DeepSeek · Mid-tier · 128K context window

DeepSeek R1 pricing for data extraction

$0.004390 per call at 4,000 input / 1,000 output tokens.

Per call

$0.004390

10K calls/mo

$43.9

Cache savings

75% off input

Batch savings

0% off all

Calculate your DeepSeek R1 costs

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

Configure your usage

4,000
100100K
1,000
5050K
10,000
1001M

Estimated cost

Monthly cost
$44
10,000 calls/month
Cost per call$0.004390
Daily cost$1
Input rate$0.55/MTok
Output rate$2.19/MTok
Analyze your real spend

Quick start

Call DeepSeek R1 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-r1",
    max_tokens=1000,
    messages=[{"role": "user", "content": "Your prompt here"}]
)
# Cost: ~$0.004390 per call at standard rates
# Input:  $0.55/MTok
# Output: $2.19/MTok

What drives data extraction cost

Extraction is input-heavy and output-light (the raw document goes in, structured fields come out), which makes it one of the cheapest tasks per unit of value on this list. Output is small enough that output pricing is nearly irrelevant. Cost tracks document size, so the lever is sending only the pages that contain the fields you want.

For DeepSeek R1 specifically, that means output tokens cost 4.0x more than input, at $2.19 vs $0.55 per MTok. At this use case’s 4,000/1,000 token split, output accounts for 50% of the $0.004390 per-call cost.

Complete DeepSeek R1 pricing breakdown

Standard token rates

Direction$/MTokTokens per call
Input$0.554,000
Output$2.191,000

Prompt caching: 75% off input tokens

Caching drops input cost from $0.55 to $0.14/MTok. For repeated system prompts, that saves $0.001639 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$0.004390$43.9$27.51$16.39
50,000 calls$0.004390$219.5$137.55$81.95
100,000 calls$0.004390$439$275.1$163.9
500,000 calls$0.004390$2,195$1,375.5$819.5
1,000,000 calls$0.004390$4,390$2,751$1,639

DeepSeek R1 quality benchmarks for data extraction

Benchmark data for data extraction is pending for DeepSeek R1. Test against your own evaluation suite before moving to production.

Benchmark data is not yet available for DeepSeek R1. We recommend testing against your own evaluation criteria.

Alternative models for data extraction

2 models score 80+ on data extraction benchmarks, sorted by input rate. Cheapest: Gemini 3 Flash (14% more, 86/100 quality).

ModelProviderInput $/MTokOutput $/MTokQualityPer callvs DeepSeek
Gemini 3 FlashGemini$0.50$3.0086/100$0.00500014% more
Claude Haiku 4.5Claude$1.00$5.0088/100$0.009000105% more

About DeepSeek R1

Provider

DeepSeek

Tier

Mid-tier

Context

128K tokens

Released

Jan 2025

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: $0.14/MTok input. No batch discount published. Reasoning model: output includes chain-of-thought tokens. Not yet benchmarked, so never recommended.

Other models from DeepSeek

ModelTierInput $/MTokOutput $/MTokContext
DeepSeek V3Mid-tier$0.27$1.10164K
DeepSeek FlashFast / Budget$0.15$0.601M
DeepSeek V4 ProFlagship$0.66$1.981M

You can compare DeepSeek R1 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 R1 cost for data extraction per API call?

A typical data extraction call using DeepSeek R1 costs about $0.004390 per call. This estimate uses 4,000 input tokens and 1,000 output tokens at standard rates. Standard rates are $0.55 per million input tokens and $2.19 per million output tokens.

Is DeepSeek R1 the best model for data extraction?

Our benchmark data does not yet include a data extraction ranking for DeepSeek R1. We recommend testing it against your own evaluation criteria before production usage.

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

The most affordable model for data 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 R1 but scores higher on quality benchmarks for this task type.

How can I reduce my DeepSeek R1 costs for data extraction?

Three strategies lower DeepSeek R1 costs for this task type effectively. Prompt caching gives a 75% 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 $0.004390 to about $0.001119 per call.

How does DeepSeek R1 pricing compare to other DeepSeek models?

DeepSeek has 3 other models alongside DeepSeek R1 today: DeepSeek V3 at $0.27/$1.10 per million tokens (mid-tier), DeepSeek Flash at $0.15/$0.60 per million tokens (fast / budget), DeepSeek V4 Pro at $0.66/$1.98 per million tokens (flagship). The right choice depends on whether your data extraction workload prioritizes quality, cost, or speed.

What context window does DeepSeek R1 support?

DeepSeek R1 supports a context window of 128K tokens per API call. This sets the maximum combined length of your input prompt and generated response. For data extraction, typical calls use 4,000 input and 1,000 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.