model comparison

vs

DeepSeek V4 Flash vs DeepSeek V4 Pro

two DeepSeek models, compared on listed price, real workload cost, context and capabilities.

the short answer

  • DeepSeek V4 Flash lists lower input and output prices.
  • DeepSeek V4 Flash reads cached input for less ($0.014/M against DeepSeek V4 Pro's $0.044/M), which decides the bill for agents that resend long context.
  • DeepSeek V4 Flash retired on 1 November 2026; its numbers are kept for reference.

side-by-side specs

specDeepSeek V4 FlashDeepSeek V4 Pro
providerDeepSeekDeepSeek
input price$0.44/M$1.32/M
output price$1.32/M$3.96/M
cached input$0.014/M$0.044/M
blended price (3:1)$0.66/M$1.98/M
context window1M tokens1M tokens
max output—384k tokens
inputtexttext
structured outputyesyes
weightsopen (MIT)open (MIT)
releasedApril 24, 2026April 24, 2026
availabilityretired 1 November 2026live

same work, both models

workloadDeepSeek V4 FlashDeepSeek V4 Pro
one chat reply3,000 tokens in, 500 outDeepSeek V4 Pro costs 3.0× as much as DeepSeek V4 Flash$0.002$0.0059
summarise a 100-page report50,000 tokens in, 1,500 out, one request$0.02$0.07
1,000 classification calls500 tokens in, 20 out, per call$0.25$0.74
coding-agent session2M tokens in across ~60 turns, 60,000 out, no cache$0.96$2.88
same session, cached85% of input read from the prompt cache, the rest written to it$0.24$0.71

at listed rates. token counts are typical sizes, not measurements.

DeepSeek V4 Flash pricing notes

  • the listed rate is DeepSeek's peak-hour price from its 2026-08-16 revision. it applies at all hours here, although DeepSeek's own off-peak rate was half.
  • DeepSeek retired the model on its own api on 2026-09-10, and that route now serves V4.1 Flash. this page is for the V4 Flash open weights served by third-party hosts.

DeepSeek V4 Pro pricing notes

  • since 2026-08-16 16:00 UTC DeepSeek's own api bills peak and off-peak; the listed price is the peak rate, and off-peak is half ($0.66 / $1.98).
  • on DeepSeek's api, peak is 01:00-04:00 and 06:00-10:00 UTC Monday-Friday, excluding Chinese public holidays.

when to pick which

DeepSeek V4 Flash

the smaller DeepSeek V4 model: an open-weights mixture-of-experts with 284B total and 13B active parameters that takes text only. on its own api, DeepSeek has replaced it with V4.1 Flash, which costs less and adds image input.

pick it if

  • you want MIT-licensed open weights from DeepSeek's cheaper V4 tier
  • you need a 1M-token context with cached input at $0.014 per 1M
  • you want a choice of non-think, Think High or Think Max reasoning

skip it if

  • you need image input; V4.1 Flash accepts images
  • the cheaper V4.1 Flash sibling covers your workload

DeepSeek V4 Pro

DeepSeek's larger V4 model: 1.6T total parameters (49B active), text-only, with a 1M-token context and selectable thinking effort. previewed in April 2026 and generally available from 2026-08-13, it sits above V4.1 Flash, which costs less and also reads images.

pick it if

  • want DeepSeek's largest V4 model with MIT-licensed open weights
  • resend long prompts: cache hits bill $0.044 per 1M versus $1.32
  • need low / high / max thinking effort for agent workflows

skip it if

  • you need image input; V4.1 Flash accepts images
  • V4.1 Flash at $0.30 / $1.20 already covers your workload

faq

which is cheaper, DeepSeek V4 Flash or DeepSeek V4 Pro?

DeepSeek V4 Flash lists lower input and output prices. on a coding-agent session (2M tokens in, 60,000 out) DeepSeek V4 Flash costs $0.96 and DeepSeek V4 Pro $2.88.

try either model

switch between models inside the same octomind session.

prices from the catalog of 2026-11-18