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 2026-10-17). Cheapest inference provider: OpenRouter, input 0.2088, output 0.4176 USD per million tokens. 246 sites have comparable prices; 563 sites list this model.

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 0.261 · median 1.625 · highest 2 · 3 quotes USD / per million tokens

Official price

Provider	Input	Output	Cache read	Cache write	Unit	Observed	Conditions and source
DeepSeek	1.32	3.96	0.044	—	USD / 1M tokens	2026-10-17	Official source
DeepSeek	9.0	27.0	0.30	—	CNY / 1M tokens	2026-10-17	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	0.2088	0.4176	0.0174	—	USD / 1M tokens	2026-10-17	Official source	Input 84% lower · Output 89% lower
DeepInfra	1.30	2.60	0.10	—	USD / 1M tokens	2026-10-17	Official source	Input 2% lower · Output 34% lower
Novita AI	1.6	3.2	0.135	—	USD / 1M tokens	2026-10-17	Official source	Input 21% higher · Output 19% 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	12.00	24.00	1.00	—	CNY / 1M tokens	2026-10-17	Official source	Input 33% higher · Output 11% lower

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

Showing: Special groups。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. Back to the default ranking

Find a provider by name or address

Searching…

Browse all providers

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

Price range: lowest — · median — · highest — (0 quotes, USD credits per million total tokens)

sites have comparable prices246563 sites list this model; approximately 4 operators

Lowest input price—USD credits / 1M

Median of each provider’s lowest price—USD credits / 1M

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
Special groups · not ranked · Recent price
—	test-api.apiqik.onlineAsk or discussCollected: 16 Oct 2026, 07:52 UTC Collected this cycle View 1 plans	default Default group [machine translation]Original: 默认分组 Group notes: test or debug group Operator pending verification	1.71428	3.42856	0.142856666666	2.14285	Full prices and sources
Special groups · not ranked · Flagged · not ranked · Recent price
—	realmrouter.cnAsk or discussCollected: 16 Oct 2026, 07:51 UTC Collected this cycle View 1 plans	Chinese models - test [machine translation]Group on site: 国模-test 站点标注为测试分组 New resources test [machine translation]Original: 新资源 test Note: unrecognized flag GROUP_FLAGGED. This price is not ranked or counted. Group notes: test or debug group Operator pending verification	0.348	0.696	0.00289999999988	0.435	Full prices and sources
—	ai.daoyivip.comAsk or discussCollected: 16 Oct 2026, 07:36 UTC Collected this cycle View 1 plans	Chinese models test [machine translation]Group on site: 国模测试站点标注为测试分组 0.1 rate multiplier, few fallback channels, use the Chinese models group when unstable [machine translation]Original: 0.1 倍率，兜底渠道少，不稳定时用国模分组 Note: unrecognized flag GROUP_FLAGGED. This price is not ranked or counted. Group notes: test or debug group Operator pending verification	0.9	2.7	0.0299999999997	1.35	Full prices and sources
—	shangyou.zhuozaiya.topAsk or discussCollected: 16 Oct 2026, 07:51 UTC Collected this cycle View 1 plans	Do not leak your APIkey [machine translation]Group on site: 请勿泄漏你的APIkey 倍率 99999 Note: far from other providers’ prices. This price is not ranked or counted. Group notes: ratio looks like a placeholder Operator pending verification	299,997	599,994	24999.7499999	374,996.25	Full prices and sources

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 1100 recorded prices; 393 can be compared directly (383 ranked, 10 listed separately). Not comparable yet: tiered by rules (see Tiered prices) 288, price not parsed yet 258, billed per request or another unit 63, display unit not confirmed 38, ratio looks unset 35, scope of the official doc price not confirmed 10

4 recent · 0 stale (older than 10 days, or not updated by this refresh) · 0 unverified timestamps. No recent prices to summarize in this group. 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 →

Switch model

Search modelsModel529 matches; choose and submit to view prices.

Sources not accepted this cycle and reasons

FAQ

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

No valid quotes within 10 days. Older quotes are listed as reference prices.

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

Input 1.32, output 3.96 USD per million tokens, checked 2026-10-17. Lowest inference provider: OpenRouter, input 0.2088, output 0.4176 USD per million tokens. Input 84% lower than official.

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

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