API PRICES
DeepSeek · deepseek-v4-pro
Provider prices, cheapest first
DeepSeek · deepseek-v4-pro official price: input 1.32, output 3.96 USD per million tokens (DeepSeek, observed 2026-10-16). Cheapest inference provider: OpenRouter, input 0.95526, output 1.91052 USD per million tokens. Cheapest relay: llm.kagu.one, group "Hodgepodge [machine translation] (on site: 大杂烩)" 0.271875 USD_CREDIT per million total tokens (credit price, not cash, observed 2026-10-10). 234 sites have comparable prices; 544 sites list this model.Relay blended price uses 75% input and 25% output.
Official price
| Provider | Input | Output | Cache read | Cache write | Unit | Observed | Conditions and source |
|---|---|---|---|---|---|---|---|
| DeepSeek | 1.32 | 3.96 | 0.044 | — | USD / 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 |
|---|---|---|---|---|---|---|---|---|
| OpenRouter · Aggregator | 0.95526 | 1.91052 | 0.079605 | — | USD / 1M tokens | Official source | Input 28% lower · Output 52% lower | |
| DeepInfra | 1.30 | 2.60 | 0.10 | — | USD / 1M tokens | Official source | Input 2% lower · Output 34% lower | |
| SiliconFlow | 12.00 | 24.00 | 1.00 | — | CNY / 1M tokens | Official source |
Unit: USD credits per 1M tokens. These are site-credit prices; actual cost depends on each site’s top-up rate.
Searching…
Browse all providersRelays
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 | godoftoken.eu.ccAsk or discussCollected: View 3 plans | gpt GPT models (0.1x) [machine translation]Original: GPT模型(0.1倍) | 0.2 | 0.8 | 0.02 | 0.35 | Full prices and sources |
| 02 | llm.kagu.oneAsk or discussCollected: View 2 plans | Hodgepodge [machine translation]Group on site: 大杂烩 | 0.2175 | 0.435 | 0.00050768673535093369125 | 0.271875 | Full prices and sources |
| 03 | ai.lt4net.orgAsk or discussCollected: View 1 plans | opencode | 0.24 | 0.76000000000008 | 0.00799999999992 | 0.37000000000002 | Full prices and sources |
| 04 | apiqd.comAsk or discussCollected: View 1 plans | deepseek All latest models supported [machine translation]Original: 最新模型均支持 | 0.315 | 0.945 | 0.010499999999895 | 0.4725 | Full prices and sources |
| 05 | oojj.topAsk or discussCollected: View 3 plans | cnmodel-w 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 | 0.36 | 0.72 | 0.00299999999988 | 0.45 | Full prices and sources |
| 06 | ainzy.netAsk or discussCollected: View 2 plans | chinese-model-3 Chinese models high cache group · 30% of official price | Chinese Models (DeepSeek / GLM / Kimi) · 30% of list [machine translation]Original: 国模高缓存组 · 官方价 3 折 | Chinese Models (DeepSeek / GLM / Kimi) · 30% of list | 0.40000002 | 1.160000058 | 0.0120000006 | 0.5900000295 | Full prices and sources |
| 07 | api.pezayo.comAsk or discussCollected: 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 | 0.428 | 0.856999999999944 | 0.00356999999986 | 0.535249999999986 | Full prices and sources |
| 07 | api.pezayo.comAsk or discussCollected: 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 | 0.428 | 0.856999999999944 | 0.00356999999986 | 0.535249999999986 | Full prices and sources |
| 07 | api.pezayo.comAsk or discussCollected: View 4 plans | default Default group, use all models via the openai chat completion format [machine translation]Original: 默认分组，通过 openai chat completion 格式使用全部模型 | 0.428 | 0.856999999999944 | 0.00356999999986 | 0.535249999999986 | Full prices and sources |
| 07 | api.pezayo.comAsk or discussCollected: View 4 plans | official Official group, gpt, claude gemini official models [machine translation]Original: 官方 分组，gpt, claude gemini 官方模型 | 0.428 | 0.856999999999944 | 0.00356999999986 | 0.535249999999986 | Full prices and sources |
| 11 | api.tokengo.comAsk or discussCollected: View 1 plans | default Name on site: deepseek/deepseek-v4-pro | 0.435 | 0.87 | — | 0.54375 | Full prices and sources |
| 12 | api.changsf.topAsk or discussCollected: View 2 plans | deepseek deepseek preview version [machine translation]Original: deepseek预览版 | 0.45 | 1.35 | 0.01499999999985 | 0.675 | Full prices and sources |
| 13 | 1yapi.comAsk or discussCollected: View 1 plans | Chinese models [machine translation]Group on site: 国产模型 Chinese models · GLM/DeepSeek/Kimi/MiniMax/Qwen [machine translation]Original: 国产模型 · GLM/DeepSeek/Kimi/MiniMax/Qwen | 0.5 | 0.5 | — | 0.5 | Full prices and sources |
| 14 | api.llmgw.xyzAsk or discussCollected: View 2 plans | gm-01 | 0.54 | 1.62 | 0.01799999999982 | 0.81 | Full prices and sources |
| 15 | aiapi.worldAsk or discussCollected: View 1 plans | cmodels cmodels | 0.578 | 1.156 | — | 0.7225 | Full prices and sources |
| 16 | airouter.mxyhi.comAsk or discussCollected: View 4 plans | Special price [machine translation]Group on site: 特价 Special price model group [machine translation]Original: 特价模型分组 | 0.6 | 1.2 | 0.0049999999998 | 0.75 | Full prices and sources |
| 16 | godoftoken.eu.ccAsk or discussCollected: View 3 plans | domestic Name on site: DeepSeek-V4-Pro Chinese models (0.3x) [machine translation]Original: 国产模型(0.3倍) | 0.6 | 2.4 | — | 1.05 | Full prices and sources |
| 18 | ainzy.netAsk or discussCollected: View 2 plans | aliyun-chinese-model Alibaba Cloud Chinese models group · Bailian direct connection · 45% of official price (4.5/10) | Aliyun Bailian Chinese Models (DeepSeek / Kimi) · 45% of list [machine translation]Original: 阿里云国模组 · 百炼直连 · 官方价 4.5 折 | Aliyun Bailian Chinese Models (DeepSeek / Kimi) · 45% of list | 0.60000003 | 1.740000087 | 0.0180000009 | 0.88500004425 | Full prices and sources |
| 19 | sheapi.topAsk or discussCollected: View 1 plans | deepseek deepseek series models, in-house special-supply channel [machine translation]Original: deepseek系列模型，自研特供渠道 | 0.63 | 1.89 | 0.02099999999979 | 0.945 | Full prices and sources |
| 20 | newapi.prorisehub.comAsk or discussCollected: View 3 plans | Overseas Chinese coding models [machine translation]Group on site: 海外国产编程模 [Stability ⭐⭐⭐⭐⭐] Overseas open-source model channel, full-strength relay, full-strength coding models [machine translation]Original: 【稳定性⭐⭐⭐⭐⭐】海外开源模型渠道满血中转，满血版本编程模型 | 0.66 | 1.98 | 0.021999999978 | 0.99 | Full prices and sources |
| 21 | sudobug.topAsk or discussCollected: View 1 plans | Chinese models [machine translation]Group on site: 国模 ds\glm\kimi | 0.72 | 2.16 | 0.02399999999976 | 1.08 | Full prices and sources |
| 22 | realmrouter.cnAsk or discussCollected: View 1 plans | default Default [machine translation]Original: 默认 | 0.87 | 1.74 | 0.00724999999971 | 1.0875 | Full prices and sources |
| 23 | newapi.fangyi.asiaAsk or discussCollected: View 1 plans | Chinese models [machine translation]Group on site: 国产 Supports claude code cli only [machine translation]Original: 仅支持claude code cli | 0.9 | 1.8 | 0.0749999999997 | 1.125 | Full prices and sources |
| 23 | pro.auroai.icuAsk or discussCollected: View 1 plans | Chinese [machine translation]Group on site: 国 Chinese [machine translation]Original: 国 | 0.9 | 2.7 | 0.0299999999997 | 1.35 | Full prices and sources |
| 23 | vbcode.ioAsk or discussCollected: View 3 plans | deepseek-cheap | 0.9 | 2.7 | — | 1.35 | Full prices and sources |
Special groups · 15 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.
- test or debug group: 13 rows
- marked display-only or do-not-select: 2 rows
- internal or channel key: 2 rows
- tokhubs.com · route-deepseek · deepseek-v4-pro · Input 0.198 / Output 0.594 USD credits / 1M
- realmrouter.cn · Chinese models - test [machine translation]Group on site: 国模-test · deepseek-v4-pro · Input 0.348 / Output 0.696 USD credits / 1M
- ai.daoyivip.com · Chinese models test [machine translation]Group on site: 国模测试 · deepseek-v4-pro · Input 0.9 / Output 2.7 USD credits / 1M
- hk.apitoken.ai · sandbox-China · deepseek-v4-pro · Input 1.74 / Output 3.48 USD credits / 1M
- hk.apitoken.ai · sandbox · deepseek-v4-pro · Input 1.74 / Output 3.48 USD credits / 1M
- hk.apitoken.ai · sandbox · DeepSeek-V4-Pro · Input 1.74 / Output 3.48 USD credits / 1M
- hk.apitoken.ai · sandbox-China · DeepSeek-V4-Pro · Input 1.74 / Output 3.48 USD credits / 1M
- api.uniprep.world · Personal use [machine translation]Group on site: 个人自用 · deepseek-v4-pro · Input 2.07 / Output 4.14 USD credits / 1M
- api.ai-gaochao.cn · test · deepseek-v4-pro · Input 3 / Output 6 USD credits / 1M
- rivora.cc · test · deepseek-v4-pro · Input 10.8 / Output 54 USD credits / 1M
Related variants · 3 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-pro-max (-max · max edition): 3 rows
- wqdsjhaoai.site · coderapi · deepseek-v4-pro-max · Input 1.3735 / Output 1.3735 USD credits / 1M
- apinexus.dpdns.org · default · deepseek-v4-pro-max · Input 120 / Output 450 USD credits / 1M
- apinexus.dpdns.org · vip · deepseek-v4-pro-max · Input 180 / Output 675 USD credits / 1M
How this ranking works
All per-token prices: 96,427 prices from 839 sites (about 733 companies). 88,950 are ranked, from 826 sites (about 720 companies); 7,477 more are listed separately and not ranked. Prices collected up to 2026-10-10.
This model has 1065 recorded prices; 399 can be compared directly (377 ranked, 22 listed separately). Not comparable yet: tiered by rules (see Tiered prices) 277, price not parsed yet 144, new price under review; showing the previous one 101, billed per request or another unit 61, display unit not confirmed 39, ratio looks unset 34, scope of the official doc price not confirmed 10
291 recent · 3 stale (older than 7 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.