JSON output, tool calls, Responses API, Anthropic API, chat prefix completion (beta), FIM completion (beta) and vision. Pricing per 1M tokens in USD: cache-hit input off-peak $0.003 and peak $0.006; cache-miss input off-peak $0.15 and peak $0.3; output off-peak $0.6 and peak $1.2; concurrency limit 2500. Notes state that deepseek-flash is the model name, off-peak rates are half of peak rates, peak hours are 01:00-04:00 and 06:00-10:00 UTC Monday through Friday excluding Chinese public holidays, and the legacy name deepseek-v4-flash is still accepted but its model has been retired and is served by DeepSeek-V4.1-Flash-1017 at the Flash price."}},{"id":"claim.version.deepseek.deepseek-v4-1-flash.deployment","fieldKey":"deployment_options","value":{"value":["api","official_api"]},"rawValue":null,"ingestionOrigin":"curated_official","unit":null,"condition":"Set on 2026-10-20 from the pricing page: the model is served through the DeepSeek API at https://api.deepseek.com in OpenAI and Anthropic compatible formats.","status":"approved","confidence":"high","reviewedBy":"system:curated-publisher","reviewedAt":"2026-10-20 13:25:48.651124+08","effectiveFrom":null,"effectiveTo":null,"source":{"id":"source.deepseek.pricing-en","title":"DeepSeek API Models & Pricing (English)","url":"https://api-docs.deepseek.com/quick_start/pricing","accessedAt":"2026-10-20 10:52:07.759524+08","robotsStatus":"allowed","collectionEligibility":"eligible","collectionCheckedAt":"2026-10-20 10:52:07.759524+08"},"evidence":{"id":"evidence.deepseek.v4-1-flash.pricing-usd.2026-10-20","locator":"DeepSeek API Models & Pricing, model details and pricing table, column deepseek-flash","excerpt":"Model details for deepseek-flash: model version DeepSeek-V4.1-Flash-1017; supports both non-thinking and thinking modes; context length 1M; max output 384K; features include JSON output, tool calls, Responses API, Anthropic API, chat prefix completion (beta), FIM completion (beta) and vision. Pricing per 1M tokens in USD: cache-hit input off-peak $0.003 and peak $0.006; cache-miss input off-peak $0.15 and peak $0.3; output off-peak $0.6 and peak $1.2; concurrency limit 2500. Notes state that deepseek-flash is the model name, off-peak rates are half of peak rates, peak hours are 01:00-04:00 and 06:00-10:00 UTC Monday through Friday excluding Chinese public holidays, and the legacy name deepseek-v4-flash is still accepted but its model has been retired and is served by DeepSeek-V4.1-Flash-1017 at the Flash price."}},{"id":"claim.version.deepseek.deepseek-v4-1-flash.input-price","fieldKey":"input_price_usd_per_mtok","value":{"unit":"USD/MTok","value":0.3},"rawValue":null,"ingestionOrigin":"curated_official","unit":"USD/MTok","condition":"Recorded on 2026-10-20 as the peak cache-miss input rate; off-peak is half of peak ($0.15) and peak hours are 01:00-04:00 and 06:00-10:00 UTC on weekdays excluding Chinese public holidays.","status":"approved","confidence":"high","reviewedBy":"system:curated-publisher","reviewedAt":"2026-10-20 13:25:48.651124+08","effectiveFrom":null,"effectiveTo":null,"source":{"id":"source.deepseek.pricing-en","title":"DeepSeek API Models & Pricing (English)","url":"https://api-docs.deepseek.com/quick_start/pricing","accessedAt":"2026-10-20 10:52:07.759524+08","robotsStatus":"allowed","collectionEligibility":"eligible","collectionCheckedAt":"2026-10-20 10:52:07.759524+08"},"evidence":{"id":"evidence.deepseek.v4-1-flash.pricing-usd.2026-10-20","locator":"DeepSeek API Models & Pricing, model details and pricing table, column deepseek-flash","excerpt":"Model details for deepseek-flash: model version DeepSeek-V4.1-Flash-1017; supports both non-thinking and thinking modes; context length 1M; max output 384K; features include JSON output, tool calls, Responses API, Anthropic API, chat prefix completion (beta), FIM completion (beta) and vision. Pricing per 1M tokens in USD: cache-hit input off-peak $0.003 and peak $0.006; cache-miss input off-peak $0.15 and peak $0.3; output off-peak $0.6 and peak $1.2; concurrency limit 2500. Notes state that deepseek-flash is the model name, off-peak rates are half of peak rates, peak hours are 01:00-04:00 and 06:00-10:00 UTC Monday through Friday excluding Chinese public holidays, and the legacy name deepseek-v4-flash is still accepted but its model has been retired and is served by DeepSeek-V4.1-Flash-1017 at the Flash price."}},{"id":"claim.version.deepseek.deepseek-v4-1-flash.lifecycle-status","fieldKey":"lifecycle_status","value":{"value":"active"},"rawValue":null,"ingestionOrigin":"curated_official","unit":null,"condition":"Set on 2026-10-20 because the pricing page lists deepseek-flash as the current model name and the release note documents the 2026-10-17 version as the model now served by the API; the earlier DeepSeek-V4-Flash-0731 version is retired and its legacy alias is served by this version.","status":"approved","confidence":"high","reviewedBy":"system:curated-publisher","reviewedAt":"2026-10-20 13:25:48.651124+08","effectiveFrom":null,"effectiveTo":null,"source":{"id":"source.deepseek.pricing-en","title":"DeepSeek API Models & Pricing (English)","url":"https://api-docs.deepseek.com/quick_start/pricing","accessedAt":"2026-10-20 10:52:07.759524+08","robotsStatus":"allowed","collectionEligibility":"eligible","collectionCheckedAt":"2026-10-20 10:52:07.759524+08"},"evidence":{"id":"evidence.deepseek.v4-1-flash.pricing-usd.2026-10-20","locator":"DeepSeek API Models & Pricing, model details and pricing table, column deepseek-flash","excerpt":"Model details for deepseek-flash: model version DeepSeek-V4.1-Flash-1017; supports both non-thinking and thinking modes; context length 1M; max output 384K; features include JSON output, tool calls, Responses API, Anthropic API, chat prefix completion (beta), FIM completion (beta) and vision. Pricing per 1M tokens in USD: cache-hit input off-peak $0.003 and peak $0.006; cache-miss input off-peak $0.15 and peak $0.3; output off-peak $0.6 and peak $1.2; concurrency limit 2500. Notes state that deepseek-flash is the model name, off-peak rates are half of peak rates, peak hours are 01:00-04:00 and 06:00-10:00 UTC Monday through Friday excluding Chinese public holidays, and the legacy name deepseek-v4-flash is still accepted but its model has been retired and is served by DeepSeek-V4.1-Flash-1017 at the Flash price."}},{"id":"claim.version.deepseek.deepseek-v4-1-flash.max-output","fieldKey":"max_output_tokens","value":{"unit":"tokens","value":384000},"rawValue":null,"ingestionOrigin":"curated_official","unit":"tokens","condition":"Recorded on 2026-10-20 from the pricing page model details: max output 384K.","status":"approved","confidence":"high","reviewedBy":"system:curated-publisher","reviewedAt":"2026-10-20 13:25:48.651124+08","effectiveFrom":null,"effectiveTo":null,"source":{"id":"source.deepseek.pricing-en","title":"DeepSeek API Models & Pricing (English)","url":"https://api-docs.deepseek.com/quick_start/pricing","accessedAt":"2026-10-20 10:52:07.759524+08","robotsStatus":"allowed","collectionEligibility":"eligible","collectionCheckedAt":"2026-10-20 10:52:07.759524+08"},"evidence":{"id":"evidence.deepseek.v4-1-flash.pricing-usd.2026-10-20","locator":"DeepSeek API Models & Pricing, model details and pricing table, column deepseek-flash","excerpt":"Model details for deepseek-flash: model version DeepSeek-V4.1-Flash-1017; supports both non-thinking and thinking modes; context length 1M; max output 384K; features include JSON output, tool calls, Responses API, Anthropic API, chat prefix completion (beta), FIM completion (beta) and vision. Pricing per 1M tokens in USD: cache-hit input off-peak $0.003 and peak $0.006; cache-miss input off-peak $0.15 and peak $0.3; output off-peak $0.6 and peak $1.2; concurrency limit 2500. Notes state that deepseek-flash is the model name, off-peak rates are half of peak rates, peak hours are 01:00-04:00 and 06:00-10:00 UTC Monday through Friday excluding Chinese public holidays, and the legacy name deepseek-v4-flash is still accepted but its model has been retired and is served by DeepSeek-V4.1-Flash-1017 at the Flash price."}},{"id":"claim.version.deepseek.deepseek-v4-1-flash.output-price","fieldKey":"output_price_usd_per_mtok","value":{"unit":"USD/MTok","value":1.2},"rawValue":null,"ingestionOrigin":"curated_official","unit":"USD/MTok","condition":"Recorded on 2026-10-20 as the peak output rate; off-peak is half of peak ($0.60). The page lists cache-hit input separately at $0.006 peak and $0.003 off-peak per 1M tokens.","status":"approved","confidence":"high","reviewedBy":"system:curated-publisher","reviewedAt":"2026-10-20 13:25:48.651124+08","effectiveFrom":null,"effectiveTo":null,"source":{"id":"source.deepseek.pricing-en","title":"DeepSeek API Models & Pricing (English)","url":"https://api-docs.deepseek.com/quick_start/pricing","accessedAt":"2026-10-20 10:52:07.759524+08","robotsStatus":"allowed","collectionEligibility":"eligible","collectionCheckedAt":"2026-10-20 10:52:07.759524+08"},"evidence":{"id":"evidence.deepseek.v4-1-flash.pricing-usd.2026-10-20","locator":"DeepSeek API Models & Pricing, model details and pricing table, column deepseek-flash","excerpt":"Model details for deepseek-flash: model version DeepSeek-V4.1-Flash-1017; supports both non-thinking and thinking modes; context length 1M; max output 384K; features include JSON output, tool calls, Responses API, Anthropic API, chat prefix completion (beta), FIM completion (beta) and vision. Pricing per 1M tokens in USD: cache-hit input off-peak $0.003 and peak $0.006; cache-miss input off-peak $0.15 and peak $0.3; output off-peak $0.6 and peak $1.2; concurrency limit 2500. Notes state that deepseek-flash is the model name, off-peak rates are half of peak rates, peak hours are 01:00-04:00 and 06:00-10:00 UTC Monday through Friday excluding Chinese public holidays, and the legacy name deepseek-v4-flash is still accepted but its model has been retired and is served by DeepSeek-V4.1-Flash-1017 at the Flash price."}},{"id":"claim.version.deepseek.deepseek-v4-1-flash.release-date","fieldKey":"release_date","value":{"value":"2026-10-17","precision":"day"},"rawValue":null,"ingestionOrigin":"curated_official","unit":null,"condition":"Set on 2026-10-20 from the official release note index entry 'DeepSeek-V4.1-Flash-1017 Release 2026/10/17'.","status":"approved","confidence":"high","reviewedBy":"system:curated-publisher","reviewedAt":"2026-10-20 13:25:48.651124+08","effectiveFrom":null,"effectiveTo":null,"source":{"id":"source.deepseek.v4-1-flash-news-2026-10-17","title":"DeepSeek-V4.1-Flash-1017 Release","url":"https://api-docs.deepseek.com/news/news261017","accessedAt":"2026-10-20 13:25:47.827693+08","robotsStatus":"allowed","collectionEligibility":"eligible","collectionCheckedAt":"2026-10-20 13:25:47.827693+08"},"evidence":{"id":"evidence.deepseek.v4-1-flash-news.2026-10-17","locator":"DeepSeek release note 'DeepSeek-V4.1-Flash-1017: Wish-Driven Programming Made Real' (news261017)","excerpt":"The news index lists 'DeepSeek-V4.1-Flash-1017 Release 2026/10/17' and the release note introduces DeepSeek-V4.1-Flash-1017 as the current DeepSeek Flash model served through the DeepSeek API."}}],"benchmarks":[]}],"dataUpdatedAt":"2026-10-20 13:25:48.651124+08","latestVersion":{"id":"version.deepseek.deepseek-v4-1-flash-1017","name":"DeepSeek-V4.1-Flash-1017","externalModelId":"deepseek-flash","status":"active"},"dataQuality":{"approved":19,"pending":0,"stale":4,"conflicted":0},"availabilityRegions":["global"],"availabilityChannels":["api"],"availabilityScopes":["global|api"],"decisionReadiness":{"overall":"A","evaluatedAt":"2026-11-01T11:31:17.790Z","tracks":[{"key":"api","applicable":true,"grade":"A","verifiedAt":"2026-10-20 13:23:01+08","satisfiedFields":["release_date","lifecycle_status","capability_tags","deployment_options","context_window_tokens","api_id","input_price_usd_per_mtok","output_price_usd_per_mtok","availability"],"missingFields":[],"missingEvidenceFields":[],"staleFields":[],"conflictedFields":[],"ineligibleSourceFields":[],"reasons":[],"fields":[{"fieldKey":"release_date","status":"satisfied","verifiedAt":"2026-10-20 13:25:48.651124+08","expiresAt":"2027-01-18T05:25:48.651Z"},{"fieldKey":"lifecycle_status","status":"satisfied","verifiedAt":"2026-10-20 13:25:48.651124+08","expiresAt":"2026-11-19T05:25:48.651Z"},{"fieldKey":"capability_tags","status":"satisfied","verifiedAt":"2026-10-20 13:25:48.651124+08","expiresAt":"2027-01-18T05:25:48.651Z"},{"fieldKey":"deployment_options","status":"satisfied","verifiedAt":"2026-10-20 13:25:48.651124+08","expiresAt":"2027-01-18T05:25:48.651Z"},{"fieldKey":"context_window_tokens","status":"satisfied","verifiedAt":"2026-10-20 13:25:48.651124+08","expiresAt":"2027-01-18T05:25:48.651Z"},{"fieldKey":"api_id","status":"satisfied","verifiedAt":"2026-10-20 13:25:48.651124+08","expiresAt":"2027-01-18T05:25:48.651Z"},{"fieldKey":"input_price_usd_per_mtok","status":"satisfied","verifiedAt":"2026-10-20 13:25:48.651124+08","expiresAt":"2026-11-19T05:25:48.651Z"},{"fieldKey":"output_price_usd_per_mtok","status":"satisfied","verifiedAt":"2026-10-20 13:25:48.651124+08","expiresAt":"2026-11-19T05:25:48.651Z"},{"fieldKey":"availability","status":"satisfied","verifiedAt":"2026-10-20 13:23:01+08","expiresAt":"2026-11-19T05:23:01.000Z"}]},{"key":"self_hosted","applicable":false,"grade":"incomplete","verifiedAt":null,"satisfiedFields":[],"missingFields":[],"missingEvidenceFields":[],"staleFields":[],"conflictedFields":[],"ineligibleSourceFields":[],"reasons":[],"fields":[]}]},"timeline":[{"id":"timeline.version.version.deepseek.deepseek-v4-flash","kind":"version","subjectId":"version.deepseek.deepseek-v4-flash","date":"2026-07-31","datePrecision":"day","title":"DeepSeek-V4-Flash-0731","summary":"模型版本 · superseded","eventType":"version","lifecycleStatus":"superseded","source":null},{"id":"event.version.deepseek.deepseek-v4-flash.api-update-0731","kind":"event","subjectId":"version.deepseek.deepseek-v4-flash","date":"2026-07-31","datePrecision":"day","title":"DeepSeek V4 Flash API 更新为 0731 版本","summary":"DeepSeek 官方 API 文档记录 v4-flash 已更新为 DeepSeek-V4-Flash-0731，调用方式保持不变；官网 2026-07-31 发布快照提供同日正式版 API 公测公告。","eventType":"update","lifecycleStatus":null,"source":{"id":"source.deepseek.v4-release-2026-07","title":"DeepSeek API V4 Flash 0731 update","url":"https://api-docs.deepseek.com/"}},{"id":"event.version.deepseek.deepseek-v4-flash.public-beta","kind":"event","subjectId":"version.deepseek.deepseek-v4-flash","date":"2026-07-31","datePrecision":"day","title":"DeepSeek V4 Flash 正式版 API 上线公测","summary":"DeepSeek 官网原文称“DeepSeek-V4-Flash 正式版 API 已上线公测”，并强调 Agent 能力大幅增强；V4 Pro 暂未变动。","eventType":"release","lifecycleStatus":null,"source":{"id":"source.deepseek.website.home","title":"DeepSeek official website","url":"https://www.deepseek.com/"}},{"id":"timeline.version.version.deepseek.deepseek-v4-1-flash-1017","kind":"version","subjectId":"version.deepseek.deepseek-v4-1-flash-1017","date":"2026-10-17","datePrecision":"day","title":"DeepSeek-V4.1-Flash-1017","summary":"模型版本 · active","eventType":"version","lifecycleStatus":"active","source":null}],"availability":[{"id":"availability.deepseek.deepseek-v4-1-flash.global.api","versionId":"version.deepseek.deepseek-v4-1-flash-1017","versionName":"DeepSeek-V4.1-Flash-1017","accessChannel":"api","regionCode":"global","regionName":"global","status":"available","restriction":null,"effectiveFrom":"2026-10-17 08:00:00+08","effectiveTo":null,"source":{"id":"source.deepseek.pricing-en","title":"DeepSeek API Models & Pricing (English)","url":"https://api-docs.deepseek.com/quick_start/pricing"},"evidence":{"id":"evidence.deepseek.v4-1-flash.pricing-usd.2026-10-20","excerpt":"Model details for deepseek-flash: model version DeepSeek-V4.1-Flash-1017; supports both non-thinking and thinking modes; context length 1M; max output 384K; features include JSON output, tool calls, Responses API, Anthropic API, chat prefix completion (beta), FIM completion (beta) and vision. Pricing per 1M tokens in USD: cache-hit input off-peak $0.003 and peak $0.006; cache-miss input off-peak $0.15 and peak $0.3; output off-peak $0.6 and peak $1.2; concurrency limit 2500. Notes state that deepseek-flash is the model name, off-peak rates are half of peak rates, peak hours are 01:00-04:00 and 06:00-10:00 UTC Monday through Friday excluding Chinese public holidays, and the legacy name deepseek-v4-flash is still accepted but its model has been retired and is served by DeepSeek-V4.1-Flash-1017 at the Flash price."}}],"enterpriseCases":[],"useCases":[],"deploymentProfiles":[],"learningResources":[],"trainingProfiles":[],"publication":{"approvedClaimsOnly":true,"note":"页面只展示已审核 Claim；待审核数据不会被当作公开事实。"}}