DeepSeek · Flagship · 1M context window

DeepSeek V4 Pro pricing for json extraction

$0.003564 per call at 3,000 input / 800 output tokens.

Per call

$0.003564

10K calls/mo

$35.64

Cache savings

97% off input

Batch savings

0% off all

Calculate your DeepSeek V4 Pro costs

Adjust token counts, volume, and discount toggles to model your json extraction spend. Prices verified daily against provider pricing pages.

Configure your usage

3,000
100100K
800
5050K
10,000
1001M

Estimated cost

Monthly cost
$36
10,000 calls/month
Cost per call$0.003564
Daily cost$1
Input rate$0.66/MTok
Output rate$1.98/MTok
Analyze your real spend

Quick start

Call DeepSeek V4 Pro with the OpenAI Python SDK pointed at api.deepseek.com:

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.deepseek.com/v1",
    api_key=os.environ["DEEPSEEK_API_KEY"],
)
response = client.chat.completions.create(
    model="deepseek-v4-pro",
    max_tokens=800,
    messages=[{"role": "user", "content": "Your prompt here"}]
)
# Cost: ~$0.003564 per call at standard rates
# Input:  $0.66/MTok
# Output: $1.98/MTok

What drives json extraction cost

Structured JSON output is compact and predictable, so cost is set almost entirely by how much source text you send. The schema itself is identical on every call and belongs in the cached prefix. This is also a task where a smaller model often matches a larger one: the output space is constrained by the schema, which limits how wrong a cheaper model can go.

For DeepSeek V4 Pro specifically, that means output tokens cost 3.0x more than input, at $1.98 vs $0.66 per MTok. At this use case’s 3,000/800 token split, output accounts for 44% of the $0.003564 per-call cost.

Complete DeepSeek V4 Pro pricing breakdown

Standard token rates

Direction$/MTokTokens per call
Input$0.663,000
Output$1.98800

Prompt caching: 97% off input tokens

Caching drops input cost from $0.66 to $0.02/MTok. For repeated system prompts, that saves $0.001915 per call.

Batch API: 0% off all tokens

Submit requests asynchronously and receive 0% off all token costs. This works best for offline pipelines where latency requirements are flexible.

Monthly cost projections

Monthly volumeCost per callStandard monthlyCached monthlyYou save with caching
10,000 calls$0.003564$35.64$16.49$19.15
50,000 calls$0.003564$178.2$82.47$95.73
100,000 calls$0.003564$356.4$164.93$191.47
500,000 calls$0.003564$1,782$824.67$957.33
1,000,000 calls$0.003564$3,564$1,649.34$1,914.66

DeepSeek V4 Pro quality benchmarks for json extraction

Benchmark data for json extraction is pending for DeepSeek V4 Pro. Test against your own evaluation suite before moving to production.

Benchmark data is not yet available for DeepSeek V4 Pro. We recommend testing against your own evaluation criteria.

Alternative models for json extraction

2 models score 80+ on json extraction benchmarks, sorted by input rate. Cheapest: Gemini 3 Flash (9% more, 86/100 quality).

ModelProviderInput $/MTokOutput $/MTokQualityPer callvs DeepSeek
Gemini 3 FlashGemini$0.50$3.0086/100$0.0039009% more
Claude Haiku 4.5Claude$1.00$5.0088/100$0.00700096% more

About DeepSeek V4 Pro

Provider

DeepSeek

Tier

Flagship

Context

1M tokens

Released

Not published

Prices are off-peak rates from api-docs.deepseek.com (read 2026-10-11). Peak-hour prices are 2x the listed input and output rates — Tokeven does not model time-of-day tiers; off-peak is used as the base. Cache hit: $0.022/MTok input. No batch discount published. Not yet benchmarked, so never recommended.

Other models from DeepSeek

ModelTierInput $/MTokOutput $/MTokContext
DeepSeek V3Mid-tier$0.27$1.10164K
DeepSeek R1Mid-tier$0.55$2.19128K
DeepSeek FlashFast / Budget$0.15$0.601M

You can compare DeepSeek V4 Pro head-to-head against any other model on our model comparison pages, or track how pricing has changed over time on the pricing history tracker.

Frequently asked questions

How much does DeepSeek V4 Pro cost for json extraction per API call?

A typical json extraction call using DeepSeek V4 Pro costs about $0.003564 per call. This estimate uses 3,000 input tokens and 800 output tokens at standard rates. Standard rates are $0.66 per million input tokens and $1.98 per million output tokens.

Is DeepSeek V4 Pro the best model for json extraction?

Our benchmark data does not yet include a json extraction ranking for DeepSeek V4 Pro. We recommend testing it against your own evaluation criteria before production usage.

What is the cheapest model for json extraction with good quality?

The most affordable model for json extraction above 80/100 quality is Gemini 3 Flash. It comes from Gemini at $0.50 per million input tokens. Output costs $3.00 per million tokens with a quality score of 86/100. Gemini 3 Flash costs more per call than DeepSeek V4 Pro but scores higher on quality benchmarks for this task type.

How can I reduce my DeepSeek V4 Pro costs for json extraction?

Three strategies lower DeepSeek V4 Pro costs for this task type effectively. Prompt caching gives a 97% discount on input tokens when reusing system prompts. The batch API gives 0% off all tokens for asynchronous processing workloads. Prompt optimization reduces token counts through more concise instructions and context windows. Combining caching with batching brings your cost from $0.003564 to about $0.000118 per call.

How does DeepSeek V4 Pro pricing compare to other DeepSeek models?

DeepSeek has 3 other models alongside DeepSeek V4 Pro today: DeepSeek V3 at $0.27/$1.10 per million tokens (mid-tier), DeepSeek R1 at $0.55/$2.19 per million tokens (mid-tier), DeepSeek Flash at $0.15/$0.60 per million tokens (fast / budget). The right choice depends on whether your json extraction workload prioritizes quality, cost, or speed.

What context window does DeepSeek V4 Pro support?

DeepSeek V4 Pro supports a context window of 1M tokens per API call. This sets the maximum combined length of your input prompt and generated response. For json extraction, typical calls use 3,000 input and 800 output tokens. That is well within this limit, leaving room for longer prompts or multi-turn conversations.

Track what you spend on AI

This calculator estimates costs based on published rates only. Connect your API usage to see where your money goes and which models drive your spend.