DeepSeek API Cost Calculator

Use this free DeepSeek API cost calculator to estimate spend per request, day, month, or year for deepseek-v4-flash and deepseek-v4-pro. Enter input tokens, output tokens, request volume, and an observed or expected cache-hit rate. For the complete rate table and model-selection guidance, see our DeepSeek API pricing guide.

The most reliable estimate comes from a real API response’s usage object. It separates cache-hit input, cache-miss input, and completion tokens, so the calculator can apply the correct rate to each billing item.

How DeepSeek API Cost Is Calculated

DeepSeek bills input and output tokens separately. Input tokens are split between the lower cache-hit rate and the regular cache-miss rate. The calculator uses this equation:

request cost =
  (cache-hit input tokens / 1,000,000 x cache-hit price)
+ (cache-miss input tokens / 1,000,000 x cache-miss price)
+ (output tokens / 1,000,000 x output price)

• Cache-hit input: prompt tokens DeepSeek reports in prompt_cache_hit_tokens.
• Cache-miss input: prompt tokens DeepSeek reports in prompt_cache_miss_tokens.
• Output: generated completion tokens, including billable reasoning-token usage where applicable.
• Volume: per-request cost multiplied by the number of requests. This page uses 30 days for a monthly projection and 365 days for a yearly projection.

Worked DeepSeek API Cost Examples

These static examples remain readable without JavaScript and show exactly how the displayed totals are obtained. Values use the regular prices verified on August 3, 2026.

Example 1: Flash Chatbot With a 50% Cache-Hit Rate

Assume 800 input tokens, 400 output tokens, a 50% cache-hit rate, and 2,000 requests per day:

• Cache-hit input: 400 / 1,000,000 x $0.0028 = $0.00000112
• Cache-miss input: 400 / 1,000,000 x $0.14 = $0.000056
• Output: 400 / 1,000,000 x $0.28 = $0.000112
• Total: $0.00016912 per request, $0.33824 per day, $10.1472 per 30-day month, or $123.4576 per 365-day year.

Example 2: The Same Workload on V4 Pro

Using the same 800 input tokens, 400 output tokens, 50% cache-hit rate, and 2,000 requests per day, V4 Pro costs $0.00052345 per request. That projects to $31.407 per 30-day month or $382.1185 per 365-day year. The comparison isolates the price difference; it does not measure whether Pro’s output quality reduces retries or downstream work.

Example 3: How Caching Changes a Flash RAG Budget

For 10,000 input tokens, 1,000 output tokens, and 100,000 requests per month, a 0% hit-rate estimate is $168.00 per month. A theoretical 100% input cache-hit estimate is $30.80 per month, a difference of $137.20. This is a planning boundary, not a promised saving: DeepSeek documents caching as best-effort, and only persisted matching prefixes count as hits. Use observed usage fields instead of assuming 100%. Read our DeepSeek context caching guide for prefix design and measurement.

Original Deterministic Calculator Test Matrix

We created the following frozen arithmetic vectors for the August 3, 2026 calculator review. Each expected result was recomputed independently from the published price table. This validates calculator math; it is not a claim about a live API invoice, model quality, latency, or cache availability.

Original Live DeepSeek API Cost Test

On August 3, 2026, we ran an English-only synthetic cache test against the live DeepSeek API. The reusable prompt contained 1,580 input tokens, and each response contained 8 output tokens. We sent the same prompt twice to V4 Flash, then sent it once to V4 Pro. The table uses the exact token counters returned by the API and calculates cost from the regular official rates shown on this page.

The repeated Flash request demonstrates why real cache counters matter: 1,536 of 1,580 prompt tokens were reported as cache hits, while 44 remained cache misses. The calculator reproduced all three costs before display rounding. This test confirms the formula and usage-field handling for this workload; it does not guarantee the same cache-hit rate for another prompt, account, region, or time.

Use the counter above for a quick pre-request token estimate. DeepSeek’s documentation gives a general approximation of one English character being about 0.3 token, but tokenization varies by model and content. For billing reconciliation, use the token fields returned by the API rather than this text estimate.

Calculator Limits and Assumptions

• Currency and units: US dollars per 1 million tokens, before taxes, credits, grants, account-level adjustments, or provider rounding.
• Time periods: monthly projections use 30 days; yearly projections use 365 days. A direct monthly request count takes priority when the calculator provides that input.
• Token source: typed token values and a pasted API usage object are more useful than word or character estimates. Log prompt_cache_hit_tokens, prompt_cache_miss_tokens, and completion_tokens.
• Cache behavior: the cache-hit percentage is an estimate unless it comes from observed responses. Caching applies to matching input prefixes, works on a best-effort basis, and does not discount output tokens.
• Model limits: the official table lists a 1M context length and a maximum output of 384K for both V4 models. A cost estimate does not guarantee that a payload, endpoint, feature, or requested output is valid.
• Unmodeled usage: system prompts, tool schemas, conversation history, retries, failed application attempts that still generated tokens, and reasoning tokens can increase real usage.
• Price changes: estimates use the regular rates verified on August 3, 2026. The announced future peak multiplier is not applied automatically until DeepSeek publishes its effective date.

Methodology and Verification

We reviewed DeepSeek’s official Models & Pricing, Token & Token Usage, and Context Caching documentation on August 3, 2026. We transcribed the current regular prices, checked the model context and output limits, independently recomputed every frozen test vector, and separated documented facts from estimates. We did not use an account balance, invoice, promotion, or tax calculation.

For production monitoring, record the provider-returned usage fields for every request, group them by model and pricing period, then reconcile derived estimates with your DeepSeek billing records. Our DeepSeek token usage fields guide explains the counters; the DeepSeek API guide covers setup and request structure; and the DeepSeek API updates tracker records model and pricing changes.

DeepSeek API Cost Calculator FAQ

How much does the DeepSeek API cost?

As verified on August 3, 2026, DeepSeek lists V4 Flash at $0.0028 per 1M cache-hit input tokens, $0.14 per 1M cache-miss input tokens, and $0.28 per 1M output tokens. V4 Pro is $0.003625, $0.435, and $0.87 for the same billing categories. Prices can change, so verify the official table before committing spend.

How do I calculate DeepSeek API cost?

Multiply cache-hit input, cache-miss input, and output tokens by their respective per-token prices, then add the three amounts. Multiply that request total by expected volume for a daily, monthly, or yearly projection.

Is DeepSeek V4 Flash cheaper than V4 Pro?

Yes, Flash has lower published rates for cache hits, cache misses, and output. Pro may still be economical for a workload if its stronger result reduces retries or downstream review, so test cost per successful task rather than token price alone.

Does DeepSeek context caching reduce API cost?

It can reduce input cost when a request fully matches a persisted prompt-prefix unit. DeepSeek enables caching by default but describes it as best-effort, so use the returned hit and miss token fields instead of assuming a perfect hit rate.

Does this calculator include DeepSeek peak pricing?

Not automatically. DeepSeek has announced 2x pricing during specified Beijing-time peak hours, but its official pricing page had not provided an effective date when this page was verified. The calculator therefore uses regular rates; use the scenario method above until an effective date is published.

How can I get an accurate DeepSeek token count?

Use the usage object returned by a real API response. Text, word, and character conversions are planning approximations and can differ by language, formatting, code, and model tokenizer.

What is the difference between this calculator and the pricing page?

The pricing page is the site’s detailed rate and model reference. This page converts those rates into workload-specific estimates using your token mix, cache behavior, and request volume.

Is this an official DeepSeek calculator?

No. Chat-Deep.ai is an independent guide and is not affiliated with DeepSeek. This tool provides estimates from published documentation; the official platform’s usage and billing records remain authoritative for your account.

Sources and Related Guides

• DeepSeek Models & Pricing — model limits, regular token prices, and the announced peak-pricing policy.
• DeepSeek Context Caching — cache persistence, matching rules, usage fields, and best-effort limitations.
• DeepSeek Token & Token Usage — token estimates and provider-returned usage guidance.
• DeepSeek API Pricing — detailed rate comparison and purchasing context.
• DeepSeek Context Caching Explained — practical cache-friendly prompt design.
• DeepSeek Token Usage Fields — logging and interpreting the usage object.
• DeepSeek API Updates — current changes that can affect estimates.
• DeepSeek API Guide — authentication, models, endpoints, and request examples.

Last verified: August 3, 2026. Pricing is time-sensitive. Recheck the official source before making a purchasing or production decision.