TechCompare LogoTechCompare

DeepSeek V4 Pro API Pricing & Cost Calculator

DeepSeek V4 Pro is the ultimate price-to-performance champion. Prompt caching drops inputs to a near-zero $0.0036 per million, making it exceptionally cost-effective.

DeepSeek V4 Pro offers industry-disrupting pricing for frontier-level reasoning capabilities.

By TechCompare · Updated

Input tokens
100,000
per request
Output tokens
5,000
per request
Volume
100 / monthly
Standard API

Calculator

Cost Comparison

Based on 100,000 input tokens (50% cached), 5,000 output tokens, and 100 requests.

Same 100,000 in / 5,000 out (50% cached) scenario, pre-loaded. Adjust tokens, caching, or swap models.
Edit in the full tool

How this is calculated

DeepSeek V4 Pro is priced at $0.435 per million input tokens and $0.87 per million output tokens, supporting an aggressive 99.17% caching discount ($0.003625 per million). These are the original April preview rates - the 0813 refresh repriced the model, and the new rates are listed on the /llm-pricing-calculator/deepseek-v4-pro-0813 page.

Verdict

The base numbers are already extreme: $0.435/M input and $0.87/M output, far below any US-frontier rival. The 99.17% cache discount then takes cached input down to $0.0036/M, which on a stable-prompt workload is effectively free, a 100K-token system prompt reused 100K times per day lands at roughly $0.036 of daily cached input cost. There's no batch discount, which is the one missing lever, but the cache math alone is enough to make DeepSeek V4 Pro the cost-floor pick for high-volume TTL-stable prompts where the model's reasoning tier is good enough.

More API Standalones scenarios

GPT-5.5 Pricing
Single-model gpt-5.5 cost estimate
View details ➜
GPT-5.4 Pricing
Single-model gpt-5.4 cost estimate
View details ➜
Claude Opus 4.8 Pricing
Single-model claude-opus-4.8 cost estimate
View details ➜

Related guides

deepseek v4 pro VRAM estimate
VRAM footprint for the deepseek v4 pro model this pricing entry is for.
View guide ➜
BPE tokenization explained
How tokenizers chunk text into the units VRAM serves.
View guide ➜

Frequently asked questions

Does DeepSeek V4 Pro support prompt caching?
Yes, it offers a 99.17% discount on cached input tokens, reducing the input price to $0.0036 per million for matches.
How much does DeepSeek V4 Pro cost per million output tokens?
DeepSeek V4 Pro charges just $0.87 per million output tokens, making it one of the cheapest frontier-tier models on the market. With the aggressive 99.17% prompt caching discount, cached input drops to $0.0036 per million. There is no batch discount on DeepSeek V4 Pro.
Is DeepSeek V4 Pro too cheap to be safe?
No, the price reflects vendor economics, not quality compromise. DeepSeek's parent company can offer the rate because of cheaper Chinese infrastructure and a different cost structure. Independent benchmarks show V4 Pro competitive with Claude Sonnet 4.6 and GPT-5.4 on most tasks, often at 5-10x lower cost. The trade-off is geographic data residency and tooling integration.

Related tools

LLM VRAM Calculator

Calculate the VRAM needed to run or fine-tune any LLM at any quantization.

Use tool ➜

Power Cost Estimator

Estimate annual electricity costs for your PC, Server, or TV.

Use tool ➜

Data Transfer Calculator

Estimate transfer times for files over USB, WiFi, Ethernet, and more.

Use tool ➜

JSON Formatter

Validate, format, and minify JSON data with syntax highlighting.

Use tool ➜