Compare the price per token.

Subscription effective prices, point packs and API providers. All in USD per 1M tokens.

YOUR WORKLOAD

Estimate your API cost

Enter a 30-day workload in millions of tokens. Enter cached input separately from uncached input.

Choose your workload and calculate an estimate. JavaScript is required for the calculator; the examples below remain available.

Assumptions and limits

All figures use the DSSUB design catalog, not a live quote. The selected model is used for the entire workload, including peak windows. The cost excludes taxes, credit-pack bonuses, extra tools and overage.

Plan points = input (including cached input) + output, multiplied by the model rate. We compare both peak windows and a normalized 30-day allowance (weekly allowance × 30 ÷ 7). This is a planning check, not a guarantee: actual fixed window boundaries, activation dates, concurrent usage and rate limits still matter.

Yearly prices show a monthly equivalent and the full upfront charge. One-time access lasts one calendar month; this estimate uses 30 days for comparison. No model or purchase is available in this preview.

Is a subscription always cheaper? No. Low or irregular usage, unused allowances and cached input can favor pay-as-you-go. Compare costs using the prices, dates and workload assumptions below.

DeepSeek V4.1 Flash

USD per 1 million tokens

DeepSeek V4.1 Flash prices in USD per 1 million tokens. Subscription prices assume full allowance use.
Plan / providerPrice / 1M tokens
BaseSubscription · effective price$0.0116
MaxSubscription · effective price$0.0093
Pro MaxSubscription · effective price$0.0067
UltraSubscription · effective price$0.0091
Point packsPay as you go
Input
$0.135Cache read $0.01
Output
$0.55
DeepSeek APIOfficial · Off-peak / peak
Input
$0.15 / $0.30Cache read $0.003 / $0.006
Output
$0.60 / $1.20
OpenRouterMorph · FP8 · Flash 1017
Input
$0.022Cache read $0.004
Output
$0.40
Together AIFlash 1017 · Serverless · Precision not disclosed
Input
$0.30Cache read $0.006
Output
$1.20
Fireworks AIFlash 1017 · Serverless · Precision not disclosed
Input
$0.30Cache read $0.006
Output
$1.20
SiliconFlowFP8 · Global · Flash
Input
$0.15Cache read $0.003
Output
$0.60
DeepInfraFP8 · Flash 1017 · Standard · 51% off
Input
$0.098Cache read $0.003
Output
$0.294
Novita AIFP8 · Flash 1017 · Serverless
Input
$0.30Cache read $0.006
Output
$1.20

Cache read · Reusing input

A cache hit reuses computation for an identical input prefix, such as a repeated system prompt or conversation history. Only the matched input tokens receive the cache-read rate; the rest use the regular input rate. It does not reuse a finished answer or change the model’s numerical precision. Cache availability and rules vary by provider. About Cache →

FP8 · Numerical precision

FP8 means 8-bit floating point, used for parts of model inference to reduce memory use and potentially speed up computation. Compared with FP16/BF16, it can introduce numerical differences; the effect on answer quality depends on the model and implementation. A cache hit can happen on an FP8 route too: caching concerns input reuse, while FP8 concerns how numbers are represented. About FP8 →

Subscription effective price = monthly fee ÷ (7-day token allowance × 30 ÷ 7), shown per 1M tokens. Yearly plans use the annual fee ÷ 12. This assumes full weekly allowance use within the plan’s usage windows; using fewer tokens increases your effective price. Input, cached input and output share one allowance at 1×, so the same effective price applies to each.

Compare a workload, not just a token price.

Example 30-day workloads with 90% input and 10% output. Each volume is shown without caching and with 80% of input cached.

Monthly plan: recurring monthly charge. All amounts below are USD for the whole example workload.

Same token volume and mix · Official Flash rates checked November 5, 2026
Total tokens / 30 daysOfficial API
Off-peak / peak
Point-pack usageBaseMaxPro MaxUltra
10M0% of input cached$1.95 / $3.90$1.77$19.90$39.90$79.90$329.00
10M80% of input cached$0.89 / $1.78$0.87$19.90$39.90$79.90$329.00
100M0% of input cached$19.50 / $39.00$17.65$19.90$39.90$79.90$329.00
100M80% of input cached$8.92 / $17.83$8.65$19.90$39.90$79.90$329.00
1,000M0% of input cached$195.00 / $390.00$176.50$19.90$39.90$79.90$329.00
1,000M80% of input cached$89.16 / $178.32$86.50$19.90$39.90$79.90$329.00

Calculations normalize the weekly allowance to 30 days using weekly allowance × 30 ÷ 7. Requests use the actual 5-hour and 7-day windows. Point-pack figures show usage charges before pack bonuses. Taxes, payment fees, extra tools and overage are excluded.

API cost = uncached input × input rate + cached input × cache rate + output × output rate, using millions of tokens. Official columns assume all tokens use off-peak or all use peak rates; a mixed schedule falls between those amounts. Verify current official rates and hours ↗

What if I use only part of my allowance?

Effective subscription price in USD per 1M tokens at 10%, 30% or 100% of the normalized allowance. The subscription fee stays the same when you use less.

Plan10% used30% used100% used
Base$0.1161$0.0387$0.0116
Max$0.0931$0.031$0.0093
Pro Max$0.0666$0.0222$0.0067
Ultra$0.0914$0.0305$0.0091

Unused quota is not a cash balance. Actual effective price is undefined when no tokens are used.

For low or irregular usage, pay-as-you-go may cost less. A subscription is worth considering when the recurring fee, model features and usage windows fit your work. Read the plan selection guide →

Point-pack rates are deducted from API credit before pack bonuses. Official rates checked November 5, 2026. DeepSeek prices & peak hours ↗ · Plan limits ↗

Provider prices and precision labels checked November 5, 2026; click a provider for its source. OpenRouter uses the named Morph route; other providers show direct API prices. DeepInfra included a 51% promotion at the last check; its cached price is rounded as published. SiliconFlow uses its global Flash listing. Token prices exclude credit-purchase fees and taxes. FP8 labels show the provider’s published precision.