DeepSeek API Pricing 2026: Is It Really the Cheapest?

Kim Han — Tue, 27 Oct 2026 13:58:22 +0000

DeepSeek's reputation rests on one claim: flagship-class models at a fraction of the price. Its official price list is also the most unusual of any major provider — the price depends on when you call and whether your prompt hits the cache.

This post lists the official rates for both models DeepSeek currently sells, works out monthly costs at peak and off-peak, and then answers the "cheapest" question with numbers.

Disclosure: this article contains no affiliate links. On CostMyTokens, some pages use affiliate links (e.g. Novita AI); they never change sort order — every table is sorted by price only. Disclosure.

Prices verified 2026-10-26 against DeepSeek's official pricing. Prices change — check the official page before you commit budget. Full version with internal links: costmytokens.com/deepseek-api-pricing.

DeepSeek API prices (official, per 1M tokens)

DeepSeek's current price list has exactly two models. Both are priced twice: peak and off-peak. Off-peak is always half of peak.

Model	Input (cache miss) / 1M	Input (cache hit) / 1M	Output / 1M	Context
deepseek-flash (DeepSeek-V4.1-Flash-1017)	$0.15 off-peak / $0.30 peak	$0.003 off-peak / $0.006 peak	$0.60 off-peak / $1.20 peak	1,000,000
deepseek-v4-pro (DeepSeek-V4-Pro)	$0.66 off-peak / $1.32 peak	$0.022 off-peak / $0.044 peak	$1.98 off-peak / $3.96 peak	1,000,000

Peak hours are 01:00–04:00 and 06:00–10:00 UTC, Monday to Friday, excluding Chinese public holidays. Everything else is off-peak — including all of Saturday and Sunday.

In Beijing time, those peak windows are 09:00–12:00 and 14:00–18:00 on weekdays: DeepSeek charges double during its home market's working hours and half everywhere else.

What a month costs

Workload: 80% input / 20% output. Sorted by cost.

Model	10M tokens, off-peak	10M tokens, peak	100M tokens, off-peak	Off-peak, 50% of input cached
deepseek-flash	$2.40	$4.80	$24.00	$1.81 (10M)
deepseek-v4-pro	$9.24	$18.48	$92.40	$6.69 (10M)

There is no separate Batch API discount on this price list. Off-peak is the batch discount: work that can wait for the evening or the weekend costs exactly half.

So, is it the cheapest?

Two different questions hide inside that one.

Cheapest tokens, outright: no. Lower-tier closed models (e.g. GPT-6 Luna / Claude Haiku-class list prices around $0.10 input / $0.50 output as of the verification date) can undercut deepseek-flash's $0.15 / $0.60 off-peak. If the workload is simple and price is the only variable, DeepSeek is not the absolute floor.

Cheapest flagship-class reasoning: yes — and it is not close. deepseek-v4-pro at $0.66 / $1.98 off-peak undercuts every closed flagship on list price in the comparison we ran on CostMyTokens. Even DeepSeek's peak rate is about half the standard rate of the cheapest closed flagship tier we checked that day.

Cache behaviour is where DeepSeek claws back the token gap. A cache hit on Flash costs $0.003 per 1M — 2% of its cache-miss price. With half of your input served from cache, Flash off-peak can land near the cheap closed tiers' standard-rate bill.

Billing rules that change the bill

The clock is a pricing tier. The same request can cost 2× inside peak UTC windows on weekdays.
Cache hits are nearly free, and automatic. A stable system prompt or document prefix is unusually valuable here.
Old model names may silently map to Flash. Budgets keyed to retired Flash-era names need a re-check on the official list.
R1 is no longer on the current official two-model list we verified — do not budget from stale R1 screenshots.
Agent tool calls: DeepSeek documents per-request charges for Search/Fetch-style tool usage (see official docs for the start date and rate). Treat that as an extra line for coding-agent workloads.

Which model to price first

deepseek-flash — default starting point (vision, higher concurrency, cheapest cache hits).
deepseek-v4-pro — reasoning flagship; text-only, lower concurrency, higher output price. Measure before you assume it is "always worth it".

Try it on your own traffic

Paste your token mix into the free calculator: CostMyTokens — official vs gateway rows, sorted by price only.

Deeper pages on the same topic:

Source: DeepSeek API pricing, verified 2026-10-26.