Switch model

API PRICES

DeepSeek · deepseek-v4-flash

Provider prices, cheapest first

Browse all models

Price comparison

Official (cash)
Input 0.3 / output 1.2 USD/million tokensDeepSeek ·
Lowest inference provider (cash)
Input 0.09 / output 0.18 USD/million tokensDeepInfra ·
Lowest relay (credit)
4.05 USD credit/million total tokenscnapi.kksj.org "default" ·

Official and inference-provider prices are cash; relay prices are site credit (USD credit or CNY credit), a different unit, compared separately. Relay prices are per million total tokens at 75% input and 25% output.

All official and inference price observations

DeepSeek · deepseek-v4-flash official price: input 0.3, output 1.2 USD per million tokens (DeepSeek, observed 2026-10-24). Cheapest inference provider: DeepInfra, input 0.09, output 0.18 USD per million tokens. Cheapest relay: cnapi.kksj.org, group "default" 4.05 USD_CREDIT per million total tokens (credit price, not cash, observed 2026-10-23). 182 sites have comparable prices; 510 sites list this model.Relay blended price uses 75% input and 25% output. Conditions: tariffWindow: PEAK · declaredTemporalCondition: Peak hours are 01:00 - 04:00 and 06:00 - 10:00 UTC, Monday through Friday, excluding Chinese public holidays. All other hours are off-peak, including we…

Price ranges per million tokens

Official cash prices · Lowest 0.525 · median 0.525 · highest 0.525 · 1 quotes USD / per million tokens

Official cash prices · Lowest 3.5 · median 3.5 · highest 3.5 · 1 quotes CNY / per million tokens

Inference provider cash prices · Lowest 0.1125 · median 0.11313 · highest 0.11375 · 2 quotes USD / per million tokens

Inference provider cash prices · Lowest 4.5 · median 4.5 · highest 4.5 · 1 quotes CNY / per million tokens

Relay USD credit prices · Lowest 4.05 · median 4.725 · highest 5.4 · 2 quotes USD / per million tokens, site credit

Official price

ProviderTariffInputOutputCache readCache writeUnitObservedConditions and source
DeepSeekStandard0.31.20.006—USD / 1M tokenstariffWindow: PEAK · declaredTemporalCondition: Peak hours are 01:00 - 04:00 and 06:00 - 10:00 UTC, Monday through Friday, excluding Chinese public holidays. All other hours are off-peak, including we…
Full price conditions
{
  "sourceUnit": null,
  "sourceAmounts": null,
  "conditions": [],
  "contextTier": null,
  "processingMode": null,
  "conditionNotes": [
    "tariffWindow: PEAK",
    "declaredTemporalCondition: Peak hours are 01:00 - 04:00 and 06:00 - 10:00 UTC, Monday through Friday, excluding Chinese public holidays. All other hours are off-peak, including weekends and Chinese public holidays in full."
  ],
  "effectiveFrom": null,
  "effectiveUntil": null
}

Official source
DeepSeekStandard280.04—CNY / 1M tokenstariffWindow: PEAK · declaredTemporalCondition: 北京时间周一至周五(不含中国法定节假日)9:00 - 12:00、14:00 - 18:00 为高峰时段;其余时段,包括周末及中国法定节假日全天均为空闲时段。
Full price conditions
{
  "sourceUnit": null,
  "sourceAmounts": null,
  "conditions": [],
  "contextTier": null,
  "processingMode": null,
  "conditionNotes": [
    "tariffWindow: PEAK",
    "declaredTemporalCondition: 北京时间周一至周五(不含中国法定节假日)9:00 - 12:00、14:00 - 18:00 为高峰时段;其余时段,包括周末及中国法定节假日全天均为空闲时段。"
  ],
  "effectiveFrom": null,
  "effectiveUntil": null
}

Official source

Official prices are the vendor's cash prices. Inference providers also list cash prices and can be compared directly. Relays list prices in site credit; what you actually pay depends on each site's top-up rate, so they cannot be compared with official prices directly.

Inference providers

ProviderTariffInputOutputCache readCache writeUnitObservedConditions and sourcevs official
DeepInfraStandard0.090.180.018—USD / 1M tokens
Full price conditions
{
  "sourceUnit": null,
  "sourceAmounts": null,
  "conditions": [],
  "contextTier": null,
  "processingMode": null,
  "conditionNotes": [],
  "effectiveFrom": null,
  "effectiveUntil": null
}

Official source
OpenRouter · AggregatorStandard0.0910.1820.0182—USD / 1M tokens
Full price conditions
{
  "sourceUnit": "USD_PER_TOKEN",
  "sourceAmounts": {
    "cacheRead": "0.0000000182",
    "input": "0.000000091",
    "output": "0.000000182"
  },
  "conditions": [],
  "contextTier": null,
  "processingMode": null,
  "conditionNotes": [],
  "effectiveFrom": null,
  "effectiveUntil": null
}

Official source
SiliconFlowStandard390.3—CNY / 1M tokenstime window as stated (time zone not stated): 费用发生时段: 0点~2点/8点~24点
Full price conditions
{
  "sourceUnit": null,
  "sourceAmounts": null,
  "conditions": [],
  "contextTier": null,
  "processingMode": null,
  "conditionNotes": [
    "time window as stated (time zone not stated): 费用发生时段: 0点~2点/8点~24点"
  ],
  "effectiveFrom": null,
  "effectiveUntil": null
}

Official source
Other tariffs and prices to review

Official price

ProviderTariffInputOutputCache readCache writeUnitObservedConditions and source
DeepSeekOff-peak0.150.60.003—USD / 1M tokenstariffWindow: OFF_PEAK · declaredTemporalCondition: Peak hours are 01:00 - 04:00 and 06:00 - 10:00 UTC, Monday through Friday, excluding Chinese public holidays. All other hours are off-peak, including we…
Full price conditions
{
  "sourceUnit": null,
  "sourceAmounts": null,
  "conditions": [
    "tariffWindow: OFF_PEAK"
  ],
  "contextTier": null,
  "processingMode": null,
  "conditionNotes": [
    "declaredTemporalCondition: Peak hours are 01:00 - 04:00 and 06:00 - 10:00 UTC, Monday through Friday, excluding Chinese public holidays. All other hours are off-peak, including weekends and Chinese public holidays in full."
  ],
  "effectiveFrom": null,
  "effectiveUntil": null
}

Official source
DeepSeekOff-peak140.02—CNY / 1M tokenstariffWindow: OFF_PEAK · declaredTemporalCondition: 北京时间周一至周五(不含中国法定节假日)9:00 - 12:00、14:00 - 18:00 为高峰时段;其余时段,包括周末及中国法定节假日全天均为空闲时段。
Full price conditions
{
  "sourceUnit": null,
  "sourceAmounts": null,
  "conditions": [
    "tariffWindow: OFF_PEAK"
  ],
  "contextTier": null,
  "processingMode": null,
  "conditionNotes": [
    "declaredTemporalCondition: 北京时间周一至周五(不含中国法定节假日)9:00 - 12:00、14:00 - 18:00 为高峰时段;其余时段,包括周末及中国法定节假日全天均为空闲时段。"
  ],
  "effectiveFrom": null,
  "effectiveUntil": null
}

Official source

Inference providers

ProviderTariffInputOutputCache readCache writeUnitObservedConditions and source
SiliconFlowOff-peak1.54.50.15—CNY / 1M tokenstime window as stated (time zone not stated): 费用发生时段: 2点~8点
Full price conditions
{
  "sourceUnit": null,
  "sourceAmounts": null,
  "conditions": [],
  "contextTier": null,
  "processingMode": null,
  "conditionNotes": [
    "time window as stated (time zone not stated): 费用发生时段: 2点~8点"
  ],
  "effectiveFrom": null,
  "effectiveUntil": null
}

Official source
Older official and inference provider prices

Earlier price observations and their original conditions

Official price

ProviderTariffInputOutputCache readCache writeUnitObservedConditions and source
DeepSeekOff-peak140.02—CNY / 1M tokenstariffWindow: OFF_PEAK · declaredTemporalCondition: 北京时间周一至周五(不含中国法定节假日)9:00 - 12:00、14:00 - 18:00 为高峰时段;其余时段,包括周末及中国法定节假日全天均为空闲时段。
Full price conditions
{
  "sourceUnit": null,
  "sourceAmounts": null,
  "conditions": [
    "tariffWindow: OFF_PEAK"
  ],
  "contextTier": null,
  "processingMode": null,
  "conditionNotes": [
    "declaredTemporalCondition: 北京时间周一至周五(不含中国法定节假日)9:00 - 12:00、14:00 - 18:00 为高峰时段;其余时段,包括周末及中国法定节假日全天均为空闲时段。"
  ],
  "effectiveFrom": null,
  "effectiveUntil": null
}

Official source
DeepSeekStandard280.04—CNY / 1M tokenstariffWindow: PEAK · declaredTemporalCondition: 北京时间周一至周五(不含中国法定节假日)9:00 - 12:00、14:00 - 18:00 为高峰时段;其余时段,包括周末及中国法定节假日全天均为空闲时段。
Full price conditions
{
  "sourceUnit": null,
  "sourceAmounts": null,
  "conditions": [],
  "contextTier": null,
  "processingMode": null,
  "conditionNotes": [
    "tariffWindow: PEAK",
    "declaredTemporalCondition: 北京时间周一至周五(不含中国法定节假日)9:00 - 12:00、14:00 - 18:00 为高峰时段;其余时段,包括周末及中国法定节假日全天均为空闲时段。"
  ],
  "effectiveFrom": null,
  "effectiveUntil": null
}

Official source
DeepSeekOff-peak0.150.60.003—USD / 1M tokenstariffWindow: OFF_PEAK · declaredTemporalCondition: Peak hours are 01:00 - 04:00 and 06:00 - 10:00 UTC, Monday through Friday, excluding Chinese public holidays. All other hours are off-peak, including we…
Full price conditions
{
  "sourceUnit": null,
  "sourceAmounts": null,
  "conditions": [
    "tariffWindow: OFF_PEAK"
  ],
  "contextTier": null,
  "processingMode": null,
  "conditionNotes": [
    "declaredTemporalCondition: Peak hours are 01:00 - 04:00 and 06:00 - 10:00 UTC, Monday through Friday, excluding Chinese public holidays. All other hours are off-peak, including weekends and Chinese public holidays in full."
  ],
  "effectiveFrom": null,
  "effectiveUntil": null
}

Official source
DeepSeekStandard0.31.20.006—USD / 1M tokenstariffWindow: PEAK · declaredTemporalCondition: Peak hours are 01:00 - 04:00 and 06:00 - 10:00 UTC, Monday through Friday, excluding Chinese public holidays. All other hours are off-peak, including we…
Full price conditions
{
  "sourceUnit": null,
  "sourceAmounts": null,
  "conditions": [],
  "contextTier": null,
  "processingMode": null,
  "conditionNotes": [
    "tariffWindow: PEAK",
    "declaredTemporalCondition: Peak hours are 01:00 - 04:00 and 06:00 - 10:00 UTC, Monday through Friday, excluding Chinese public holidays. All other hours are off-peak, including weekends and Chinese public holidays in full."
  ],
  "effectiveFrom": null,
  "effectiveUntil": null
}

Official source

Inference providers

ProviderTariffInputOutputCache readCache writeUnitObservedConditions and source
SiliconFlowOff-peak1.54.50.15—CNY / 1M tokenstime window as stated (time zone not stated): 费用发生时段: 2点~8点
Full price conditions
{
  "sourceUnit": null,
  "sourceAmounts": null,
  "conditions": [],
  "contextTier": null,
  "processingMode": null,
  "conditionNotes": [
    "time window as stated (time zone not stated): 费用发生时段: 2点~8点"
  ],
  "effectiveFrom": null,
  "effectiveUntil": null
}

Official source
SiliconFlowStandard390.3—CNY / 1M tokenstime window as stated (time zone not stated): 费用发生时段: 0点~2点/8点~24点
Full price conditions
{
  "sourceUnit": null,
  "sourceAmounts": null,
  "conditions": [],
  "contextTier": null,
  "processingMode": null,
  "conditionNotes": [
    "time window as stated (time zone not stated): 费用发生时段: 0点~2点/8点~24点"
  ],
  "effectiveFrom": null,
  "effectiveUntil": null
}

Official source
OpenRouter · AggregatorStandard0.0910.1820.0182—USD / 1M tokens
Full price conditions
{
  "sourceUnit": "USD_PER_TOKEN",
  "sourceAmounts": {
    "cacheRead": "0.0000000182",
    "input": "0.000000091",
    "output": "0.000000182"
  },
  "conditions": [],
  "contextTier": null,
  "processingMode": null,
  "conditionNotes": [],
  "effectiveFrom": null,
  "effectiveUntil": null
}

Official source
DeepInfraStandard0.090.180.018—USD / 1M tokens
Full price conditions
{
  "sourceUnit": null,
  "sourceAmounts": null,
  "conditions": [],
  "contextTier": null,
  "processingMode": null,
  "conditionNotes": [],
  "effectiveFrom": null,
  "effectiveUntil": null
}

Official source

Unit: USD credits per 1M tokens. These are site-credit prices; actual cost depends on each site’s top-up rate.

Filtering by provider: cnapi.kksj.org

Searching…

Browse all providers
Clear filters

Blended price = input × 75% + output × 25%, without cache.

Price range: lowest 4.05 · median 4.725 · highest 5.4 (2 quotes, USD credits per million total tokens)

sites have comparable prices182510 sites list this model; approximately 1 operators
Lowest input price2.7USD credits / 1M
Median of each provider’s lowest price2.7USD credits / 1M

Relays

Prices below are in site credit, not cash.

#ProviderPlan / conditionsInput ↑USD credits / 1MOutput USD credits / 1MCache readUSD credits / 1MBlendedUSD credits / 1MDetails
Recent price
01cnapi.kksj.orgAsk or discussCollected:
Collected this cycle
View 2 plans
default
Default group, AZ channel plus official reverse-engineered channel for some models, AZ first, reverse-engineered as fallback, auto-tuning (default) [machine translation]Original: 默认分组,AZ渠道加部分模型官方逆向渠道,优先AZ,保底逆向,自动调优(default)
Operator pending verification
2.78.1—4.05Median price ÷ this price: 1.2×Full prices and sources
02cnapi.kksj.orgAsk or discussCollected:
Collected this cycle
View 2 plans
azpro
More az concurrency group (azpro) [machine translation]Original: 更多的az并发分组(azpro)
Operator pending verification
3.610.8—5.4Median price ÷ this price: 0.9×Full prices and sources
Special groups · 5 rows · not ranked

These plans are marked as test, internal, disabled, gated by top-up or membership, or have a near-zero ratio. They may not be purchasable or stable, so they are listed separately and left out of the ranking and statistics.

  • Free declaration, listed separately: 4 rows
  • zero-ratio group: 4 rows
  • near-zero-ratio group: 1 rows
  • ai.38yun.cn · Professional free model channel [machine translation]Group on site: 专业免费模型通道 · deepseek-ai/deepseek-v4-flash · Input 0 / Output 0 USD credits / 1M
  • api.wapq.cn · Perk [machine translation]Group on site: 福利 · deepseek-v4-flash · Input 0 / Output 0 USD credits / 1M
  • omnigate.cc · deepseek-v4-flash free channel, hammer it [machine translation]Group on site: deepseek-v4-flash免费渠道,请猛攻 · deepseek-v4-flash · Input 0 / Output 0 USD credits / 1M
  • wqdsjhaoai.site · amd free models [machine translation]Group on site: amd免费模型 · DeepSeek-V4-Flash · Input 0 / Output 0 USD credits / 1M
  • 222650156.xyz · Perk free [machine translation]Group on site: 福利free · free/deepseek-v4-flash · Input 0.0001 / Output 0.0002 USD credits / 1M
View all 5 rows →
Related variants · 2 rows · not ranked

These are special editions of the model (thinking, max, search, batch, long context, free, etc.). They are priced differently from the base model, so they are listed separately and not ranked. Names that only add an effort level such as low, high or nothinking are compared with the base model.

  • deepseek-v4-flash-max (-max · max edition): 1 rows
  • deepseek-v4-flash:free (:free · free variant): 1 rows
  • xckjj.com · Chinese models [machine translation]Group on site: 国模 · deepseek-v4-flash:free · Input 0.014 / Output 0.028 USD credits / 1M
  • yinli.one · deepseek · deepseek-v4-flash-max · Input 1 / Output 2 USD credits / 1M
View all 2 rows →
How this ranking works

All per-token prices: 93,968 prices from 854 sites (about 751 companies). 84,786 are ranked, from 838 sites (about 736 companies); 9,182 more are listed separately and not ranked. Prices collected up to 2026-10-24.

This model has 1023 recorded prices; 298 can be compared directly (287 ranked, 11 listed separately). Not comparable yet: tiered by rules (see Tiered prices) 313, price not parsed yet 216, new price under review; showing the previous one 60, billed per request or another unit 58, display unit not confirmed 34, ratio looks unset 24, scope of the official doc price not confirmed 8

2 recent · 0 stale (older than 10 days, or not updated by this refresh) · 0 unverified timestamps. Minimum and median only count recent paid prices; older prices stay in the table. 0 zero-valued pairs are separately unverified, without proof of free eligibility. Timing does not verify payment, upstream identity or quality.

Prices are converted to site credits using each site’s published ratio. What you actually pay depends on its top-up rate. Input, output and cache prices in each row come from the same plan. Several sites run by the same company take one place in the ranking: its cheapest plan, with the other sites listed under it. We judge “same company” by identical prices, status pages or homepage code; this is not a legal finding. To see every site’s prices, choose “All plans” or filter by provider.

“Self-declared unofficial channel” means the plan name itself says “reverse-engineered” or similar. We have not verified their source or quality. Minimum and median only count regular plans.

Full methodology →

Sources not accepted this cycle and reasons

Manufacturer documentation and lifecycle

These manufacturer statements do not verify relay backends, availability, GPU ownership or cash eligibility. Aliases are never merged automatically.

Alias observations over time · deepseek-v4-flash

Current documented target: deepseek-flash · Target version: DeepSeek-V4.1-Flash-1017

RETIRED_MODEL_LEGACY_ROUTE_STILL_ACCEPTED

Documentation checked: 2026-10-23T20:08:17.113847+00:00

Complete declarations and historical observations
{
  "alias": "deepseek-v4-flash",
  "author": "DeepSeek",
  "autoMergeAllowed": false,
  "currentObservation": {
    "checkedAt": [
      "2026-10-23T20:08:17.113847+00:00"
    ],
    "isIdentityEquivalence": false,
    "sourceIds": [
      "availability:deepseek-intro"
    ],
    "status": "RETIRED_MODEL_LEGACY_ROUTE_STILL_ACCEPTED",
    "targetModelId": "deepseek-flash",
    "targetVersion": "DeepSeek-V4.1-Flash-1017"
  },
  "key": "DeepSeek::deepseek-v4-flash",
  "lifecycleNotices": [
    {
      "author": "DeepSeek",
      "availability": "RETIRED_WITH_COMPATIBILITY_REDIRECT",
      "availabilityScope": "DeepSeek official API",
      "backendTested": false,
      "deprecationAnnouncedOn": null,
      "documentationReadAt": "2026-10-23T20:08:17.113847+00:00",
      "documentedAliases": [],
      "endpointDisposition": "CONTINUES_ACCEPTING_REQUESTS_REDIRECTED",
      "evidenceKeys": [
        "deepseek-updates",
        "deepseek-intro"
      ],
      "newUserAccessDateStatus": "NOT_ESTABLISHED_BY_REVIEWED_DOCUMENTATION",
      "newUserAccessStopsOn": null,
      "note": "原厂当前首页确认旧名仍接受并由 V4.1-Flash-1017 服务;不等同原模型仍在售。",
      "officialId": "deepseek-v4-flash",
      "qualificationEffect": "DOCUMENTATION_ONLY_NO_AUTOMATIC_PRICE_OR_RANKING_CHANGE",
      "recommendedReplacements": [
        "deepseek-flash"
      ],
      "retiredBy": "2026-09-10",
      "retirementDate": null,
      "retirementDateBasis": "9/10 announcement states predecessors have retired; exact retirement date/time not established.",
      "routeTarget": "deepseek-flash",
      "servedModelVersion": "DeepSeek-V4.1-Flash-1017",
      "sourceIds": [
        "availability:deepseek-updates",
        "availability:deepseek-intro"
      ],
      "sourceUrls": [
        "https://api-docs.deepseek.com/updates/",
        "https://api-docs.deepseek.com/"
      ],
      "verifiedOn": "2026-10-23"
    }
  ],
  "observations": [
    {
      "baselineVerifiedOn": "2026-10-19",
      "checkedAt": [
        "2026-10-19T02:23:01.035345+00:00"
      ],
      "sourceIds": [
        "4i:deepseek-pricing"
      ],
      "status": "old_model_retired_requests_rerouted",
      "targetModelId": "deepseek-flash",
      "targetVersion": "DeepSeek-V4.1-Flash-1017"
    },
    {
      "checkedAt": [
        "2026-10-23T20:08:17.113847+00:00"
      ],
      "isIdentityEquivalence": false,
      "sourceIds": [
        "availability:deepseek-intro"
      ],
      "status": "RETIRED_MODEL_LEGACY_ROUTE_STILL_ACCEPTED",
      "targetModelId": "deepseek-flash",
      "targetVersion": "DeepSeek-V4.1-Flash-1017"
    }
  ],
  "recommendedReplacementObservations": [],
  "relationship": "accepted_legacy_route",
  "runtimeBackendVerified": false
}

deepseek-v4-flash

Manufacturer-declared status
RETIRED_WITH_COMPATIBILITY_REDIRECT
Deprecation date (separate from retirement)
Not specified
New-user access cutoff
Not specified
Model retirement date
Not specified
Already retired by (not exact retirement date)
2026-09-10
Compatibility route target (not identity equivalence)
deepseek-flash
Manufacturer-declared serving version
DeepSeek-V4.1-Flash-1017
Recommended migration (not an alias)
deepseek-flash
Documentation checked
2026-10-23T20:08:17.113847+00:00

原厂当前首页确认旧名仍接受并由 V4.1-Flash-1017 服务;不等同原模型仍在售。

原模型已退役,旧 API 名保留并转到另一服务模型。

Complete declarations and historical observations
{
  "author": "DeepSeek",
  "availability": "RETIRED_WITH_COMPATIBILITY_REDIRECT",
  "availabilityScope": "DeepSeek official API",
  "backendTested": false,
  "deprecationAnnouncedOn": null,
  "documentationReadAt": "2026-10-23T20:08:17.113847+00:00",
  "documentedAliases": [],
  "endpointDisposition": "CONTINUES_ACCEPTING_REQUESTS_REDIRECTED",
  "evidenceKeys": [
    "deepseek-updates",
    "deepseek-intro"
  ],
  "newUserAccessDateStatus": "NOT_ESTABLISHED_BY_REVIEWED_DOCUMENTATION",
  "newUserAccessStopsOn": null,
  "note": "原厂当前首页确认旧名仍接受并由 V4.1-Flash-1017 服务;不等同原模型仍在售。",
  "officialId": "deepseek-v4-flash",
  "qualificationEffect": "DOCUMENTATION_ONLY_NO_AUTOMATIC_PRICE_OR_RANKING_CHANGE",
  "recommendedReplacements": [
    "deepseek-flash"
  ],
  "retiredBy": "2026-09-10",
  "retirementDate": null,
  "retirementDateBasis": "9/10 announcement states predecessors have retired; exact retirement date/time not established.",
  "routeTarget": "deepseek-flash",
  "servedModelVersion": "DeepSeek-V4.1-Flash-1017",
  "sourceUrls": [
    "https://api-docs.deepseek.com/updates/",
    "https://api-docs.deepseek.com/"
  ],
  "verifiedOn": "2026-10-23"
}

Download complete public documentation archive, including unmatched items

FAQ

Which API is cheapest for DeepSeek · deepseek-v4-flash?

cnapi.kksj.org, group "default", 4.05 USD credit per million total tokens, observed 2026-10-23. 182 sites have comparable prices.

What is the official price for DeepSeek · deepseek-v4-flash?

Input 0.3, output 1.2 USD per million tokens, checked 2026-10-24. Lowest inference provider: DeepInfra, input 0.09, output 0.18 USD per million tokens.

How do I use DeepSeek · deepseek-v4-flash in Claude Code or Codex?

Install Grandet Skill, then say "Connect the cheapest DeepSeek · deepseek-v4-flash API to Claude Code for me". Install Skill →