TechCompare LogoTechCompare

DeepSeek V4 Flash API Pricing & Cost Calculator

DeepSeek V4 Flash is the cheapest 1M-context frontier API you can buy. Cache-hit input at $0.014/M makes stable-prompt loops nearly free, and scheduling off-peak halves the entire bill.

DeepSeek V4 Flash is the small fast member of the V4 pair, priced for high-volume traffic with a peak/off-peak rate split and one of the deepest prompt-cache discounts of any frontier vendor.

By TechCompare · Updated

Input tokens
100,000
per request
Output tokens
5,000
per request
Volume
1,000 / monthly
Standard API

Calculator

Cost Comparison

Based on 100,000 input tokens (50% cached), 5,000 output tokens, and 1,000 requests.

Open full calculator to adjust tokens, caching, or add other models

How this is calculated

DeepSeek V4 Flash is priced at $0.44 per million input tokens and $1.32 per million output tokens at peak hours (01:00-04:00 and 06:00-10:00 UTC), dropping to $0.22/$0.66 off-peak. Cached input at peak is $0.014 per million, a 96.8% discount. The context window is 1M tokens with up to 384K output.

Verdict

Peak rates land a 100K + 5K call at $0.05, which no US lab comes close to - GPT-5.6 Sol runs $0.65 for the same call. The real trick is the two levers stacked: cache-hit input at $0.014/M drops the input side by 30x on repeated context, and off-peak scheduling halves both rows for any workload that can wait. Against DeepSeek V4 Pro 0813 ($1.32/$3.96) Flash is 3x cheaper per token and is the right default unless the job genuinely needs Pro's deeper reasoning.

More API Standalones scenarios

GPT-5.5 Pricing
Single-model gpt-5.5 cost estimate
View details ➜
GPT-5.4 Pricing
Single-model gpt-5.4 cost estimate
View details ➜
Claude Opus 4.8 Pricing
Single-model claude-opus-4.8 cost estimate
View details ➜

Related guides

Token cost calculator
How per-token counts turn into API costs.
View guide ➜
Prompt optimization
Cutting tokens is the cheapest way to cut cost.
View guide ➜

Frequently asked questions

What do DeepSeek's peak and off-peak hours mean for billing?
Peak is 01:00-04:00 and 06:00-10:00 UTC. V4 Flash at peak is $0.44/M input and $1.32/M output. Off-peak halves both to $0.22/M input and $0.66/M output. Batch-style workloads that can queue overnight effectively cost half the published rate.
How deep is the DeepSeek prompt cache discount?
96.8% on V4 Flash. Cache-hit input is $0.014 per million versus $0.44 standard. For agent loops that reuse the same system prompt and tool definitions, the input side of the bill nearly disappears. V4 Pro has a similar 96.7% discount ($1.32 to $0.044).
DeepSeek V4 Flash or V4 Pro?
Flash for volume: it's 3x cheaper per token ($0.44/$1.32 vs $1.32/$3.96 peak) with the same 1M context. Pro for hard reasoning, multi-step planning, and anything where the evals clearly separate. Mix them by routing - Flash as default, Pro as escalation.

Related tools

LLM VRAM Calculator

Calculate the VRAM needed to run or fine-tune any LLM at any quantization.

Use tool ➜

Power Cost Estimator

Estimate annual electricity costs for your PC, Server, or TV.

Use tool ➜

Data Transfer Calculator

Estimate transfer times for files over USB, WiFi, Ethernet, and more.

Use tool ➜

JSON Formatter

Validate, format, and minify JSON data with syntax highlighting.

Use tool ➜