A rate per million tokens is not a budget. The calculator takes your request volume, prompt size and cache hit rate and gives you a monthly figure.

DeepSeek Flash (V4.1) API pricing (October 2026)

Prices verified 30 Oct 2026

Off-peak rate; bills 2x during Beijing peak hours (09:00-12:00 and 14:00-18:00 UTC+8, Monday to Friday, except Chinese public holidays). API name deepseek-flash; the old deepseek-v4-flash name now routes to V4.1 Flash.

Input

$0.150

per 1M tokens

Output

$0.600

per 1M tokens

Cached input

$0.00300

per 1M tokens

Batch discount

None

no batch API

What it costs at real volumes

A chat-shaped workload: 800 input tokens and 300 output tokens per request, no caching, no batch.

Volume	Per request	Per month	Per year
10K requests/day	$0.00030	$91	$1,096	Adjust →
100K requests/day	$0.00030	$913	$10,958	Adjust →
1M requests/day	$0.00030	$9,132	$109,584	Adjust →

Specifications

Provider: DeepSeek
Context window: 1.0M tokens
Max output: 384K tokens
Tier: Workhorse
Status: GA
Blended $/1M (3:1): $0.262
Cache break-even, caching each turn: 0%, caching always saves
Prices verified: 30 Oct 2026

Source: DeepSeek pricing. Finitizer is not affiliated with DeepSeek.

Similar models

Other DeepSeek models

DeepSeek V4 Pro+$0.728

Closest prices elsewhere

DeepSeek Flash (V4.1) vs GPT-4o mini

Frequently asked questions

How much does DeepSeek Flash (V4.1) cost per 1M tokens?

DeepSeek Flash (V4.1) costs $0.150 per million input tokens and $0.600 per million output tokens at DeepSeek list prices. Output is 4.0x the input rate, so the input:output ratio of a workload drives the real cost more than the headline price.

Does DeepSeek Flash (V4.1) support prompt caching?

Yes. Cached input is billed at $0.00300 per million tokens, 50x cheaper than uncached input. There is no cache-write premium, so caching is never a net loss.

What is the batch discount for DeepSeek Flash (V4.1)?

DeepSeek Flash (V4.1) does not offer a batch pricing tier.

What is DeepSeek Flash (V4.1)'s context window?

1.0M tokens of context with up to 384K output tokens per request. A larger context window raises the ceiling on what you can send, not the price per token, but filling it on every request is one of the most common causes of an unexpected bill.

Running DeepSeek Flash (V4.1) in production?

Finitizer Tokenomics reads what this model actually costs you from your own bills and exports, shows which workload, team or API key is spending it, flags a spike or a new spend source the day your data shows it, and forecasts where the month will land.

See Finitizer Tokenomics