DEEPSEEK API PRICING

DeepSeek token cost calculator.

Compare DeepSeek API token rates with effective dates and time-sensitive pricing rules kept visible.

Calculate a workload Review rate cards →

Models: 2
Rate cards: 6
Input range: $0.14–$1.32
Output range: $0.28–$3.96
Cache-priced cards: 6
Verified: 2026-08-16

DEEPSEEK WORKLOAD

Model the calls you actually make.

Enter monthly workload, tokens, and quality pass rates. The calculator resolves eligible price bands, then shows cost per accepted answer and the candidate break-even pass rate.

Provider and model tierRequests / monthInput tokens / requestOutput tokens / requestInput reduction25%Output reduction20%Warm cache-read share30%Baseline quality pass rate90%Candidate quality pass rate85%

Estimated monthly API spend · DeepSeek

DeepSeek V4 FlashBefore · Off-peak · scheduled UTC windows: $0.22 input · $0.007 cache read · $0.66 output / 1MAfter · Off-peak · scheduled UTC windows: $0.22 input · $0.007 cache read · $0.66 output / 1MGlobal · price bands selected automatically from input size

Before$9.90

After$6.15

Potential saving: $3.75 (37.9%)

QUALITY-ADJUSTED COST

Before / accepted answer$0.001190% pass assumption

After / accepted answer$0.000785% pass assumption

Candidate break-even: 55.9% pass rate. Your scenario assumes 85%.

Warm cache-read scenario, not general ROI. It excludes cache writes/storage, tools, regional uplifts, retries, and quality failures. A dash means no published cache-read rate.

DeepSeek API pricing ↗

NEXT STEPValidate the 34.2% accepted-answer advantage.

The estimate is not a saving until the same workload still passes its quality bar. Compare a supported recipe in the lab, or use the evidence library to design a provider-specific test.

Run a controlled test Attribute by workflow Audit an existing bill Browse evidence methods See one-time access

DeepSeek can publish scheduled and time-window pricing changes. TokenGauge keeps effective boundaries on separate rate cards and never applies a future rate before it begins.

DATED RATE CARDS

DeepSeek prices with their scope intact.

Rates are USD per one million tokens. Future and transitional cards remain labeled with their effective dates instead of silently replacing today’s tier.

Official provider API rate cards, USD per one million tokens
Provider / model	Price scope	Input USD / 1M	Cache read USD / 1M	Output USD / 1M	Context	Source
DeepSeekDeepSeek V4 Flash`deepseek-v4-flash`	Off-peak · scheduled UTC windowsGlobalFrom 16 Aug 2026	$0.22	$0.007	$0.66	1M	Official ↗
DeepSeekDeepSeek V4 Flash`deepseek-v4-flash`	Peak · 01:00–04:00 and 06:00–10:00 UTCGlobalFrom 16 Aug 2026	$0.44	$0.014	$1.32	1M	Official ↗
DeepSeekDeepSeek V4 Flash`deepseek-v4-flash`	Standard · through 2026-08-16 16:00 UTCGlobalThrough 16 Aug 2026	$0.14	$0.0028	$0.28	1M	Official ↗
DeepSeekDeepSeek V4 Pro`deepseek-v4-pro`	Off-peak · scheduled UTC windowsGlobalFrom 16 Aug 2026	$0.66	$0.022	$1.98	1M	Official ↗
DeepSeekDeepSeek V4 Pro`deepseek-v4-pro`	Peak · 01:00–04:00 and 06:00–10:00 UTCGlobalFrom 16 Aug 2026	$1.32	$0.044	$3.96	1M	Official ↗
DeepSeekDeepSeek V4 Pro`deepseek-v4-pro`	Standard · through 2026-08-16 16:00 UTCGlobalThrough 16 Aug 2026	$0.435	$0.003625	$0.87	1M	Official ↗

Rates in USD per 1M tokens

DeepSeek

DeepSeek V4 Flash

deepseek-v4-flash

Off-peak · scheduled UTC windowsGlobal

Input: $0.22
Cache read: $0.007
Output: $0.66
Context: 1M

Effective from 16 Aug 2026Open official source

DeepSeek

DeepSeek V4 Flash

deepseek-v4-flash

Peak · 01:00–04:00 and 06:00–10:00 UTCGlobal

Input: $0.44
Cache read: $0.014
Output: $1.32
Context: 1M

Effective from 16 Aug 2026Open official source

DeepSeek

DeepSeek V4 Flash

deepseek-v4-flash

Standard · through 2026-08-16 16:00 UTCGlobal

Input: $0.14
Cache read: $0.0028
Output: $0.28
Context: 1M

Effective through 16 Aug 2026Open official source

DeepSeek

DeepSeek V4 Pro

deepseek-v4-pro

Off-peak · scheduled UTC windowsGlobal

Input: $0.66
Cache read: $0.022
Output: $1.98
Context: 1M

Effective from 16 Aug 2026Open official source

DeepSeek

DeepSeek V4 Pro

deepseek-v4-pro

Peak · 01:00–04:00 and 06:00–10:00 UTCGlobal

Input: $1.32
Cache read: $0.044
Output: $3.96
Context: 1M

Effective from 16 Aug 2026Open official source

DeepSeek

DeepSeek V4 Pro

deepseek-v4-pro

Standard · through 2026-08-16 16:00 UTCGlobal

Input: $0.435
Cache read: $0.003625
Output: $0.87
Context: 1M

Effective through 16 Aug 2026Open official source

USD per 1M tokens. Snapshot verified 2026-08-16. Cache writes, cache storage, tools, regions, and provider-specific thresholds may be billed separately.

A missing cache rate is shown as “—”, never treated as free. Consumer chat-plan quotas are not API prices.

BILLING CAVEAT

What to verify before shipping

DeepSeek can publish scheduled and time-window pricing changes. TokenGauge keeps effective boundaries on separate rate cards and never applies a future rate before it begins.

Official source 1 ↗

MEASUREMENT RULE

Price accepted answers, not token deltas

Count retries, fallbacks, tool calls, latency failures, and answers rejected by the quality rubric. A lower estimated token bill is useful only when the workload still succeeds.

Open the controlled A/B lab

QUESTIONS

Before you trust the estimate.

How current are the DeepSeek API prices?

This page uses TokenGauge’s 2026-08-16 official-source snapshot. Follow the linked provider pages before making a production commitment because prices can change.

Does this calculator include every DeepSeek charge?

No. It models input, output, and a warm cache-read share. Cache writes or storage, tools, retries, regional uplifts, taxes, batch modes, and quality failures can change the final invoice.

Are consumer chat subscriptions included?

No. ChatGPT, Claude, Gemini, Grok, Kimi, and other consumer-plan quotas are separate from provider API token billing.