API PRICES
DeepSeek · deepseek-v4-flash
Provider prices, cheapest first
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 · Input 70% lower than official · output 85% lower than official ·
- Lowest relay (credit)
- 0 USD credit/million total tokensai.38yun.cn "GPT 稳定渠道" ·
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.
DeepSeek · deepseek-v4-flash official price: input 0.3, output 1.2 USD per million tokens (DeepSeek, observed 2026-10-17). Cheapest inference provider: DeepInfra, input 0.09, output 0.18 USD per million tokens. Cheapest relay: ai.38yun.cn, group "GPT stable channel [machine translation] (on site: GPT 稳定渠道)" 0 USD_CREDIT per million total tokens (credit price, not cash, observed 2026-10-16). 221 sites have comparable prices; 527 sites list this model.Relay blended price uses 75% input and 25% output.
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
Relay USD credit prices · Lowest 0.044669 · median 1.25 · highest 30 · 224 quotes USD / per million tokens, site credit
Relay CNY credit prices · Lowest 0.0000013 · median 1.25 · highest 7.8 · 57 quotes CNY / per million tokens, site credit
Official price
| Provider | Input | Output | Cache read | Cache write | Unit | Observed | Conditions and source |
|---|---|---|---|---|---|---|---|
| DeepSeek | 0.3 | 1.2 | 0.006 | — | USD / 1M tokens | Official source | |
| DeepSeek | 2 | 8 | 0.04 | — | CNY / 1M tokens | 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
| Provider | Input | Output | Cache read | Cache write | Unit | Observed | Conditions and source | vs official |
|---|---|---|---|---|---|---|---|---|
| DeepInfra | 0.09 | 0.18 | 0.018 | — | USD / 1M tokens | Official source | Input 70% lower · Output 85% lower | |
| OpenRouter · Aggregator | 0.091 | 0.182 | 0.0182 | — | USD / 1M tokens | Official source | Input 70% lower · Output 85% lower |
Inference provider prices at least 10% above official (1)
Inference providers
| Provider | Input | Output | Cache read | Cache write | Unit | Observed | Conditions and source | vs official |
|---|---|---|---|---|---|---|---|---|
| SiliconFlow | 3 | 9 | 0.3 | — | CNY / 1M tokens | Official source | Input 50% higher · Output 13% higher |
Unit: USD credits per 1M tokens. These are site-credit prices; actual cost depends on each site’s top-up rate.
Price range: lowest 0.044669 · median 1.25 · highest 30 (224 quotes, USD credits per million total tokens)
Relays
Prices below are in site credit, not cash.
| # | Provider | Plan / conditions | Input ↑USD credits / 1M | Output USD credits / 1M | Cache readUSD credits / 1M | BlendedUSD credits / 1M | Details |
|---|---|---|---|---|---|---|---|
| Recent price | |||||||
| 01 | ihonghu.com.cnAsk or discussCollected: Collected this cycle View 2 plans | yuanli Name on site: DeepSeek-V4-Flash China Mobile [machine translation]Original: 中移 Operator pending verification | 0.03575 | 0.071425 | — | 0.044669Median price ÷ this price: 28× | Full prices and sources |
| 02 | ainzy.netAsk or discussCollected: Collected this cycle View 2 plans | chinese-model-3 Chinese models group · DeepSeek V4 / GLM-5.3 / Kimi K3 · official price at 1.5-zhe (15% of original price) | Chinese Models · DeepSeek V4 / GLM-5.3 / Kimi K3 · 15% of list [machine translation]Original: 国模组 · DeepSeek V4 / GLM-5.3 / Kimi K3 · 官方价 1.5 折 | Chinese Models · DeepSeek V4 / GLM-5.3 / Kimi K3 · 15% of list Operator pending verification | 0.05 | 0.18 | 0.0009 | 0.0825Median price ÷ this price: 15.2× | Full prices and sources |
| 03 | aws.babyAsk or discussCollected: Collected this cycle View 2 plans | Alibaba Cloud selected special offers [machine translation]Group on site: 阿里云精选特惠 Qwen GLM DeepSeek etc. high volume can use a key or sub-account [machine translation]Original: Qwen GLM DeepSeek 等 量大可以上key或子账户 Operator pending verification | 0.07 | 0.14 | 0.0014 | 0.0875Median price ÷ this price: 14.3× | Full prices and sources |
| 03 | llm.kagu.oneAsk or discussCollected: Collected this cycle View 2 plans | Hodgepodge [machine translation]Group on site: 大杂烩 Operator pending verification | 0.07 | 0.14 | 0.0014737 | 0.0875Median price ÷ this price: 14.3× | Full prices and sources |
| 05 | synai996.spaceAsk or discussCollected: Collected this cycle View 1 plans | default Default group, Chinese model related [machine translation]Original: 默认分,国产模型相关 Operator pending verification | 0.09 | 0.36 | 0.0018 | 0.1575Median price ÷ this price: 7.9× | Full prices and sources |
| 06 | api.tokengo.comAsk or discussCollected: Collected this cycle View 1 plans | default Name on site: deepseek/deepseek-v4-flash Operator pending verification | 0.098 | 0.196 | 0.028 | 0.1225Median price ÷ this price: 10.2× | Full prices and sources |
| 07 | apiqd.comAsk or discussCollected: Collected this cycle View 1 plans | deepseek All latest models supported [machine translation]Original: 最新模型均支持 Operator pending verification | 0.105 | 0.315 | 0.0105 | 0.1575Median price ÷ this price: 7.9× | Full prices and sources |
| 08 | aws.babyAsk or discussCollected: Collected this cycle View 2 plans | Alibaba Cloud Bailian major clients [machine translation]Group on site: 阿里云百炼大客户 站点写明：大客户专享 Bailian public pool, major clients only, all models; for popular models pick others with bigger discounts [machine translation]Original: 百炼公池大客户专享 全模型 热门模型请选则其他折扣更低的 Operator pending verification | 0.112 | 0.224 | 0.00224 | 0.14Median price ÷ this price: 8.9× | Full prices and sources |
| 09 | oojj.topAsk or discussCollected: Collected this cycle View 3 plans | cnmodel-w 站点标注为测试分组 cnmodel-w (Chinese models reverse-engineered channel W, no bulk external use) beta [machine translation]Original: cnmodel-w（国模逆向渠道W,禁止批量外接）测试版 Operator pending verification | 0.12 | 0.24 | 0.0024 | 0.15Median price ÷ this price: 8.3× | Full prices and sources |
| 10 | new.ainat.qzz.ioAsk or discussCollected: Collected this cycle View 1 plans | Chinese models [machine translation]Group on site: 国模 deepseek no cache [machine translation]Original: deepseek 无缓存 Operator pending verification | 0.13 | 0.52 | 0.0026 | 0.2275Median price ÷ this price: 5.5× | Full prices and sources |
| 11 | airouter.cloudAsk or discussCollected: Collected this cycle View 1 plans | default Default group [machine translation]Original: 默认分组 Operator pending verification | 0.14 | 0.28 | 0.028 | 0.175Median price ÷ this price: 7.1× | Full prices and sources |
| 11 | hk.apitoken.aiAsk or discussCollected: Collected this cycle View 9 plans | bi bi Operator pending verification | 0.14 | 0.28 | 0.028 | 0.175Median price ÷ this price: 7.1× | Full prices and sources |
| 11 | hk.apitoken.aiAsk or discussCollected: Collected this cycle View 9 plans | bi Name on site: DeepSeek-V4-Flash bi Operator pending verification | 0.14 | 0.28 | 0.028 | 0.175Median price ÷ this price: 7.1× | Full prices and sources |
| 11 | hk.apitoken.aiAsk or discussCollected: Collected this cycle View 9 plans | deepseek Name on site: DeepSeek-V4-Flash deepseek Operator pending verification | 0.14 | 0.28 | 0.028 | 0.175Median price ÷ this price: 7.1× | Full prices and sources |
| 11 | hk.apitoken.aiAsk or discussCollected: Collected this cycle View 9 plans | deepseek deepseek Operator pending verification | 0.14 | 0.28 | 0.028 | 0.175Median price ÷ this price: 7.1× | Full prices and sources |
| 11 | hk.apitoken.aiAsk or discussCollected: Collected this cycle View 9 plans | default Name on site: DeepSeek-V4-Flash Default group [machine translation]Original: 默认分组 Operator pending verification | 0.14 | 0.28 | 0.028 | 0.175Median price ÷ this price: 7.1× | Full prices and sources |
| 11 | hk.apitoken.aiAsk or discussCollected: Collected this cycle View 9 plans | default Default group [machine translation]Original: 默认分组 Operator pending verification | 0.14 | 0.28 | 0.028 | 0.175Median price ÷ this price: 7.1× | Full prices and sources |
| 11 | hk.apitoken.aiAsk or discussCollected: Collected this cycle View 9 plans | zsOperator pending verification | 0.14 | 0.28 | 0.028 | 0.175Median price ÷ this price: 7.1× | Full prices and sources |
| 11 | hk.apitoken.aiAsk or discussCollected: Collected this cycle View 9 plans | zs Name on site: DeepSeek-V4-Flash Operator pending verification | 0.14 | 0.28 | 0.028 | 0.175Median price ÷ this price: 7.1× | Full prices and sources |
| 11 | hk.apitoken.aiAsk or discussCollected: Collected this cycle View 9 plans | Domestic (Chinese) models [machine translation]Group on site: 国内模型 Name on site: DeepSeek-V4-Flash Domestic (Chinese) models [machine translation]Original: 国内模型 Operator pending verification | 0.14 | 0.28 | 0.028 | 0.175Median price ÷ this price: 7.1× | Full prices and sources |
| 11 | new.bohr.de5.netAsk or discussCollected: Collected this cycle View 3 plans | coding Group for Coding [machine translation]Original: 用于Coding的分组 Operator pending verification | 0.14 | 0.28 | 0.0028 | 0.175Median price ÷ this price: 7.1× | Full prices and sources |
| 11 | new.bohr.de5.netAsk or discussCollected: Collected this cycle View 3 plans | default Default group [machine translation]Original: 默认分组 Operator pending verification | 0.14 | 0.28 | 0.0028 | 0.175Median price ÷ this price: 7.1× | Full prices and sources |
| 11 | new.bohr.de5.netAsk or discussCollected: Collected this cycle View 3 plans | shareOperator pending verification | 0.14 | 0.28 | 0.0028 | 0.175Median price ÷ this price: 7.1× | Full prices and sources |
| 24 | api.pezayo.comAsk or discussCollected: Collected this cycle View 4 plans | coding anthropic coding anthropic group, can only call kimi-latest, deepseek-flash models via the anthropic format [machine translation]Original: coding anthropic 分组，只能通过 anthropic 格式调用 kimi-latest，deepseek-flash 模型 Operator pending verification | 0.143 | 0.286 | 0.00256 | 0.17875Median price ÷ this price: 7× | Full prices and sources |
| 24 | api.pezayo.comAsk or discussCollected: Collected this cycle View 4 plans | coding openai coding openai group, can call kimi-latest, deepseek-flash models via the openai chat completion format and the openai response format [machine translation]Original: coding openai 分组，能通过 openai chat completion格式和 openai response 格式调用 kimi-latest，deepseek-flash 模型 Operator pending verification | 0.143 | 0.286 | 0.00256 | 0.17875Median price ÷ this price: 7× | Full prices and sources |
Special groups · 7 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
- test or debug group: 2 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
- realmrouter.cn · Chinese models - test [machine translation]Group on site: 国模-test · deepseek-v4-flash · Input 0.112 / Output 0.224 USD credits / 1M
- test-api.apiqik.online · default · deepseek-v4-flash · Input 0.14286 / Output 0.28572 USD credits / 1M
Related variants · 8 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): 3 rows
- deepseek-v4-flash-thinking (-thinking · thinking edition): 2 rows
- deepseek-v4-flash-free (-free · free variant): 1 rows
- deepseek-v4-flash:free (:free · free variant): 1 rows
- zen/deepseek-v4-flash-free (-free · free variant): 1 rows
- ai.bytonsec.com · zen · zen/deepseek-v4-flash-free · Input 0 / Output 0 USD credits / 1M
- ai.bytonsec.com · zen · deepseek-v4-flash-free · Input 0 / Output 0 USD credits / 1M
- xckjj.com · Chinese models [machine translation]Group on site: 国模 · deepseek-v4-flash:free · Input 0.0112 / Output 0.0224 USD credits / 1M
- api.pezayo.com · default · deepseek-v4-flash-thinking · Input 0.143 / Output 0.286 USD credits / 1M
- api.pezayo.com · official · deepseek-v4-flash-thinking · Input 0.143 / Output 0.286 USD credits / 1M
- yinli.one · deepseek · deepseek-v4-flash-max · Input 1 / Output 2 USD credits / 1M
- apinexus.dpdns.org · default · deepseek-v4-flash-max · Input 60 / Output 180 USD credits / 1M
- apinexus.dpdns.org · vip · deepseek-v4-flash-max · Input 90 / Output 270 USD credits / 1M
How this ranking works
All per-token prices: 97,455 prices from 871 sites (about 765 companies). 89,631 are ranked, from 861 sites (about 755 companies); 7,824 more are listed separately and not ranked. Prices collected up to 2026-10-17.
This model has 1052 recorded prices; 375 can be compared directly (354 ranked, 21 listed separately). Not comparable yet: tiered by rules (see Tiered prices) 291, price not parsed yet 244, billed per request or another unit 59, display unit not confirmed 36, ratio looks unset 26, scope of the official doc price not confirmed 8
264 recent · 8 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. 3 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.
Switch model
Sources not accepted this cycle and reasons
FAQ
Which API is cheapest for DeepSeek · deepseek-v4-flash?
ai.38yun.cn, group "GPT 稳定渠道 (GPT stable channel)", 0 USD credit per million total tokens, observed 2026-10-16. 221 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 2026-10-17. Lowest inference provider: DeepInfra, input 0.09, output 0.18 USD per million tokens. Input 70% lower than official.
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 →