AI Calculator Pro
Value

DeepSeek API Cost Calculator

Estimate DeepSeek V4 Flash and V4 Pro API costs.

Quick answer

With the default inputs, $0.000280 per request — ~$8.40/month at 1,000 requests/day. Enter your own numbers below to recompute instantly; the full step-by-step math is shown under the worked example.

Results update automatically as you type.

Result
$0.000280 per request
~$8.40/month at 1,000 requests/day
Input cost
$0.000140
Output cost
$0.000140
Per request
$0.000280
Per day
$0.2800
Per month
$8.40

Estimate the cost of DeepSeek's API. DeepSeek is among the cheapest frontier options, with V4 Flash and V4 Pro both offering huge context windows and aggressive cache-hit discounts.

How this is calculated

Cost per request = (input tokens ÷ 1,000,000 × input price) + (output tokens ÷ 1,000,000 × output price) for your chosen DeepSeek model. DeepSeek's cache-hit pricing bills repeated input at a steep discount, so we apply your cached-input share; monthly cost scales by requests per day × 30.

Is this a good result? What to do next

DeepSeek is among the cheapest capable APIs — V4 Flash is a fraction of the price of GPT-5 or Claude Opus, and cache hits cost cents per million tokens. The trade-offs to weigh are latency and data-residency, not price.

Typical planning ranges

DeepSeek V4 Flash
fraction of flagship pricing
Cache hits
pennies per 1M tokens
V4 Pro
still cheap for its capability

Ranges are typical planning figures to sanity-check your result, not authoritative benchmarks. Your numbers will vary with use case, volume, and vendor.

How to improve this number

  • Use cache-hit pricing for repeated context.
  • V4 Flash for high volume; V4 Pro for the hardest tasks.
  • Trim output — the cheaper side is still worth optimizing.

Common mistakes

  • Ignoring latency and data-residency trade-offs versus US providers.
  • Assuming every request hits the cache.

When to use a different approach

To see the exact saving versus GPT, use the DeepSeek vs GPT cost calculator. To rank all models, use the model cost comparison.

Worked example (defaults)

With the default inputs above, here is the result:

Result
$0.000280 per request
~$8.40/month at 1,000 requests/day
Input cost
$0.000140
Output cost
$0.000140
Per request
$0.000280
Per day
$0.2800
Per month
$8.40
  • input: 1,000 / 1e6 x $0.14/M = $0.000140
  • output: 500 / 1e6 x $0.28/M = $0.000140
  • monthly = $0.000280 x 1,000 x 30 days

Sources & references

Frequently asked questions

Is DeepSeek really that cheap?+

Yes. V4 Flash is a fraction of the price of GPT-5 or Claude Opus, and cache hits cost cents per million tokens, though latency and data-residency may differ.

Related calculators

API Cost
LLM API Cost Calculator

Estimate the cost of any LLM API call per request and per month.

Comparisons
LLM Model Cost Comparison

Compare the cost of every model for the same workload.

API Cost
Prompt Caching Savings Calculator

See how much prompt caching cuts your input cost.

Answering a real question?

This calculator powers these problem-solving guides: