New blogMaking an AI Agent You Can Trust With Money
logo

★ DeepSeek · Mid-tier · Open weights

DeepSeek V4 Pro API Pricing Calculator

$1.32 per 1M input tokens, $3.96 per 1M output. DeepSeek's larger open-weight model. A low-cost alternative to mid-tier closed models.

  • Runs in your browser
  • No signup
  • Updated 7 Nov 2026

Price card · DeepSeek V4 Pro

DeepSeek

Input
$1.32 / 1M
Output
$3.96 / 1M
Cached input
$0.044 / 1M
Batch
No batch tier
Context window
Not published
Tier
Mid-tier

Workload

tok
tok
%

Repeated system prompt or docs

%

Jobs that can wait hours

Models

Anthropic
OpenAI
Google
Mistral
DeepSeek

$ per 1M tokens, input / output

Monthly cost · 30 days

Cheapest
$609
Mistral Large 4
Priciest
$1,148
DeepSeek V4 Pro
Spread
1.9×
priciest vs cheapest
Per 1K users / mo
Mistral Large 4Cheapest
$609$305
Gemini 3.8 FlashIntro price
$788$394
DeepSeek V4 Pro
$1,148$574
Per 1K users assumesrequests per user per day.

Where the money is

If 60% of your traffic is simple enough for Mistral Large 4, routing it there instead of DeepSeek V4 Pro saves about $324/month.

Caching half your input on DeepSeek V4 Pro (a shared system prompt or document) would cut about $383/month.

You're looking at $609–$1,148/month.

Most AI products I audit can cut that 30–60% with routing, caching and shorter prompts.

Get a cost-cutting audit
01

What DeepSeek V4 Pro costs in practice

List prices per million tokens are hard to reason about. Here is what common request types cost on DeepSeek V4 Pro, with no caching or batch discount applied.

DeepSeek V4 Pro cost by request type
Request typeTokens in / outPer callPer 1K callsPer 1M calls
Classification or routing call400 / 10$0.00057$0.5676$568
Support chat reply1,500 / 250$0.00297$2.97$2,970
RAG answer over your docs6,000 / 400$0.00950$9.50$9,504
Long document summary40,000 / 1,000$0.0568$56.76$56,760
02

Pricing notes

DeepSeek's larger open-weight model. A low-cost alternative to mid-tier closed models.

  • Prices shown are peak-hour rates. Off-peak hours are billed at half (per the DeepSeek change log).
  • Caching is automatic on matching prompt prefixes. No batch tier.

Source: api-docs.deepseek.com, updates. Verified 7 Nov 2026.

03

Compare

Or compare all 14 models in the full calculator.

04

How the math works

Every provider bills input tokens (your prompt, system prompt and retrieved documents) and output tokens (the reply) separately, per million. Output is usually 4–5× the input price, so chatty apps are output-heavy and RAG apps are input-heavy.

cost per request = (fresh_in × input_price
+ cached_in × cached_price
+ out × output_price) / 1,000,000
× (1 − batched_share × batch_discount)
monthly = cost per request × requests per day × 30

Two adjustments are applied automatically. Introductory prices (currently on some Gemini models) are used until their end date. Long-prompt surcharges kick in when your average input crosses the provider's threshold: 272K tokens on current OpenAI models, 100K on Claude Haiku 5.5.

Not modelled: cache-write premiums, priority or fast tiers, regional surcharges, image and audio tokens, and reasoning tokens a model spends before answering (they bill as output, so add them to your output estimate if you use extended thinking).

05

DeepSeek V4 Pro questions

How much does DeepSeek V4 Pro cost per 1M tokens?
DeepSeek V4 Pro costs $1.32 per 1M input tokens and $3.96 per 1M output tokens, with cached input at $0.044 per 1M. There is no batch tier.
Is DeepSeek V4 Pro cheaper than Gemini 3.8 Flash?
For a typical request of 2,000 input and 300 output tokens, Gemini 3.8 Flash is about 1.5× cheaper ($0.00383 vs $0.00263 per call for DeepSeek V4 Pro and Gemini 3.8 Flash). Price is only half the decision; test both on your own prompts.
What is prompt caching and should I use it?
When the start of your prompt (system prompt, tool definitions, a long document) repeats across requests, providers can serve it from cache at a fraction of the input price, often 90–99% off. If your requests share a large fixed prefix, caching is usually the single biggest saving available. Put the stable content first and the variable content last.
Why does my real bill differ from this estimate?
Usually because of tokens you are not counting: reasoning or thinking tokens (billed as output), retries, tool-call round trips, and cache-write premiums. Compare the estimate against the usage page in your provider console for a week and adjust the averages.
06

More from the workbench

01 · Plan & scopeMVP Cost EstimatorPick features and who builds it. Get an hour-by-hour estimate, not an agency teaser.03 · Money & fundraisingRunway & Burn CalculatorMonths of cash left, the date it hits zero, and whether you are default alive.04 · Money & fundraisingSaaS Metrics CalculatorsLTV, CAC, churn, NRR, burn multiple and more, each with the formula and benchmarks.

Fine print

Tools: on the house.
Engineer: by the hour.

Knowing your AI bill was free. Cutting it in half isn't, but I'm cheaper than the overspend.

I'm Himanshu, an AI and full-stack engineer. I build MVPs, AI agents and the growth plumbing around them for early-stage startups.

Hire me →My projects