Skip to content
CostPerPrompt

DeepSeek V4 Flash 0423 API Pricing

DeepSeek · context window 1M · prices updated 2026-09-15

Input per 1M tokens
$0.0886
Output per 1M tokens
$0.1772
Cached input per 1M
$0.0177
80% cheaper than fresh input

Where DeepSeek V4 Flash 0423 sits on price

At $0.1772 per million output tokens, DeepSeek V4 Flash 0423 is a budget tier model — 11.7× cheaper than the median output price of $2.08, which puts it in the cheapest 10% of everything we track. It sits 2th cheapest of the 18 DeepSeek models we track. Output is only 2.0× the input price, an unusually flat spread: long prompts hurt about as much as long answers, so prompt size is where the savings are.

Output tokens per $1
5,643,341
One full context fill
$0.0929
Cheaper than
95% of tracked models

Cached input is 80% cheaper. On an input-heavy workload you need roughly a 31% cache-hit rate to take 25% off the input line — reachable for chatbots and agents that resend the same system prompt and history.

What real workloads cost on DeepSeek V4 Flash 0423

These three workloads are the ones teams actually run on a budget-priced model — a $0.1772/1M model is not bought for the same job as one ten times the price.

Workload Per request Per month
High-volume classification — 200K requests/day (400 in / 20 out) Short output, huge volume: the input price dominates the bill. $0 $234
Small app — 1K requests/day (500 in / 150 out) The baseline most side projects actually run at. $0.0001 $2.13
Long-context analysis — 200 runs/day (250K in / 4K out) Only possible on large-context models; input cost is nearly the whole bill. $0.0229 $137

Model your exact traffic in the API cost calculator — it preloads DeepSeek V4 Flash 0423 with caching and batch options.

DeepSeek V4 Flash 0423 price history

DeepSeek last raised DeepSeek V4 Flash 0423's output price on Sep 14, 2026 (+81% per output token), from $0.049/$0.098 to $0.0886/$0.1772 per 1M in/out. That is one of 22 repricings in the 44 days we have tracked it — worth knowing before you hard-code today's rate into a budget.

Date Input /1M Output /1M Output change
Aug 2, 2026 (tracking began) $0.14 $0.28
Aug 6, 2026 $0.0882 $0.1764 -37%
Aug 8, 2026 $0.14 $0.28 +59%
Aug 15, 2026 $0.0741 $0.1481 -47%
Aug 16, 2026 $0.0615 $0.1229 -17%
Aug 17, 2026 $0.0826 $0.1652 +34%
Aug 21, 2026 $0.0797 $0.1593 -4%
Aug 22, 2026 $0.0713 $0.1425 -11%
Aug 23, 2026 $0.0517 $0.1033 -28%
Aug 24, 2026 $0.0574 $0.1148 +11%
Aug 25, 2026 $0.0886 $0.1772 +54%
Aug 28, 2026 $0.0868 $0.1736 -2%
Aug 29, 2026 $0.0848 $0.1697 -2%
Aug 30, 2026 $0.0798 $0.1596 -6%
Aug 31, 2026 $0.0886 $0.1772 +11%
Sep 1, 2026 $0.0809 $0.1618 -9%
Sep 2, 2026 $0.0886 $0.1772 +10%
Sep 5, 2026 $0.0853 $0.1705 -4%
Sep 6, 2026 $0.0811 $0.1621 -5%
Sep 7, 2026 $0.0886 $0.1772 +9%
Sep 12, 2026 $0.0668 $0.1336 -25%
Sep 13, 2026 $0.049 $0.098 -27%
Sep 14, 2026 $0.0886 $0.1772 +81%

Change-points from our daily price snapshots (tracking since Aug 2, 2026; intraday moves between snapshots are not captured).

DeepSeek V4 Flash 0423 vs Llama Guard 4 12B

The closest-priced alternative from another vendor is Llama Guard 4 12B (Meta) — priced within a rounding error on output, with $0.0914 more per million input tokens. When two models land this close on price, the decision is quality on your own workload, not the price sheet: run 50 real requests through both and compare.

See Llama Guard 4 12B pricing →

Cheaper alternatives

More DeepSeek models

Frequently asked questions

How much does the DeepSeek V4 Flash 0423 API cost?

DeepSeek V4 Flash 0423 costs $0.0886 per million input tokens and $0.1772 per million output tokens, with cached input at $0.0177 per million (80% cheaper). That works out to roughly 5,643,341 output tokens per dollar.

What does the high-volume classification workload cost on DeepSeek V4 Flash 0423?

High-volume classification — 200K requests/day (400 in / 20 out) costs about $0 per request and $234 per month on DeepSeek V4 Flash 0423. Short output, huge volume: the input price dominates the bill.

What does it cost to fill DeepSeek V4 Flash 0423's 1M context window?

Sending 1M of input in a single request costs $0.0929 at $0.0886 per million tokens — before any output. With prompt caching that same fill drops to about $0.0186 on repeat requests. This is why large context windows are cheap to advertise and expensive to actually use.

Is DeepSeek V4 Flash 0423 worth the price?

DeepSeek V4 Flash 0423 is in the cheapest end of the market — cheaper than 95% of the models we track. At this price the question is not cost but capability: it is a good fit for classification, extraction, routing and bulk summarisation, and a poor fit for multi-step reasoning where a wrong answer costs more than the tokens saved.