Skip to content
这个页面有中文版。
切换到中文
API Pricing

11,195 prices on 4,854 listings · last collected 9 h ago · 442 flagged changes in 30 days

Every price, as each platform publishes it

A collector reads every public price on ten platforms, daily by default, and keeps the page it read. Nothing is typed in by hand. Search a model to see who charges least, per unit, right now.

Showing 1–11 of 11

“Cheapest” is the lowest exact price in this unit for your search. Rows can differ in resolution, length or quality — read the label, or add it to the search (e.g. “1080”).

Per million input tokens4

PlatformModel · what it coversUSDPlatform’s own wordingSince
OpenRouterThird-partyDeepSeek: DeepSeek V4 Flash 0423via Baidu · fp8$0.05/M inCheapestprompt: 0.00000004998 / token (endpoint baidu/fp8)
RunwareNot disclosedDeepSeek-V4-Flash-0731$0.076/M in$7.6e-8 / inputToken
AibermNot disclosedDeepSeek V4 Flash$0.144/M inmodel_ratio 0.3126 × $2/M · group default ×0.23Claims official price $0.14/M in
APIMartNot discloseddeepseek-v4-flash$0.171/M inInput $0.1714 / Output $0.5143 · Per 1M tokens

Per million output tokens4

PlatformModel · what it coversUSDPlatform’s own wordingSince
OpenRouterThird-partyDeepSeek: DeepSeek V4 Flash 0423via Baidu · fp8$0.1/M outCheapestcompletion: 0.00000009996 / token (endpoint baidu/fp8)
RunwareNot disclosedDeepSeek-V4-Flash-0731$0.153/M out$1.53e-7 / outputToken
AibermNot disclosedDeepSeek V4 Flash$0.216/M outmodel_ratio 0.3126 × $2/M · group default ×0.23 · completion_ratio 1.5Claims official price $0.28/M out
APIMartNot discloseddeepseek-v4-flash$0.514/M outInput $0.1714 / Output $0.5143 · Per 1M tokens

Per million cached input tokens (read)3

PlatformModel · what it coversUSDPlatform’s own wordingSince
OpenRouterThird-partyDeepSeek: DeepSeek V4 Flash 0423via Baidu · fp8$0.01/M cache readCheapestinput_cache_read: 0.000000009996 / token (endpoint baidu/fp8)
RunwareNot disclosedDeepSeek-V4-Flash-0731Per 1M$0.014/M cache read$1.4e-8 / cachedInputToken
AibermNot disclosedDeepSeek V4 Flash$0.029/M cache readmodel_ratio 0.3126 × $2/M · group default ×0.23 · cache_ratio 0.2