Skip to content
LLM Pricing Calc
Pricing last verified

DeepSeek V4.1 Flash pricing calculator

DeepSeek's low-cost fast model, with near-free cache hits.

Input
$0.30 / 1M
Cached input
$0.006 / 1M
Output
$1.20 / 1M
Context window
1M
Batch API
No
Reasoning
Yes

Official pricing ↗

NotePeak price shown. DeepSeek offers 50% off during off-peak hours.

Workload

Quick presets

1,000 tokens ≈ 750 English words.

Pro / Agent mode

Caching, batch, multi-turn loops, reasoning tokens

Cost comparison

Cheapest / month

$14.15

GPT-4o mini

Most expensive / month

$69.97

Grok Build 0.1

Tokens / request

1.5K in

400 out (cheapest model)

Estimated cost per model
Remove
GPT-4o miniCheapestOpenAI · $0.15 / $0.60$0.00047$0.465$14.15$169.73
DeepSeek V4.1 FlashDeepSeek · $0.30 / $1.20$0.00093$0.93$28.29$339.45
Gemini 3.5 Flash-LiteGoogle · $0.30 / $2.50$0.00145$1.45$44.11$529.25
Grok Build 0.1xAI · $1.00 / $2.00$0.0023$2.30$69.97$839.50

Monthly = daily × 30.42. Prices are list prices for the standard context tier. Long-context surcharges, regional pricing and taxes are not included.Official pricing: DeepSeek ↗ · Google ↗ · OpenAI ↗ · xAI ↗

What DeepSeek V4.1 Flash costs for common workloads

Monthly estimates using the presets above, at list price.

WorkloadPer request / sessionMonthlyYearly
Small Chatbot1K chats/day, short prompts$0.00054$16.43$197.10
RAG App5K queries/day, 4K-token retrieved context$0.00121$183.98$2,208
Coding Agent200 sessions/day × 25 turns$0.0976$593.94$7,126
Enterprise Scale250K requests/day, batched$0.00115$8,724$104,682

Official pricing ↗ (DeepSeek) · API model ID deepseek-flash

DeepSeek V4.1 Flash pricing FAQ

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

DeepSeek V4.1 Flash costs $0.30 per 1M input tokens and $1.20 per 1M output tokens. Cached input is $0.006 per 1M. Prices were last verified on Nov 21, 2026.

How much does one DeepSeek V4.1 Flash request cost?

A typical request with 1,000 input tokens and 500 output tokens costs about $0.0009. At 1,000 such requests per day that is $27.38 per month.

Does DeepSeek V4.1 Flash support prompt caching?

Yes. Cached input tokens cost $0.006 per 1M, 98% less than regular input. Turn on Pro mode above to model your cache hit rate.

Is there a Batch API discount for DeepSeek V4.1 Flash?

No 50% batch discount is listed for DeepSeek V4.1 Flash. DeepSeek offers off-peak discounts instead.

What is the context window of DeepSeek V4.1 Flash?

DeepSeek V4.1 Flash supports up to 1M tokens of context and up to 375K output tokens per response. Peak price shown. DeepSeek offers 50% off during off-peak hours.

Is DeepSeek V4.1 Flash cheaper than Gemini 3.5 Flash-Lite?

For a 1,000-in / 500-out request, DeepSeek V4.1 Flash costs $0.0009 and Gemini 3.5 Flash-Lite costs $0.00155, so DeepSeek V4.1 Flash is 42% cheaper. Quality, speed and caching behaviour differ, so compare on your own workload above.

More AI cost tools