API pricing · 2 models

DeepSeek API pricing

What every DeepSeek model costs per 1M tokens through the API, at off-peak rates, with the extra charges and discounts that change the bill.

Prices from DeepSeek's pricing page as of

Prices per 1M tokens

US dollars, standard processing, off-peak hours. The last column is what one request with 1,000 input and 500 output tokens costs; try your own volumes in the cost calculator.

ModelInputCached inputOutput1K in + 500 out
DeepSeek V4
DeepSeek V4 Prodeepseek-v4-pro$0.66$0.022$1.98$0.0017
DeepSeek V4.1 Flashdeepseek-flash$0.15$0.003$0.60$0.00045

Peak-hour prices

What the same models cost during peak hours, per 1M tokens.

ModelInputCached inputOutput1K in + 500 out
DeepSeek V4 Pro$1.32$0.044$3.96$0.0033
DeepSeek V4.1 Flash$0.30$0.006$1.20$0.0009

Context windows

DeepSeek V4 Pro1M tokens
DeepSeek V4.1 Flash1M tokens

Recent DeepSeek changes

Model launches, price changes and retirements, newest first.

  1. New model

    DeepSeek V4.1 Flash released with new peak and off-peak prices

    deepseek-flash costs $0.15 / $0.60 off-peak and $0.30 / $1.20 at peak. V4 Flash and V4-Flash-Vision-Exp are retired; their names route to V4.1 Flash. A planned move of V4 Pro traffic to Flash from September 14 was later withdrawn, and V4 Pro stays at unchanged prices.

  2. New model

    DeepSeek V4 Pro generally available

    The model version behind deepseek-v4-pro is DeepSeek-V4-Pro-0813.

Billing rules that change the price

  • DeepSeek bills by time of day. The main table shows off-peak prices. Peak hours are 01:00-04:00 and 06:00-10:00 UTC, Monday to Friday, when prices double.
  • Both models have a 1M-token context window and up to 384K output tokens.
  • The older model names deepseek-v4-flash and deepseek-v4-flash-vision-exp still work; requests go to V4.1 Flash at the Flash price.
  • deepseek-chat and deepseek-reasoner no longer appear on DeepSeek's pricing page.
  • Third-party routers resell DeepSeek at their own flat rates, for example OpenRouter at $0.58 / $1.74 for V4 Pro.

Questions

How much does the DeepSeek API cost?

DeepSeek lists 2 models (off-peak prices). Input costs from $0.15 (DeepSeek V4.1 Flash) to $0.66 (DeepSeek V4 Pro) per 1M tokens, and output from $0.60 (DeepSeek V4.1 Flash) to $1.98 (DeepSeek V4 Pro). A request with 1,000 input and 500 output tokens costs between $0.00045 and $0.0017.

What is the cheapest DeepSeek API model?

By the cost of a 1,000-input, 500-output request, DeepSeek V4.1 Flash is the cheapest: $0.15 input and $0.60 output per 1M tokens, about $0.00045 per request off-peak.

Does the DeepSeek API have a batch discount?

The DeepSeek pricing page we checked lists no batch rate.

Where these numbers come from

Prices are copied from the vendor's own pages; the vendor page is the authority on what you are billed. Per-request costs are our arithmetic.

FieldSourceObserved
API prices per 1M tokens, peak hoursvendorDeepSeek API pricingSep 16, 2026
Cost of 1,000 input + 500 output tokensderivedCalculated from the prices aboveSep 16, 2026