- Monthly calculator
- V4 Flash + Pro
- Rates checked 25 Oct 2026
DeepSeek PricingTurn token rates into a monthly bill
Estimate a monthly DeepSeek bill for Flash and V4 Pro from tokens, cache hits and peak hours.
Know the cost. Now give an agent the job.
SpringBrand runs tasks on shared credits, with no API key per provider. 300 free credits to start.
Opens SpringBrand in a new tab with your task filled in. 300 free credits to start.
Interactive calculator
DeepSeek pricing calculator for monthly API usage
Enter average tokens per request and expected monthly requests. Cache-hit and peak-traffic percentages let the result reflect how the API is actually billed.
Flash / month
$85.31$0.0085 per requestV4 Pro / month
$336.88$0.0337 per requestFlash savings vs Pro
$251.56for this monthly workloadFlash peak premium
$17.06extra cost caused by peak trafficSame job on SpringBrand cloud: scheduled, 300 free credits.Set it up on SpringBrand
Estimate covers DeepSeek API tokens only. It excludes taxes, your infrastructure and third-party agent or tool charges.
DeepSeek pricing depends on model, input cache hits, output tokens and time of day. Flash (deepseek-flash, now V4.1 Flash) starts at $0.003 per million cached input tokens off-peak; V4 Pro starts at $0.022. Use the calculator below for a realistic monthly estimate.
Independent calculator · DeepSeek's published rates checked 25 October 2026 · Prices can change.
DeepSeek Harness itself is free and MIT licensed; what you pay for is the model API it calls. DeepSeek's pricing page now lists deepseek-flash (DeepSeek-V4.1-Flash-1017) at lower rates than the original V4 Flash, and the legacy deepseek-v4-flash name is billed at the new Flash price.
Estimate covers DeepSeek API tokens only. It excludes taxes, your infrastructure and third-party agent or tool charges.
DeepSeek API pricing at a glance
- Flash cached input
- $0.003 / 1M off-peak
- Flash uncached input
- $0.15 / 1M off-peak
- Flash output
- $0.60 / 1M off-peak
- Pro cached input
- $0.022 / 1M off-peak
- Pro uncached input
- $0.66 / 1M off-peak
- Pro output
- $1.98 / 1M off-peak
- Peak premium
- 2× every token category, weekdays only
- Context window
- 1M tokens, up to 384K output
Current API table
DeepSeek pricing per 1 million tokens
These are the Flash (deepseek-flash, V4.1 Flash) and V4 Pro rates on DeepSeek's pricing page on 25 October 2026. Peak pricing is double the off-peak rate in every token category.
| Model and period | Cached input | Uncached input | Output |
|---|---|---|---|
| Flash · Off-peak | $0.003 | $0.15 | $0.60 |
| Flash · Peak | $0.006 | $0.30 | $1.20 |
| V4 Pro · Off-peak | $0.022 | $0.66 | $1.98 |
| V4 Pro · Peak | $0.044 | $1.32 | $3.96 |
Flash
2,500 concurrent requestsConcurrency limit DeepSeek lists for deepseek-flash.
V4 Pro
500 concurrent requestsConcurrency limit DeepSeek lists for deepseek-v4-pro.
Context
1M tokensBoth models list a one-million-token context window and up to 384K output tokens.
Time-of-day pricing
When DeepSeek peak pricing applies
Peak windows are 01:00–04:00 UTC and 06:00–10:00 UTC, Monday to Friday, excluding Chinese public holidays. Weekends, holidays and all other hours use the off-peak table.
Converted automatically
Your local peak windows are loading…Actionable savings
How to lower DeepSeek pricing without cutting output quality
The rate table exposes two high-leverage levers: schedule flexible work off-peak and improve cache reuse on repeated context.
Move batch work outside peak windows
Every token category costs half as much off-peak, and weekends are off-peak all day. Queue evaluations, indexing and long reports for the lower-rate hours.
Keep repeated prefixes stable
System prompts, tool descriptions and long shared context are more likely to benefit from caching when their prefix does not change.
Route routine work to Flash
Off-peak, V4 Pro costs about 4.4× Flash for uncached input and 3.3× for output. Use Pro only when your own task tests show a quality gain worth that.
Measure cache hit rate
A long prompt is not automatically cheap. Read the provider usage breakdown, then enter the observed hit rate in the calculator.
FAQ
DeepSeek pricing questions
Short answers about DeepSeek API pricing for DSH and other agents.
- API tokens only
- Peak is 2× on weekdays
- Verify current rates
DeepSeek Harness is free and MIT licensed. Your cost is the DeepSeek API (or other model) usage it generates: requests multiplied by cached input, uncached input and output charges, weighted by peak-hour traffic. Use the calculator above.
Sources
Pricing source and limits
Independent calculator · DeepSeek's published rates checked 25 October 2026 · Prices can change.
- DeepSeek API pricing documentation
Flash and V4 Pro cached input, uncached input, output, peak windows, context, concurrency, and Search & Fetch billing.
Next step
Know the bill? Now schedule the job.
SpringBrand runs agent tasks in the cloud on a daily or weekly schedule, with search, social data and generation tools built in, and 300 free credits to start.
Rates change, so check the source before you budget: DeepSeek's pricing page
SpringBrand is independent, not affiliated with DeepSeek. DeepSeek Harness (dsh) is an open-source project by DeepSeek AI; community desktop builds belong to their own maintainers.