Large Scale Data Extraction: Gemini 3.1 Pro vs DeepSeek V4 (Engram) (Scenario 2)

Gemini 3.1 Pro vs DeepSeek V4 (Engram)
Complete Comparison: 20,000 input tokens × 5,000 output tokens
Comparison Mode
⚡ 30% Cached

Complete comparison of pricing, performance, and capabilities for 2 leading AI models with 30% Cached.

⚡ Caching Optimized (up to 98% savings) 📊 Batch API
Comparison Criteria Gemini 3.1 Pro
Google
DeepSeek V4 (Engram)
DeepSeek
Calculation Results (Current Inputs) (30% cached)
Input Tokens 20,000 N/A (Special Pricing)
Output Tokens 5,000 N/A (Special Pricing)
Cost Breakdown
Input Cost $0.020000 N/A (Special Pricing)
Output Cost $0.030000 N/A (Special Pricing)
Unit Cost (Audio/OCR) $0.000000 $0.000000
Service Fees $0.000000 $0.000000
Total Cost $0.044600 (rounded ~ $0.04) Most Expensive $0.010492 Best Value
Processing Time 1 minute, 7.06 seconds Fastest 1 minute, 29.35 seconds Slowest
Tokens per Second 400 N/A (Special Pricing)
Time to First Token 220ms Worst 180ms Best
Cost per 1K tokens $0.001784 N/A (Special Pricing)
Tokens per Dollar 560,538 N/A (Special Pricing)
Cost per 1 Million Tokens (Informational)
Input Cost / 1M (Base) $1.000000 N/A (Special Pricing)
Output Cost / 1M (Base) $6.000000 N/A (Special Pricing)
Input Cost / 1M (Optimized) $0.500000
Optimizations: 50.0% batch
N/A (Special Pricing)
Output Cost / 1M (Optimized) $3.000000
Optimizations: 50.0% batch
N/A (Special Pricing)
Capabilities & Advanced Features
Images Support ✓ Supported ✗ Not Supported
Video Support ✓ Supported ✗ Not Supported
Audio Support ✓ Supported ✗ Not Supported
Caching Support
30
✓ Supported ✓ Supported
Batch API Support ✓ Supported ✗ Not Supported
Tool Usage Support ✓ Supported ✓ Supported
Scroll horizontally to see all data

🔄 Compare Different AI Models

1

First Model

2

Second Model

Select providers and models above, then click "Compare Models" to update the comparison.
All other parameters will be preserved from the current comparison.

Click Recalculate to update after making changes

Select AI Model

Gemini 3.1 Pro
GoogleMax Context: 1,000,000 tokens
$2 / $12 per 1M tokens (Tier 1)
State-dependent pricing active. Current tier: Standard
▼
▼
Use Batch API (50% discount)
30%
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

$0.044600 Total Cost
$0.014000 Input Cost
$0.030000 Output Cost
$0.000000 Unit Cost
$0.000000 Search Cost
$0.000000 Request Fee
$0.000000 Tool Fee
$0.000000 Code Execution
25,000Total Tokens
$0.001784Cost per 1K
560,538Tokens per $
🔄 Dynamic Tier Pricing Active: Using Standard pricing (tier1) based on token volume.
📊 Advanced Cost Breakdown

Processing Speed

1m 7s Processing Time
400 Tokens/Second
220ms Time to First Token
374 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
📊 Multiple Models Detected: This page contains data for 2 models. See the detailed comparison table above, and switch between models using tabs below.

Gemini 3.1 Pro Google 1000000

$0.044600 (rounded ~ $0.04)
Total Cost
⚡ 30% Cached 📊 Batch API 🔧 Tools
👁️
Vision/Images
✓ Available
🎧
Audio Processing
✓ Available
🎥
Video Analysis
✓ Available
🔧
Tool Usage
✓ Available
📄
OCR Support
✗ Not Available
📊
Batch API
✓ Available
⚡
Caching
✓ Available
90% savings

💰 Total Cost Calculation (from Plugin)

Base Cost (No Optimizations) $0.050000 Input: $0.020000
Output: $0.030000
Optimized Cost $0.044600 (rounded ~ $0.04) Input: $0.020000
Output: $0.030000
Unit: $0.000000
Fees: $0.000000
Total Savings $0.005400 (rounded ~ $0.01) 10.8% discount

Advanced Cost Breakdown (from Plugin)

📊 Batch API
50.0% off
Asynchronous processing discount
📊 Dynamic Tier
Standard
tier1 pricing based on 0 tokens

Detailed Cost Analysis (from Plugin)

For 20,000 input tokens and 5,000 output tokens:

  • Input Cost: $0.020000
  • Output Cost: $0.030000
  • Total Cost: $0.044600 (rounded ~ $0.04)
  • Cost per 1K tokens: $0.001784
  • Tokens per dollar: 560,538 tokens
  • Context Window: 1000000 tokens

Speed & Performance Analysis

With a processing speed of 400 tokens per second and 220ms time to first token:

  • Processing Time: 1 minute, 7.06 seconds
  • Latency: 220 milliseconds to first token
  • Base Throughput: 400 tokens/second
  • Effective Throughput: 374 tokens/second (temperature-adjusted)

Best Use Cases

Processing massive RAG datasets and internal logs.

Want this applied to YOUR actual stack?

This calculator shows the math for Gemini 3.1 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 →

DeepSeek V4 (Engram) DeepSeek 1000000

$0.010492
Total Cost
⚡ 30% 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) $0.013050 (rounded ~ $0.01) Input: $0.008700 (rounded ~ $0.01)
Output: $0.004350
Optimized Cost $0.010492 Input: $0.008700 (rounded ~ $0.01)
Output: $0.004350
Unit: $0.000000
Fees: $0.000000
Total Savings $0.002558 19.6% discount

Detailed Cost Analysis (from Plugin)

For 20,000 input tokens and 5,000 output tokens:

  • Input Cost: $0.008700 (rounded ~ $0.01)
  • Output Cost: $0.004350
  • Total Cost: $0.010492
  • Cost per 1K tokens: $0.000420
  • Tokens per dollar: 2,382,722 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: 1 minute, 29.35 seconds
  • Latency: 180 milliseconds to first token
  • Base Throughput: 300 tokens/second
  • Effective Throughput: 280 tokens/second (temperature-adjusted)

Best Use Cases

Processing massive RAG datasets and internal logs.

Want this applied to YOUR actual stack?

This calculator shows the math for DeepSeek V4 (Engram). 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 Gemini 3.1 Pro
📋 Active Input Parameters
Input Tokens: 20,000
Output Tokens: 5,000
Batch API: Enabled (50% discount)
Cached Tokens: 30%
Tools: Enabled
Rank AI Model & Provider Total Cost vs Gemini 3.1 Pro vs DeepSeek V4 (Engram)
🏆 Mistral Small 3
Mistral AI
 $0.000740 Best Value ↓ 98.3% cheaper ↓ 92.9% cheaper
🥈 Gemini 3.1 Flash Lite
Google
 $0.002788 ↓ 93.8% cheaper ↓ 73.4% cheaper
🥉 Mistral Large 3
Mistral AI
 $0.003700 ↓ 91.7% cheaper ↓ 64.7% cheaper
#4 Gemini 3.5 Flash-Lite
Google
 $0.004220 ↓ 90.5% cheaper ↓ 59.8% cheaper
#5 Gemini 2.5 Flash
Google
 $0.004220 ↓ 90.5% cheaper ↓ 59.8% cheaper
#6 Gemini 3.8 Flash
Google
 $0.007425 (rounded ~ $0.01) ↓ 83.4% cheaper ↓ 29.2% cheaper
#7 GPT-5.4 mini
OpenAI
 $0.008363 (rounded ~ $0.01) ↓ 81.3% cheaper ↓ 20.3% cheaper
#8 o4-mini Deep Research
OpenAI
 $0.008650 (rounded ~ $0.01) ↓ 80.6% cheaper ↓ 17.6% cheaper
#9 o4-mini
OpenAI
 $0.009515 ↓ 78.7% cheaper ↓ 9.3% cheaper
#10 Claude Haiku 4.5
Anthropic
 $0.009900 ↓ 77.8% cheaper ↓ 5.6% cheaper
#11 Gemini 3.1 Flash
Google
 $0.011150 (rounded ~ $0.01) ↓ 75% cheaper ↑ 6.3% more
#12 GPT-5.6 Luna
OpenAI
 $0.011150 (rounded ~ $0.01) ↓ 75% cheaper ↑ 6.3% more
#13 Gemini 3.6 Flash
Google
 $0.014850 (rounded ~ $0.01) ↓ 66.7% cheaper ↑ 41.5% more
#14 Gemini 3.5 Flash
Google
 $0.016725 (rounded ~ $0.02) ↓ 62.5% cheaper ↑ 59.4% more
#15 Claude Sonnet 5
Anthropic
 $0.019800 ↓ 55.6% cheaper ↑ 88.7% more
#16 GPT-5.3 Codex Spark
OpenAI
 $0.023888 (rounded ~ $0.02) ↓ 46.4% cheaper ↑ 127.7% more
#17 GPT-5.3 Instant
OpenAI
 $0.023888 (rounded ~ $0.02) ↓ 46.4% cheaper ↑ 127.7% more
#18 Grok 4.3
xAI
 $0.024600 (rounded ~ $0.02) ↓ 44.8% cheaper ↑ 134.5% more
#19 Grok 4.20 Beta
xAI
 $0.024600 (rounded ~ $0.02) ↓ 44.8% cheaper ↑ 134.5% more
#20 GPT-5.6 Terra
OpenAI
 $0.027875 (rounded ~ $0.03) ↓ 37.5% cheaper ↑ 165.7% more
#21 Claude Sonnet 4.6
Anthropic
 $0.029700 ↓ 33.4% cheaper ↑ 183.1% more
#22 Gemini 2.5 Pro
Google
 $0.034125 (rounded ~ $0.03) ↓ 23.5% cheaper ↑ 225.2% more
#23 Claude Opus 4.7
Anthropic
 $0.049500 ↑ 11% more ↑ 371.8% more
#24 Claude Opus 5
Anthropic
 $0.049500 ↑ 11% more ↑ 371.8% more
#25 Claude Opus 4.8
Anthropic
 $0.049500 ↑ 11% more ↑ 371.8% more
#26 Claude Opus 4.6
Anthropic
 $0.049500 ↑ 11% more ↑ 371.8% more
#27 GPT-5.4
OpenAI
 $0.055750 (rounded ~ $0.06) ↑ 25% more ↑ 431.3% more
#28 GPT-5.4 Thinking
OpenAI
 $0.055750 (rounded ~ $0.06) ↑ 25% more ↑ 431.3% more
#29 GPT-5.5 Instant
OpenAI
 $0.055750 (rounded ~ $0.06) ↑ 25% more ↑ 431.3% more
#30 GPT-5.6 Sol
OpenAI
 $0.055750 (rounded ~ $0.06) ↑ 25% more ↑ 431.3% more
#31 o3 Deep Research
OpenAI
 $0.086500 (rounded ~ $0.09) ↑ 93.9% more ↑ 724.4% more
#32 Claude Fable 5.1
Anthropic
 $0.097875 (rounded ~ $0.10) ↑ 119.5% more ↑ 832.8% more
#33 Claude Mythos 5.1
Anthropic
 $0.097875 (rounded ~ $0.10) ↑ 119.5% more ↑ 832.8% more
#34 Claude Fable 5
Anthropic
 $0.099000 (rounded ~ $0.10) ↑ 122% more ↑ 843.6% more
#35 Claude Mythos 5
Anthropic
 $0.099000 (rounded ~ $0.10) ↑ 122% more ↑ 843.6% more
#36 GPT-5.5
OpenAI
 $0.111500 (rounded ~ $0.11) ↑ 150% more ↑ 962.7% more
#37 o3 Pro
OpenAI
 $0.173000 (rounded ~ $0.17) ↑ 287.9% more ↑ 1548.8% more
#38 GPT-6 Astra
OpenAI
 $0.198000 (rounded ~ $0.20) ↑ 343.9% more ↑ 1787.1% more
#39 GPT-5.2 Pro
OpenAI
 $0.286650 (rounded ~ $0.29) ↑ 542.7% more ↑ 2632% more
#40 GPT-5.2 Pro
OpenAI
 $0.286650 (rounded ~ $0.29) ↑ 542.7% more ↑ 2632% more
🏆

Mistral Small 3
Mistral AI

$0.000740
vs Gemini 3.1 Pro: ↓ 98.3%
vs DeepSeek V4 (Engram): ↓ 92.9%
🥈

Gemini 3.1 Flash Lite
Google

$0.002788
vs Gemini 3.1 Pro: ↓ 93.8%
vs DeepSeek V4 (Engram): ↓ 73.4%
🥉

Mistral Large 3
Mistral AI

$0.003700
vs Gemini 3.1 Pro: ↓ 91.7%
vs DeepSeek V4 (Engram): ↓ 64.7%
#4

Gemini 3.5 Flash-Lite
Google

$0.004220
vs Gemini 3.1 Pro: ↓ 90.5%
vs DeepSeek V4 (Engram): ↓ 59.8%
#5

Gemini 2.5 Flash
Google

$0.004220
vs Gemini 3.1 Pro: ↓ 90.5%
vs DeepSeek V4 (Engram): ↓ 59.8%
#6

Gemini 3.8 Flash
Google

$0.007425 (rounded ~ $0.01)
vs Gemini 3.1 Pro: ↓ 83.4%
vs DeepSeek V4 (Engram): ↓ 29.2%
#7

GPT-5.4 mini
OpenAI

$0.008363 (rounded ~ $0.01)
vs Gemini 3.1 Pro: ↓ 81.3%
vs DeepSeek V4 (Engram): ↓ 20.3%
#8

o4-mini Deep Research
OpenAI

$0.008650 (rounded ~ $0.01)
vs Gemini 3.1 Pro: ↓ 80.6%
vs DeepSeek V4 (Engram): ↓ 17.6%
#9

o4-mini
OpenAI

$0.009515
vs Gemini 3.1 Pro: ↓ 78.7%
vs DeepSeek V4 (Engram): ↓ 9.3%
#10

Claude Haiku 4.5
Anthropic

$0.009900
vs Gemini 3.1 Pro: ↓ 77.8%
vs DeepSeek V4 (Engram): ↓ 5.6%
#11

Gemini 3.1 Flash
Google

$0.011150 (rounded ~ $0.01)
vs Gemini 3.1 Pro: ↓ 75%
vs DeepSeek V4 (Engram): ↑ 6.3%
#12

GPT-5.6 Luna
OpenAI

$0.011150 (rounded ~ $0.01)
vs Gemini 3.1 Pro: ↓ 75%
vs DeepSeek V4 (Engram): ↑ 6.3%
#13

Gemini 3.6 Flash
Google

$0.014850 (rounded ~ $0.01)
vs Gemini 3.1 Pro: ↓ 66.7%
vs DeepSeek V4 (Engram): ↑ 41.5%
#14

Gemini 3.5 Flash
Google

$0.016725 (rounded ~ $0.02)
vs Gemini 3.1 Pro: ↓ 62.5%
vs DeepSeek V4 (Engram): ↑ 59.4%
#15

Claude Sonnet 5
Anthropic

$0.019800
vs Gemini 3.1 Pro: ↓ 55.6%
vs DeepSeek V4 (Engram): ↑ 88.7%
#16

GPT-5.3 Codex Spark
OpenAI

$0.023888 (rounded ~ $0.02)
vs Gemini 3.1 Pro: ↓ 46.4%
vs DeepSeek V4 (Engram): ↑ 127.7%
#17

GPT-5.3 Instant
OpenAI

$0.023888 (rounded ~ $0.02)
vs Gemini 3.1 Pro: ↓ 46.4%
vs DeepSeek V4 (Engram): ↑ 127.7%
#18

Grok 4.3
xAI

$0.024600 (rounded ~ $0.02)
vs Gemini 3.1 Pro: ↓ 44.8%
vs DeepSeek V4 (Engram): ↑ 134.5%
#19

Grok 4.20 Beta
xAI

$0.024600 (rounded ~ $0.02)
vs Gemini 3.1 Pro: ↓ 44.8%
vs DeepSeek V4 (Engram): ↑ 134.5%
#20

GPT-5.6 Terra
OpenAI

$0.027875 (rounded ~ $0.03)
vs Gemini 3.1 Pro: ↓ 37.5%
vs DeepSeek V4 (Engram): ↑ 165.7%
#21

Claude Sonnet 4.6
Anthropic

$0.029700
vs Gemini 3.1 Pro: ↓ 33.4%
vs DeepSeek V4 (Engram): ↑ 183.1%
#22

Gemini 2.5 Pro
Google

$0.034125 (rounded ~ $0.03)
vs Gemini 3.1 Pro: ↓ 23.5%
vs DeepSeek V4 (Engram): ↑ 225.2%
#23

Claude Opus 4.7
Anthropic

$0.049500
vs Gemini 3.1 Pro: ↑ 11%
vs DeepSeek V4 (Engram): ↑ 371.8%
#24

Claude Opus 5
Anthropic

$0.049500
vs Gemini 3.1 Pro: ↑ 11%
vs DeepSeek V4 (Engram): ↑ 371.8%
#25

Claude Opus 4.8
Anthropic

$0.049500
vs Gemini 3.1 Pro: ↑ 11%
vs DeepSeek V4 (Engram): ↑ 371.8%
#26

Claude Opus 4.6
Anthropic

$0.049500
vs Gemini 3.1 Pro: ↑ 11%
vs DeepSeek V4 (Engram): ↑ 371.8%
#27

GPT-5.4
OpenAI

$0.055750 (rounded ~ $0.06)
vs Gemini 3.1 Pro: ↑ 25%
vs DeepSeek V4 (Engram): ↑ 431.3%
#28

GPT-5.4 Thinking
OpenAI

$0.055750 (rounded ~ $0.06)
vs Gemini 3.1 Pro: ↑ 25%
vs DeepSeek V4 (Engram): ↑ 431.3%
#29

GPT-5.5 Instant
OpenAI

$0.055750 (rounded ~ $0.06)
vs Gemini 3.1 Pro: ↑ 25%
vs DeepSeek V4 (Engram): ↑ 431.3%
#30

GPT-5.6 Sol
OpenAI

$0.055750 (rounded ~ $0.06)
vs Gemini 3.1 Pro: ↑ 25%
vs DeepSeek V4 (Engram): ↑ 431.3%
#31

o3 Deep Research
OpenAI

$0.086500 (rounded ~ $0.09)
vs Gemini 3.1 Pro: ↑ 93.9%
vs DeepSeek V4 (Engram): ↑ 724.4%
#32

Claude Fable 5.1
Anthropic

$0.097875 (rounded ~ $0.10)
vs Gemini 3.1 Pro: ↑ 119.5%
vs DeepSeek V4 (Engram): ↑ 832.8%
#33

Claude Mythos 5.1
Anthropic

$0.097875 (rounded ~ $0.10)
vs Gemini 3.1 Pro: ↑ 119.5%
vs DeepSeek V4 (Engram): ↑ 832.8%
#34

Claude Fable 5
Anthropic

$0.099000 (rounded ~ $0.10)
vs Gemini 3.1 Pro: ↑ 122%
vs DeepSeek V4 (Engram): ↑ 843.6%
#35

Claude Mythos 5
Anthropic

$0.099000 (rounded ~ $0.10)
vs Gemini 3.1 Pro: ↑ 122%
vs DeepSeek V4 (Engram): ↑ 843.6%
#36

GPT-5.5
OpenAI

$0.111500 (rounded ~ $0.11)
vs Gemini 3.1 Pro: ↑ 150%
vs DeepSeek V4 (Engram): ↑ 962.7%
#37

o3 Pro
OpenAI

$0.173000 (rounded ~ $0.17)
vs Gemini 3.1 Pro: ↑ 287.9%
vs DeepSeek V4 (Engram): ↑ 1548.8%
#38

GPT-6 Astra
OpenAI

$0.198000 (rounded ~ $0.20)
vs Gemini 3.1 Pro: ↑ 343.9%
vs DeepSeek V4 (Engram): ↑ 1787.1%
#39

GPT-5.2 Pro
OpenAI

$0.286650 (rounded ~ $0.29)
vs Gemini 3.1 Pro: ↑ 542.7%
vs DeepSeek V4 (Engram): ↑ 2632%
#40

GPT-5.2 Pro
OpenAI

$0.286650 (rounded ~ $0.29)
vs Gemini 3.1 Pro: ↑ 542.7%
vs DeepSeek V4 (Engram): ↑ 2632%
✨ 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.

Enterprise Comparison: Processing massive RAG datasets and internal logs.

Detailed cost-performance analysis for Q2 2026.

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

Gemini 3.1 Pro currently costs $2.00 / $12.00 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 →