Document Analysis at Scale: Gemini 3.1 Pro for 1 Million Monthly Real Estate PDF Extractions

Complete Analysis: 516,100,500 tokens for Gemini 3.1 Pro
🖼️ 1000000 Images ⚡ 90% Cached

Complete analysis of pricing, performance, and use cases for Google's Gemini 3.1 Pro model with 1000000 Images, 90% Cached.

🖼️ Multimodal Input ⚡ Caching Optimized (up to 90% savings) 📊 Batch API
$196.122500 (rounded ~ $196.12) Total Cost
516,100,500 Total Tokens
365 hours, 34 minutes, 16.46 seconds Processing Time
392 Effective Tokens/Sec

Click Recalculate to update after making changes

ℹ️ Bulk Calculation: Total volume exceeds single-request limit of 1,000,000 tokens. Budgeting mode active.

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)
90%
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.
Will auto-convert to minutes for Voxtral models (9000 tokens = 1 min)
$0.067 per 1,000 pixels

Calculate Token Costs

$196.122500 Total Cost
$103.220000 Input Cost
$0.004500 Output Cost
$0.000000 Unit Cost
$0.000000 Search Cost
$0.000000 Request Fee
$0.000000 Tool Fee
$0.000000 Code Execution
516,100,500Total Tokens
$0.000380Cost per 1K
2,631,521Tokens per $
🔄 Dynamic Tier Pricing Active: Using Premium pricing (tier2) based on token volume.
📊 Advanced Cost Breakdown

Processing Speed

21934m 16s Processing Time
400 Tokens/Second
220ms Time to First Token
392 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

Gemini 3.1 Pro Google 1000000

$196.122500 (rounded ~ $196.12)
Total Cost
⚠️ Bulk Calculation: Total volume exceeds single-request limit of 1,000,000 tokens. Budgeting mode active.
🖼️ 1000000 Image (Medium) ⚡ 90% Cached 📊 Batch API
👁️
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) $1032.204500 (rounded ~ $1,032.20) Input: $1032.200000
Output: $0.004500
Optimized Cost $196.122500 (rounded ~ $196.12) Input: $1032.200000
Output: $0.004500
Unit: $0.000000
Fees: $0.000000
Total Savings $836.082000 (rounded ~ $836.08) 81.0% discount

Advanced Cost Breakdown (from Plugin)

🖼️ Multimodal Input
$0.000000
516,000,000 tokens
📊 Batch API
50.0% off
Asynchronous processing discount
📊 Dynamic Tier
Premium
tier2 pricing based on 0 tokens

Multimodal Input Details

🖼️ Images
Count: 1000000
Resolution: Medium
Tokens: 516,000,000
Cost: $0.000000

Detailed Cost Analysis (from Plugin)

For 100,000 input tokens and 500 output tokens:

  • Input Cost: $1032.200000
  • Output Cost: $0.004500
  • Total Cost: $196.122500 (rounded ~ $196.12)
  • Cost per 1K tokens: $0.000380
  • Tokens per dollar: 2,631,521 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: 365 hours, 34 minutes, 16.46 seconds
  • Latency: 220 milliseconds to first token
  • Base Throughput: 400 tokens/second
  • Effective Throughput: 392 tokens/second (temperature-adjusted)

Best Use Cases

Ideal for enterprise document processing requiring native vision/OCR and large-scale synthesis of unstructured data.

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 →

✨ Market Recommendations AI Model Registry

← Back to Gemini 3.1 Pro
📋 Active Input Parameters
Input Tokens: 100,000
Output Tokens: 500
Batch API: Enabled (50% discount)
Cached Tokens: 90%
Images: 1000000 (Medium Resolution)
Rank AI Model & Provider Total Cost vs Gemini 3.1 Pro
🏆 Mistral Small 3
Mistral AI
 $2.451513 (rounded ~ $2.45) Best Value ↓ 98.8% cheaper
🥈 Gemini 3.1 Flash Lite
Google
 $6.128875 (rounded ~ $6.13) ↓ 96.9% cheaper
🥉 Gemini 3.5 Flash-Lite
Google
 $7.354738 (rounded ~ $7.35) ↓ 96.2% cheaper
#4 Gemini 2.5 Flash
Google
 $7.354738 (rounded ~ $7.35) ↓ 96.2% cheaper
#5 Mistral Large 3
Mistral AI
 $12.257813 (rounded ~ $12.26) ↓ 93.7% cheaper
#6 Gemini 3.8 Flash
Google
 $18.386531 (rounded ~ $18.39) ↓ 90.6% cheaper
#7 GPT-5.4 mini
OpenAI
 $18.386625 (rounded ~ $18.39) ↓ 90.6% cheaper
#8 o4-mini Deep Research
OpenAI
 $24.515250 (rounded ~ $24.52) ↓ 87.5% cheaper
#9 Claude Haiku 4.5
Anthropic
 $24.515375 (rounded ~ $24.52) ↓ 87.5% cheaper
#10 GPT-5.6 Luna
OpenAI
 $24.515500 (rounded ~ $24.52) ↓ 87.5% cheaper
#11 o4-mini
OpenAI
 $26.966775 (rounded ~ $26.97) ↓ 86.3% cheaper
#12 Gemini 3.6 Flash
Google
 $36.773063 (rounded ~ $36.77) ↓ 81.2% cheaper
#13 Gemini 3.5 Flash
Google
 $36.773250 (rounded ~ $36.77) ↓ 81.2% cheaper
#14 GPT-5.3 Codex Spark
OpenAI
 $42.902563 (rounded ~ $42.90) ↓ 78.1% cheaper
#15 GPT-5.3 Instant
OpenAI
 $42.902563 (rounded ~ $42.90) ↓ 78.1% cheaper
#16 Claude Sonnet 5
Anthropic
 $49.030750 ↓ 75% cheaper
#17 Gemini 3.1 Flash
Google
 $49.031000 ↓ 75% cheaper
#18 GPT-5.6 Terra
OpenAI
 $61.288750 (rounded ~ $61.29) ↓ 68.7% cheaper
#19 Claude Sonnet 4.6
Anthropic
 $73.546125 (rounded ~ $73.55) ↓ 62.5% cheaper
#20 Claude Opus 4.7
Anthropic
 $122.576875 (rounded ~ $122.58) ↓ 37.5% cheaper
#21 Claude Opus 5
Anthropic
 $122.576875 (rounded ~ $122.58) ↓ 37.5% cheaper
#22 Claude Opus 4.8
Anthropic
 $122.576875 (rounded ~ $122.58) ↓ 37.5% cheaper
#23 Claude Opus 4.6
Anthropic
 $122.576875 (rounded ~ $122.58) ↓ 37.5% cheaper
#24 Gemini 2.5 Pro
Google
 $122.577500 (rounded ~ $122.58) ↓ 37.5% cheaper
#25 GPT-5.5 Instant
OpenAI
 $122.577500 (rounded ~ $122.58) ↓ 37.5% cheaper
#26 GPT-5.6 Sol
OpenAI
 $122.577500 (rounded ~ $122.58) ↓ 37.5% cheaper
#27 Claude Fable 5.1
Anthropic
 $158.061875 (rounded ~ $158.06) ↓ 19.4% cheaper
#28 Claude Mythos 5.1
Anthropic
 $158.061875 (rounded ~ $158.06) ↓ 19.4% cheaper
#29 Grok 4.3
xAI
 $196.120000 ↓ 0% cheaper
#30 o3 Deep Research
OpenAI
 $245.152500 (rounded ~ $245.15) ↑ 25% more
#31 GPT-5.4
OpenAI
 $245.153125 (rounded ~ $245.15) ↑ 25% more
#32 GPT-5.4 Thinking
OpenAI
 $245.153125 (rounded ~ $245.15) ↑ 25% more
#33 Claude Fable 5
Anthropic
 $245.153750 (rounded ~ $245.15) ↑ 25% more
#34 Claude Mythos 5
Anthropic
 $245.153750 (rounded ~ $245.15) ↑ 25% more
#35 o3 Pro
OpenAI
 $490.305000 (rounded ~ $490.31) ↑ 150% more
#36 GPT-5.5
OpenAI
 $490.306250 (rounded ~ $490.31) ↑ 150% more
#37 GPT-5.2 Pro
OpenAI
 $514.830750 ↑ 162.5% more
#38 GPT-6 Astra
OpenAI
 $980.615000 (rounded ~ $980.62) ↑ 400% more
#39 GPT-6 Astra
OpenAI
 $980.615000 (rounded ~ $980.62) ↑ 400% more
🏆

Mistral Small 3
Mistral AI

$2.451513 (rounded ~ $2.45)
vs Gemini 3.1 Pro: ↓ 98.8%
🥈

Gemini 3.1 Flash Lite
Google

$6.128875 (rounded ~ $6.13)
vs Gemini 3.1 Pro: ↓ 96.9%
🥉

Gemini 3.5 Flash-Lite
Google

$7.354738 (rounded ~ $7.35)
vs Gemini 3.1 Pro: ↓ 96.2%
#4

Gemini 2.5 Flash
Google

$7.354738 (rounded ~ $7.35)
vs Gemini 3.1 Pro: ↓ 96.2%
#5

Mistral Large 3
Mistral AI

$12.257813 (rounded ~ $12.26)
vs Gemini 3.1 Pro: ↓ 93.7%
#6

Gemini 3.8 Flash
Google

$18.386531 (rounded ~ $18.39)
vs Gemini 3.1 Pro: ↓ 90.6%
#7

GPT-5.4 mini
OpenAI

$18.386625 (rounded ~ $18.39)
vs Gemini 3.1 Pro: ↓ 90.6%
#8

o4-mini Deep Research
OpenAI

$24.515250 (rounded ~ $24.52)
vs Gemini 3.1 Pro: ↓ 87.5%
#9

Claude Haiku 4.5
Anthropic

$24.515375 (rounded ~ $24.52)
vs Gemini 3.1 Pro: ↓ 87.5%
#10

GPT-5.6 Luna
OpenAI

$24.515500 (rounded ~ $24.52)
vs Gemini 3.1 Pro: ↓ 87.5%
#11

o4-mini
OpenAI

$26.966775 (rounded ~ $26.97)
vs Gemini 3.1 Pro: ↓ 86.3%
#12

Gemini 3.6 Flash
Google

$36.773063 (rounded ~ $36.77)
vs Gemini 3.1 Pro: ↓ 81.2%
#13

Gemini 3.5 Flash
Google

$36.773250 (rounded ~ $36.77)
vs Gemini 3.1 Pro: ↓ 81.2%
#14

GPT-5.3 Codex Spark
OpenAI

$42.902563 (rounded ~ $42.90)
vs Gemini 3.1 Pro: ↓ 78.1%
#15

GPT-5.3 Instant
OpenAI

$42.902563 (rounded ~ $42.90)
vs Gemini 3.1 Pro: ↓ 78.1%
#16

Claude Sonnet 5
Anthropic

$49.030750
vs Gemini 3.1 Pro: ↓ 75%
#17

Gemini 3.1 Flash
Google

$49.031000
vs Gemini 3.1 Pro: ↓ 75%
#18

GPT-5.6 Terra
OpenAI

$61.288750 (rounded ~ $61.29)
vs Gemini 3.1 Pro: ↓ 68.7%
#19

Claude Sonnet 4.6
Anthropic

$73.546125 (rounded ~ $73.55)
vs Gemini 3.1 Pro: ↓ 62.5%
#20

Claude Opus 4.7
Anthropic

$122.576875 (rounded ~ $122.58)
vs Gemini 3.1 Pro: ↓ 37.5%
#21

Claude Opus 5
Anthropic

$122.576875 (rounded ~ $122.58)
vs Gemini 3.1 Pro: ↓ 37.5%
#22

Claude Opus 4.8
Anthropic

$122.576875 (rounded ~ $122.58)
vs Gemini 3.1 Pro: ↓ 37.5%
#23

Claude Opus 4.6
Anthropic

$122.576875 (rounded ~ $122.58)
vs Gemini 3.1 Pro: ↓ 37.5%
#24

Gemini 2.5 Pro
Google

$122.577500 (rounded ~ $122.58)
vs Gemini 3.1 Pro: ↓ 37.5%
#25

GPT-5.5 Instant
OpenAI

$122.577500 (rounded ~ $122.58)
vs Gemini 3.1 Pro: ↓ 37.5%
#26

GPT-5.6 Sol
OpenAI

$122.577500 (rounded ~ $122.58)
vs Gemini 3.1 Pro: ↓ 37.5%
#27

Claude Fable 5.1
Anthropic

$158.061875 (rounded ~ $158.06)
vs Gemini 3.1 Pro: ↓ 19.4%
#28

Claude Mythos 5.1
Anthropic

$158.061875 (rounded ~ $158.06)
vs Gemini 3.1 Pro: ↓ 19.4%
#29

Grok 4.3
xAI

$196.120000
vs Gemini 3.1 Pro: ↓ 0%
#30

o3 Deep Research
OpenAI

$245.152500 (rounded ~ $245.15)
vs Gemini 3.1 Pro: ↑ 25%
#31

GPT-5.4
OpenAI

$245.153125 (rounded ~ $245.15)
vs Gemini 3.1 Pro: ↑ 25%
#32

GPT-5.4 Thinking
OpenAI

$245.153125 (rounded ~ $245.15)
vs Gemini 3.1 Pro: ↑ 25%
#33

Claude Fable 5
Anthropic

$245.153750 (rounded ~ $245.15)
vs Gemini 3.1 Pro: ↑ 25%
#34

Claude Mythos 5
Anthropic

$245.153750 (rounded ~ $245.15)
vs Gemini 3.1 Pro: ↑ 25%
#35

o3 Pro
OpenAI

$490.305000 (rounded ~ $490.31)
vs Gemini 3.1 Pro: ↑ 150%
#36

GPT-5.5
OpenAI

$490.306250 (rounded ~ $490.31)
vs Gemini 3.1 Pro: ↑ 150%
#37

GPT-5.2 Pro
OpenAI

$514.830750
vs Gemini 3.1 Pro: ↑ 162.5%
#38

GPT-6 Astra
OpenAI

$980.615000 (rounded ~ $980.62)
vs Gemini 3.1 Pro: ↑ 400%
#39

GPT-6 Astra
OpenAI

$980.615000 (rounded ~ $980.62)
vs Gemini 3.1 Pro: ↑ 400%
✨ 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.

Scaling document processing for a large real estate operation involves more than just text extraction; it requires deep visual understanding to interpret property surveys, structural diagrams, and handwritten annotation on contracts. Gemini 3.1 Pro stands out in this high-volume category due to its natively multimodal architecture. Unlike systems that rely on separate OCR and language models, Gemini 3.1 Pro processes text, imagery, and structural layout information simultaneously, leading to significantly higher extraction accuracy on dense, non-standardized documents.

For enterprise teams managing workflows that reach 1 million documents monthly, Gemini 3.1 Pro provides unique advantages in latency and integration. Its ability to synthesize vast amounts of information—bringing disparate data points from hundreds of pages into a single structured format—simplifies the upstream data pipeline. If your infrastructure relies on Google Cloud, the model’s native integration with Vertex AI further streamlines deployment, offering robust governance and compliance features that are essential when handling sensitive client information at scale.

When choosing this model for your document extraction pipeline, consider the value of native multimodality. By eliminating the need for an external OCR pre-processing step, you remove a major failure point in your pipeline. Gemini 3.1 Pro is particularly effective for teams that need to not only extract data but also reason about it—such as identifying discrepancies between a property’s floor plan and its official permit records automatically.

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 are image tokens calculated?
Images are tokenized based on resolution: Low: 85 tokens, Medium: 170 tokens, High: 255 tokens, Full: 765 tokens per image. Some models (like Llama 4 Maverick) use tile-based encoding with 1,610 tokens/image (standard) or 8,050 tokens/image (high-res).
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 →