Cost per 100K Tokens: DeepSeek V4 Pro for Worker Agents

Complete Analysis: 102,000 tokens for DeepSeek V4 Pro
⚡ 10% Cached

Complete analysis of pricing, performance, and use cases for DeepSeek's DeepSeek V4 Pro model with 10% Cached.

⚡ Caching Optimized (up to 98% savings)
$0.040977 Total Cost
102,000 Total Tokens
6 minutes, 3.98 seconds Processing Time
280 Effective Tokens/Sec

Click Recalculate to update after making changes

Select AI Model

DeepSeek V4 Pro
DeepSeekMax Context: 1,000,000 tokens
$0.435 / $0.87 per 1M tokens
▼
▼
Use Batch API (50% discount)
10%
Provider-specific multipliers applied after all calculations
Enable for cache discounts
Select platform to enforce context limits
Number of requests (max 1M). Summary view auto-enabled >10k.

Calculate Token Costs

$0.040977 Total Cost
$0.039150 Input Cost
$0.001740 Output Cost
$0.000000 Unit Cost
$0.000000 Search Cost
$0.000000 Request Fee
$0.000000 Tool Fee
$0.000000 Code Execution
102,000Total Tokens
$0.000402Cost per 1K
2,489,201Tokens per $
📊 Advanced Cost Breakdown

Processing Speed

6m 3s Processing Time
300 Tokens/Second
180ms Time to First Token
280 Effective Speed

Model Comparison

Select a model to see comparisons with competitors.

Model Information

Select a model to see detailed information.

🔄 Advanced Options

⚡ Optimization
Flat fee per session (e.g., $0.03 for Code Interpreter)
Hourly storage fee for cached data
First 50 hours free, $0.05/hour after
🧠 Reasoning & Thinking
Manual thinking tokens (billed at output rate)
🔧 Special Modes
Enable 6.0x Fast Mode multiplier
📚 Research & Citations
Enable $1.00/$4.00 rates + $10.00/1k search
Enable research tier pricing
Fee per source cited
🎤 Realtime Audio & Video
Session length for billing

DeepSeek V4 Pro DeepSeek 1000000

$0.040977
Total Cost
⚡ 10% Cached 📊 Batch API 🔧 Tools
👁️
Vision/Images
✗ Not Available
🎧
Audio Processing
✗ Not Available
🎥
Video Analysis
✗ Not Available
🔧
Tool Usage
✓ Available
📄
OCR Support
✗ Not Available
📊
Batch API
✗ Not Available
⚡
Caching
✓ Available
98% savings

💰 Total Cost Calculation (from Plugin)

Base Cost (No Optimizations) $0.045240 (rounded ~ $0.05) Input: $0.043500 (rounded ~ $0.04)
Output: $0.001740
Optimized Cost $0.040977 Input: $0.043500 (rounded ~ $0.04)
Output: $0.001740
Unit: $0.000000
Fees: $0.000000
Total Savings $0.004263 9.4% discount

Detailed Cost Analysis (from Plugin)

For 100,000 input tokens and 2,000 output tokens:

  • Input Cost: $0.043500 (rounded ~ $0.04)
  • Output Cost: $0.001740
  • Total Cost: $0.040977
  • Cost per 1K tokens: $0.000402
  • Tokens per dollar: 2,489,201 tokens
  • Context Window: 1000000 tokens

Speed & Performance Analysis

With a processing speed of 300 tokens per second and 180ms time to first token:

  • Processing Time: 6 minutes, 3.98 seconds
  • Latency: 180 milliseconds to first token
  • Base Throughput: 300 tokens/second
  • Effective Throughput: 280 tokens/second (temperature-adjusted)

Best Use Cases

Ideal for scaling out worker agent tasks within an orchestration system where cost efficiency is paramountwithout compromising on reasoning and instruction-following capabilities.

Want this applied to YOUR actual stack?

This calculator shows the math for DeepSeek V4 Pro. Your decision needs more — current infrastructure, compliance requirements, actual workload patterns, volume tiers — that change which model is right for you.

Get a $39 personalized AI Architecture Audit. PDF tailored to your stack, delivered in under 60 seconds. 7-day no-questions-asked refund.

Get my instant AI audit — $39 →

✨ Market Recommendations AI Model Registry

← Back to DeepSeek V4 Pro
📋 Active Input Parameters
Input Tokens: 100,000
Output Tokens: 2,000
Batch API: Enabled (50% discount)
Cached Tokens: 10%
Tools: Enabled
Rank AI Model & Provider Total Cost vs DeepSeek V4 Pro
🏆 Mistral Small 3
Mistral AI
 $0.002425 Best Value ↓ 94.1% cheaper
🥈 Gemini 3.1 Flash Lite
Google
 $0.006438 (rounded ~ $0.01) ↓ 84.3% cheaper
🥉 Gemini 3.5 Flash-Lite
Google
 $0.008075 (rounded ~ $0.01) ↓ 80.3% cheaper
#4 Gemini 2.5 Flash
Google
 $0.008075 (rounded ~ $0.01) ↓ 80.3% cheaper
#5 Mistral Large 3
Mistral AI
 $0.012125 (rounded ~ $0.01) ↓ 70.4% cheaper
#6 Gemini 3.8 Flash
Google
 $0.018938 (rounded ~ $0.02) ↓ 53.8% cheaper
#7 GPT-5.4 mini
OpenAI
 $0.019313 ↓ 52.9% cheaper
#8 o4-mini Deep Research
OpenAI
 $0.024750 (rounded ~ $0.02) ↓ 39.6% cheaper
#9 Claude Haiku 4.5
Anthropic
 $0.025250 (rounded ~ $0.03) ↓ 38.4% cheaper
#10 Gemini 3.1 Flash
Google
 $0.025750 (rounded ~ $0.03) ↓ 37.2% cheaper
#11 GPT-5.6 Luna
OpenAI
 $0.025750 (rounded ~ $0.03) ↓ 37.2% cheaper
#12 o4-mini
OpenAI
 $0.027225 (rounded ~ $0.03) ↓ 33.6% cheaper
#13 Gemini 3.6 Flash
Google
 $0.037875 (rounded ~ $0.04) ↓ 7.6% cheaper
#14 Gemini 3.5 Flash
Google
 $0.038625 (rounded ~ $0.04) ↓ 5.7% cheaper
#15 GPT-5.3 Codex Spark
OpenAI
 $0.046813 (rounded ~ $0.05) ↑ 14.2% more
#16 GPT-5.3 Instant
OpenAI
 $0.046813 (rounded ~ $0.05) ↑ 14.2% more
#17 Claude Sonnet 5
Anthropic
 $0.050500 ↑ 23.2% more
#18 GPT-5.6 Terra
OpenAI
 $0.064375 (rounded ~ $0.06) ↑ 57.1% more
#19 Gemini 2.5 Pro
Google
 $0.066875 (rounded ~ $0.07) ↑ 63.2% more
#20 Claude Sonnet 4.6
Anthropic
 $0.075750 (rounded ~ $0.08) ↑ 84.9% more
#21 Grok 4.3
xAI
 $0.095000 (rounded ~ $0.10) ↑ 131.8% more
#22 Grok 4.20 Beta
xAI
 $0.095000 (rounded ~ $0.10) ↑ 131.8% more
#23 Gemini 3.1 Pro
Google
 $0.103000 (rounded ~ $0.10) ↑ 151.4% more
#24 Claude Opus 4.7
Anthropic
 $0.126250 (rounded ~ $0.13) ↑ 208.1% more
#25 Claude Opus 5
Anthropic
 $0.126250 (rounded ~ $0.13) ↑ 208.1% more
#26 Claude Opus 4.8
Anthropic
 $0.126250 (rounded ~ $0.13) ↑ 208.1% more
#27 Claude Opus 4.6
Anthropic
 $0.126250 (rounded ~ $0.13) ↑ 208.1% more
#28 GPT-5.4
OpenAI
 $0.128750 (rounded ~ $0.13) ↑ 214.2% more
#29 GPT-5.4 Thinking
OpenAI
 $0.128750 (rounded ~ $0.13) ↑ 214.2% more
#30 GPT-5.5 Instant
OpenAI
 $0.128750 (rounded ~ $0.13) ↑ 214.2% more
#31 GPT-5.6 Sol
OpenAI
 $0.128750 (rounded ~ $0.13) ↑ 214.2% more
#32 o3 Deep Research
OpenAI
 $0.247500 (rounded ~ $0.25) ↑ 504% more
#33 Claude Fable 5.1
Anthropic
 $0.250625 ↑ 511.6% more
#34 Claude Mythos 5.1
Anthropic
 $0.250625 ↑ 511.6% more
#35 Claude Fable 5
Anthropic
 $0.252500 (rounded ~ $0.25) ↑ 516.2% more
#36 Claude Mythos 5
Anthropic
 $0.252500 (rounded ~ $0.25) ↑ 516.2% more
#37 GPT-5.5
OpenAI
 $0.257500 (rounded ~ $0.26) ↑ 528.4% more
#38 o3 Pro
OpenAI
 $0.495000 (rounded ~ $0.50) ↑ 1108% more
#39 GPT-6 Astra
OpenAI
 $0.505000 (rounded ~ $0.51) ↑ 1132.4% more
#40 GPT-5.2 Pro
OpenAI
 $0.561750 (rounded ~ $0.56) ↑ 1270.9% more
#41 GPT-5.2 Pro
OpenAI
 $0.561750 (rounded ~ $0.56) ↑ 1270.9% more
🏆

Mistral Small 3
Mistral AI

$0.002425
vs DeepSeek V4 Pro: ↓ 94.1%
🥈

Gemini 3.1 Flash Lite
Google

$0.006438 (rounded ~ $0.01)
vs DeepSeek V4 Pro: ↓ 84.3%
🥉

Gemini 3.5 Flash-Lite
Google

$0.008075 (rounded ~ $0.01)
vs DeepSeek V4 Pro: ↓ 80.3%
#4

Gemini 2.5 Flash
Google

$0.008075 (rounded ~ $0.01)
vs DeepSeek V4 Pro: ↓ 80.3%
#5

Mistral Large 3
Mistral AI

$0.012125 (rounded ~ $0.01)
vs DeepSeek V4 Pro: ↓ 70.4%
#6

Gemini 3.8 Flash
Google

$0.018938 (rounded ~ $0.02)
vs DeepSeek V4 Pro: ↓ 53.8%
#7

GPT-5.4 mini
OpenAI

$0.019313
vs DeepSeek V4 Pro: ↓ 52.9%
#8

o4-mini Deep Research
OpenAI

$0.024750 (rounded ~ $0.02)
vs DeepSeek V4 Pro: ↓ 39.6%
#9

Claude Haiku 4.5
Anthropic

$0.025250 (rounded ~ $0.03)
vs DeepSeek V4 Pro: ↓ 38.4%
#10

Gemini 3.1 Flash
Google

$0.025750 (rounded ~ $0.03)
vs DeepSeek V4 Pro: ↓ 37.2%
#11

GPT-5.6 Luna
OpenAI

$0.025750 (rounded ~ $0.03)
vs DeepSeek V4 Pro: ↓ 37.2%
#12

o4-mini
OpenAI

$0.027225 (rounded ~ $0.03)
vs DeepSeek V4 Pro: ↓ 33.6%
#13

Gemini 3.6 Flash
Google

$0.037875 (rounded ~ $0.04)
vs DeepSeek V4 Pro: ↓ 7.6%
#14

Gemini 3.5 Flash
Google

$0.038625 (rounded ~ $0.04)
vs DeepSeek V4 Pro: ↓ 5.7%
#15

GPT-5.3 Codex Spark
OpenAI

$0.046813 (rounded ~ $0.05)
vs DeepSeek V4 Pro: ↑ 14.2%
#16

GPT-5.3 Instant
OpenAI

$0.046813 (rounded ~ $0.05)
vs DeepSeek V4 Pro: ↑ 14.2%
#17

Claude Sonnet 5
Anthropic

$0.050500
vs DeepSeek V4 Pro: ↑ 23.2%
#18

GPT-5.6 Terra
OpenAI

$0.064375 (rounded ~ $0.06)
vs DeepSeek V4 Pro: ↑ 57.1%
#19

Gemini 2.5 Pro
Google

$0.066875 (rounded ~ $0.07)
vs DeepSeek V4 Pro: ↑ 63.2%
#20

Claude Sonnet 4.6
Anthropic

$0.075750 (rounded ~ $0.08)
vs DeepSeek V4 Pro: ↑ 84.9%
#21

Grok 4.3
xAI

$0.095000 (rounded ~ $0.10)
vs DeepSeek V4 Pro: ↑ 131.8%
#22

Grok 4.20 Beta
xAI

$0.095000 (rounded ~ $0.10)
vs DeepSeek V4 Pro: ↑ 131.8%
#23

Gemini 3.1 Pro
Google

$0.103000 (rounded ~ $0.10)
vs DeepSeek V4 Pro: ↑ 151.4%
#24

Claude Opus 4.7
Anthropic

$0.126250 (rounded ~ $0.13)
vs DeepSeek V4 Pro: ↑ 208.1%
#25

Claude Opus 5
Anthropic

$0.126250 (rounded ~ $0.13)
vs DeepSeek V4 Pro: ↑ 208.1%
#26

Claude Opus 4.8
Anthropic

$0.126250 (rounded ~ $0.13)
vs DeepSeek V4 Pro: ↑ 208.1%
#27

Claude Opus 4.6
Anthropic

$0.126250 (rounded ~ $0.13)
vs DeepSeek V4 Pro: ↑ 208.1%
#28

GPT-5.4
OpenAI

$0.128750 (rounded ~ $0.13)
vs DeepSeek V4 Pro: ↑ 214.2%
#29

GPT-5.4 Thinking
OpenAI

$0.128750 (rounded ~ $0.13)
vs DeepSeek V4 Pro: ↑ 214.2%
#30

GPT-5.5 Instant
OpenAI

$0.128750 (rounded ~ $0.13)
vs DeepSeek V4 Pro: ↑ 214.2%
#31

GPT-5.6 Sol
OpenAI

$0.128750 (rounded ~ $0.13)
vs DeepSeek V4 Pro: ↑ 214.2%
#32

o3 Deep Research
OpenAI

$0.247500 (rounded ~ $0.25)
vs DeepSeek V4 Pro: ↑ 504%
#33

Claude Fable 5.1
Anthropic

$0.250625
vs DeepSeek V4 Pro: ↑ 511.6%
#34

Claude Mythos 5.1
Anthropic

$0.250625
vs DeepSeek V4 Pro: ↑ 511.6%
#35

Claude Fable 5
Anthropic

$0.252500 (rounded ~ $0.25)
vs DeepSeek V4 Pro: ↑ 516.2%
#36

Claude Mythos 5
Anthropic

$0.252500 (rounded ~ $0.25)
vs DeepSeek V4 Pro: ↑ 516.2%
#37

GPT-5.5
OpenAI

$0.257500 (rounded ~ $0.26)
vs DeepSeek V4 Pro: ↑ 528.4%
#38

o3 Pro
OpenAI

$0.495000 (rounded ~ $0.50)
vs DeepSeek V4 Pro: ↑ 1108%
#39

GPT-6 Astra
OpenAI

$0.505000 (rounded ~ $0.51)
vs DeepSeek V4 Pro: ↑ 1132.4%
#40

GPT-5.2 Pro
OpenAI

$0.561750 (rounded ~ $0.56)
vs DeepSeek V4 Pro: ↑ 1270.9%
#41

GPT-5.2 Pro
OpenAI

$0.561750 (rounded ~ $0.56)
vs DeepSeek V4 Pro: ↑ 1270.9%
✨ How recommendations work (v8.6.0): We scan all active models in the registry and only include those that support ALL your current inputs. For token-based models, we check if they can handle your token counts. For special pricing models (OCR, video, audio), we verify they have the correct pricing structure. Features marked requested were in your inputs but not supported by that model. Now using official provider pricing without reseller markups.

Optimizing Worker Agent Costs

For translation agencies implementing multi-agent systems, efficiently managing the operational costs of individual worker agents is crucial for scalability. DeepSeek V4 Pro presents a compelling choice for these roles, offering a strong blend of reasoning capabilities and competitive pricing. Worker agents often handle specific, recurring tasks within a larger orchestration flow, such as segment translation, terminology extraction, or quality checks. DeepSeek V4 Pro’s ability to follow instructions accurately and its substantial 1 million token context window ensure it can handle moderately complex sub-tasks effectively. Its attractive cost structure per 100,000 tokens makes it an ideal candidate for scaling out worker agent fleets, allowing agencies to deploy more agents or process larger volumes of data per agent without a proportional increase in expenditure. When an orchestrator delegates work, the efficiency and cost-effectiveness of each worker agent directly impacts the overall profitability and throughput of the AI-assisted translation service. DeepSeek V4 Pro empowers this by providing reliable performance at an accessible price point.

Frequently Asked Questions

How accurate are these AI model cost calculations?
Our calculations are based on official pricing from each provider (Google, OpenAI, Anthropic, Meta, xAI, Perplexity, DeepSeek, Mistral) and are updated regularly. We account for all factors including multimodal inputs, caching discounts, batch API pricing, tool usage multipliers, OCR processing, audio minutes, silence fees, and research mode pricing. Note: Reseller markups and dedicated instance multipliers have been removed to reflect official provider pricing.
How does prompt caching work?
Caching discounts vary by provider: Google and OpenAI offer 90% discounts on cached input tokens. Anthropic uses write (1.25x) and read (0.10x) multipliers. Savings are applied to the token portion only, not unit-based fees.
How do Market Recommendations work (v8.6.0)?
Our recommendation engine scans the entire model registry and only includes models that support ALL your current input parameters (tokens, images, video, audio, OCR, tools, batch API, etc.). It calculates exact costs with your settings and sorts by price, showing you the best value options that can handle your complete workflow. Special pricing models (OCR, video, audio, image generation) are properly handled and only appear when their specific input types are requested. v8.6.0 removes reseller markups (20% buffer) and dedicated instance multipliers to reflect official provider pricing.
What is the YemHub AI Calculator Tool?
The YemHub AI Calculator is the most comprehensive tool for estimating costs and comparing performance metrics across 50+ AI models. It calculates token-based pricing, analyzes multimodal processing, accounts for state-dependent pricing (context cliffs, tiered tunnels), provides optimization recommendations, and now offers intelligent market matching to find the best alternatives for your specific needs.

Related model pricing

DeepSeek V4 Pro currently costs $0.44 / $0.87 per 1M tokens. These are the models worth pricing against it, taken live from the tracked registry.

Compare across providers

Other models from the same provider

See every tracked AI pricing change →