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
| Plan / provider | Price / 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 |
|
| DeepSeek APIOfficial · Off-peak / peak |
|
| OpenRouterMorph · FP8 · Flash 1017 |
|
| Together AIFlash 1017 · Serverless · Precision not disclosed |
|
| Fireworks AIFlash 1017 · Serverless · Precision not disclosed |
|
| SiliconFlowFP8 · Global · Flash |
|
| DeepInfraFP8 · Flash 1017 · Standard · 51% off |
|
| Novita AIFP8 · Flash 1017 · Serverless |
|
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.
| Total tokens / 30 days | Official API Off-peak / peak | Point-pack usage | Base | Max | Pro Max | Ultra |
|---|---|---|---|---|---|---|
| 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.
| Plan | 10% used | 30% used | 100% 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.