Switch model

API PRICES

DeepSeek · DeepSeek-V4-Pro-0813

Provider prices, cheapest first

Browse all models

Price comparison

Official (cash)
Input 1.32 / output 3.96 USD/million tokensDeepSeek ·
Lowest inference provider (cash)
Input 1.32 / output 3.96 USD/million tokensNovita AI · same as official ·
Lowest relay (credit)
0.29 USD credit/million total tokensainzy.net "chinese-model-3" ·

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-Pro-0813 official price: input 1.32, output 3.96 USD per million tokens (DeepSeek, observed 2026-10-17). Cheapest inference provider: Novita AI, input 1.32, output 3.96 USD per million tokens. Cheapest relay: ainzy.net, group "chinese-model-3" 0.29 USD_CREDIT per million total tokens (credit price, not cash, observed 2026-10-16). 79 sites have comparable prices; 226 sites list this model.Relay blended price uses 75% input and 25% output.

Price ranges per million tokens

Official cash prices · Lowest 1.98 · median 1.98 · highest 1.98 · 1 quotes USD / per million tokens

Official cash prices · Lowest 13.5 · median 13.5 · highest 13.5 · 1 quotes CNY / per million tokens

Inference provider cash prices · Lowest 1.98 · median 1.98 · highest 1.98 · 2 quotes USD / per million tokens

Relay USD credit prices · Lowest 0.29 · median 3.375 · highest 23.625 · 35 quotes USD / per million tokens, site credit

Relay CNY credit prices · Lowest 0.495 · median 2.7 · highest 23.4 · 17 quotes CNY / per million tokens, site credit

Official price

ProviderInputOutputCache readCache writeUnitObservedConditions and source
DeepSeek1.323.960.044—USD / 1M tokens
Official source
DeepSeek9270.3—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

ProviderInputOutputCache readCache writeUnitObservedConditions and sourcevs official
Novita AI1.323.960.044—USD / 1M tokens
Official source
Input 0% · Output 0%
Together AI1.323.960.13—USD / 1M tokens
Official source
Input 0% · Output 0%

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

Searching…

Browse all providers

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

Price range: lowest 0.29 · median 3.375 · highest 23.625 (35 quotes, USD credits per million total tokens)

sites have comparable prices79226 sites list this model; approximately 42 operators
Lowest input price0.19333USD credits / 1M
Median of each provider’s lowest price2.25USD credits / 1M

Relays

Prices below are in site credit, not cash.

#ProviderPlan / conditionsInput ↑USD credits / 1MOutput USD credits / 1MCache readUSD credits / 1MBlendedUSD credits / 1MDetails
Flagged · not ranked · Recent price
—api.ai-gaochao.cnAsk or discussCollected:
Collected this cycle
View 19 plans
temp
Name on site: deepseek-v4-pro-0813
temp

Note: number precision issue. This price is not ranked or counted.

Operator pending verification
0.4350.870.0036250.54375Median price ÷ this price: 6.2×Full prices and sources
—api.ai-gaochao.cnAsk or discussCollected:
Collected this cycle
View 19 plans
tieta
Name on site: deepseek-v4-pro-0813
tieta

Note: number precision issue. This price is not ranked or counted.

Operator pending verification
0.4350.870.0036250.54375Median price ÷ this price: 6.2×Full prices and sources
—api.ai-gaochao.cnAsk or discussCollected:
Collected this cycle
View 19 plans
vip
Name on site: deepseek-v4-pro-0813
vip

Note: number precision issue. This price is not ranked or counted.

Operator pending verification
0.4350.870.0036250.54375Median price ÷ this price: 6.2×Full prices and sources
—api.ai-gaochao.cnAsk or discussCollected:
Collected this cycle
View 19 plans
Enterprise users [machine translation]Group on site: 企业用户
Name on site: deepseek-v4-pro-0813
Enterprise users [machine translation]Original: 企业用户

Note: number precision issue. This price is not ranked or counted.

Operator pending verification
0.4350.870.0036250.54375Median price ÷ this price: 6.2×Full prices and sources
—api.ai-gaochao.cnAsk or discussCollected:
Collected this cycle
View 19 plans
svip
Name on site: deepseek-v4-pro-0813
svip

Note: number precision issue. This price is not ranked or counted.

Operator pending verification
0.871.740.007251.0875Median price ÷ this price: 3.1×Full prices and sources
—ccoo.aiAsk or discussCollected:
Collected this cycle
View 1 plans
Deepseek official [machine translation]Group on site: Deepseek 官方
Name on site: deepseek-v4-pro-0813
DeepSeek V4 Pro, V4 Flash and other models, strong in complex reasoning, Coding, Agent and cost efficiency [machine translation]Original: DeepSeek V4 Pro、V4 Flash 等模型,在复杂推理、Coding、Agent 与成本效率方面表现突出

Note: number precision issue. This price is not ranked or counted.

Operator pending verification
1.012530.033751.5094Median price ÷ this price: 2.2×Full prices and sources
—aipaiai.cnAsk or discussCollected:
Collected this cycle
View 1 plans
Chinese model API calls [machine translation]Group on site: 国产模型接口调用
Name on site: deepseek-v4-pro-0813
Billed in RMB (CNY). For each provider's model rate multiplier, see the [model plaza (pricing page) > Chinese models] section [machine translation]Original: 计费方式为人民币(¥)不同服务商的模型倍率需要前往【模型广场>国产模型】专区查看

Note: number precision issue. This price is not ranked or counted.

Operator pending verification
1.0343.0580.0441.54Median price ÷ this price: 2.2×Full prices and sources
—api.gravitex.aiAsk or discussCollected:
Collected this cycle
View 1 plans
default
Name on site: deepseek-v4-pro-0813
Default group [machine translation]Original: 默认分组

Note: number precision issue. This price is not ranked or counted.

Operator pending verification
1.36184.08680.13682.0431Median price ÷ this price: 1.7×Full prices and sources
—api.aimodelserver.comAsk or discussCollected:
Collected this cycle
View 1 plans
chinese
Name on site: deepseek-v4-pro-0813
Supports Chinese models such as glm, kimi, deepseek, qwen; rate multiplier *3 [machine translation]Original: 支持glm,kimi,deepseek,qwen等国产模型,倍率*3

Note: number precision issue. This price is not ranked or counted.

Operator pending verification
1.9860.0662.985Median price ÷ this price: 1.1×Full prices and sources
—new.yihubang.topAsk or discussCollected:
Collected this cycle
View 2 plans
GLM Anthropic endpoint [machine translation]Group on site: GLM Anthropic 端点
Name on site: deepseek-v4-pro-0813
GLM, KIMI, Xiaomi, Qwen, minimax [machine translation]Original: GLM、KIMI、小米、千问、minimax

Note: number precision issue. This price is not ranked or counted.

Operator pending verification
7.0520.850.310.5Median price ÷ this price: 0.3×Full prices and sources
—new.yihubang.topAsk or discussCollected:
Collected this cycle
View 2 plans
Chinese models Openai endpoint [machine translation]Group on site: 国模 Openai 端点
Name on site: deepseek-v4-pro-0813
GLM, KIMI, Xiaomi, Qwen, minimax [machine translation]Original: GLM、KIMI、小米、千问、minimax

Note: number precision issue. This price is not ranked or counted.

Operator pending verification
7.0520.850.310.5Median price ÷ this price: 0.3×Full prices and sources
—xinsuanai.comAsk or discussCollected:
Collected this cycle
View 4 plans
vip
Name on site: deepseek-v4-pro-0813
vip group [machine translation]Original: vip分组

Note: far from other providers’ prices. This price is not ranked or counted.

Operator pending verification
6060—60Median price ÷ this price: 0.1×Full prices and sources
—xinsuanai.comAsk or discussCollected:
Collected this cycle
View 4 plans
svip
Name on site: deepseek-v4-pro-0813
svip group [machine translation]Original: svip分组

Note: far from other providers’ prices. This price is not ranked or counted.

Operator pending verification
8080—80Median price ÷ this price: 0×Full prices and sources
—xinsuanai.comAsk or discussCollected:
Collected this cycle
View 4 plans
Official relay Claude [machine translation]Group on site: 官转克劳德
Name on site: deepseek-v4-pro-0813
Official relay Claude [machine translation]Original: 官转克劳德

Note: far from other providers’ prices. This price is not ranked or counted.

Operator pending verification
200200—200Median price ÷ this price: 0×Full prices and sources
Special groups · 1 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: 1 rows
  • zero-ratio group: 1 rows
  • wqdsjhaoai.site · Free 1 yi (100 million) token daily, shared site-wide [machine translation]Group on site: 每日免费1亿token,全站共享 · deepseek-v4-pro-0813 · Input 0 / Output 0 USD credits / 1M
View all 1 rows →
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 428 recorded prices; 125 can be compared directly (124 ranked, 1 listed separately). Not comparable yet: tiered by rules (see Tiered prices) 128, price not parsed yet 116, ratio looks unset 31, display unit not confirmed 12, billed per request or another unit 12

86 recent · 2 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

FAQ

Which API is cheapest for DeepSeek · DeepSeek-V4-Pro-0813?

ainzy.net, group "chinese-model-3", 0.29 USD credit per million total tokens, observed 2026-10-16. 79 sites have comparable prices.

What is the official price for DeepSeek · DeepSeek-V4-Pro-0813?

Input 1.32, output 3.96 USD per million tokens, checked 2026-10-17. Lowest inference provider: Novita AI, input 1.32, output 3.96 USD per million tokens. Input 0% higher than official.

How do I use DeepSeek · DeepSeek-V4-Pro-0813 in Claude Code or Codex?

Install Grandet Skill, then say "Connect the cheapest DeepSeek · DeepSeek-V4-Pro-0813 API to Claude Code for me". Install Skill →