Mistral OCR 3 Pricing for 10,000 Scanned Pages Monthly

Complete Analysis: 10,500 tokens for Mistral OCR 3
🖼️ 10000 Images ⚡ 50% Cached

Complete analysis of pricing, performance, and use cases for Mistral AI's Mistral OCR 3 model with 10000 Images, 50% Cached.

🖼️ Multimodal Input ⚡ Caching Optimized (up to 90% savings) 📊 Batch API
$0.100000 Total Cost
10,500 Total Tokens
35.18 seconds Processing Time

Click Recalculate to update after making changes

Select AI Model

Mistral OCR 3

Mistral AIMax Context: 65,536 tokens
$2.00/1,000 pages per 1,000 pages (batch: 50% off)
50%
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
Number of pages to process. First 5k pages: $2.00/1k pages, after: $1.50/1k pages. Batch API: 50% discount applies.

Calculate Token Costs

$0.001000 Total Cost
$0.000000 Input Cost
$0.000000 Output Cost
$0.001000 Unit Cost
$0.000000 Search Cost
$0.000000 Request Fee
$0.000000 Tool Fee
$0.000000 Code Execution
10,500Total Tokens
$0.000095Cost per 1K
10,500,000Tokens per $

📊 Advanced Cost Breakdown

Processing Speed

35.18s Processing Time
300 Tokens/Second
200ms Time to First Token
300 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

📚 Research & Citations

Fee per source cited

🎤 Realtime Audio & Video

Session length for billing

Mistral OCR 3 Mistral AI

$0.100000
Total Cost
🖼️ 10000 Image (Medium) ⚡ 50% Cached 📊 Batch API
👁️
Vision/Images
✓ Available
🎧
Audio Processing
✗ Not Available
🎥
Video Analysis
✗ Not Available
🔧
Tool Usage
✗ Not Available
📄
OCR Support
✓ Available
📊
Batch API
✓ Available
⚡
Caching
✗ Not Available

💰 Total Cost Calculation (from Plugin)

Base Cost (No Optimizations) $0.200000 Input: $0.000000
Output: $0.000000
Optimized Cost $0.100000 Input: $0.000000
Output: $0.000000
Unit: $0.100000
Fees: $0.000000
Total Savings $0.100000 50.0% discount

Advanced Cost Breakdown (from Plugin)

📄 OCR Processing
$0.200000
100 pages
📊 Batch API
50.0% off
Asynchronous processing discount

Detailed Cost Analysis (from Plugin)

For 10,000 input tokens and 500 output tokens:

  • Input Cost: $0.000000
  • Output Cost: $0.000000
  • Unit Cost: $0.100000
  • Total Cost: $0.100000
  • Cost per 1K tokens: $0.009524
  • Tokens per dollar: 105,000 tokens
  • Context Window: 65536 tokens
  • Thinking Source: (0 tokens)

Speed & Performance Analysis

With a processing speed of 300 tokens per second and 200ms time to first token:

  • Processing Time: 35.18 seconds
  • Latency: 200 milliseconds to first token
  • Base Throughput: 300 tokens/second

Best Use Cases

Ideal for high-volumestructural document digitization where maintaining layout fidelity and archival searchability are the primary requirements.

Want this applied to YOUR actual stack?

This calculator shows the math for Mistral OCR 3. 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 Mistral OCR 3
📋 Active Input Parameters
Input Tokens: 10,000
Output Tokens: 500
Batch API: Enabled (50% discount)
Cached Tokens: 50%
Images: 10000 (Medium Resolution)
Rank AI Model & Provider Total Cost vs Mistral OCR 3
🏆 Ministral 3 (14B)
Mistral AI
 $0.142300 (rounded ~ $0.14) Best Value ↑ 42.3% more
🥈 GPT-5.6 Luna
OpenAI
 $0.142325 (rounded ~ $0.14) ↑ 42.3% more
🥉 Gemini 3.1 Flash Lite
Google
 $0.177906 (rounded ~ $0.18) ↑ 77.9% more
#4 Gemini 3.5 Flash-Lite
Google
 $0.213575 (rounded ~ $0.21) ↑ 113.6% more
#5 Gemini 2.5 Flash
Google
 $0.213575 (rounded ~ $0.21) ↑ 113.6% more
#6 GPT-6 Luna
OpenAI
 $0.284538 (rounded ~ $0.28) ↑ 184.5% more
#7 Mistral Large 3
Mistral AI
 $0.355875 (rounded ~ $0.36) ↑ 255.9% more
#8 Gemini 3.8 Flash
Google
 $0.533625 (rounded ~ $0.53) ↑ 433.6% more
#9 Gemini 3.6 Flash
Google
 $0.533625 (rounded ~ $0.53) ↑ 433.6% more
#10 GPT-5.4 mini
OpenAI
 $0.533719 (rounded ~ $0.53) ↑ 433.7% more
#11 Claude Haiku 5.5
Anthropic
 $0.711500 (rounded ~ $0.71) ↑ 611.5% more
#12 Claude Haiku 4.5
Anthropic
 $0.711500 (rounded ~ $0.71) ↑ 611.5% more
#13 Mistral Large 4
Mistral AI
 $0.967993 (rounded ~ $0.97) ↑ 868% more
#14 GPT-5.3 Codex Spark
OpenAI
 $1.245781 (rounded ~ $1.25) ↑ 1145.8% more
#15 GPT-5.3 Instant
OpenAI
 $1.245781 (rounded ~ $1.25) ↑ 1145.8% more
#16 Claude Sonnet 5.5
Anthropic
 $1.358375 (rounded ~ $1.36) ↑ 1258.4% more
#17 Gemini 4 Argon
Google
 $1.423000 (rounded ~ $1.42) ↑ 1323% more
#18 Claude Sonnet 5
Anthropic
 $1.423000 (rounded ~ $1.42) ↑ 1323% more
#19 Gemini 3.1 Flash
Google
 $1.423250 (rounded ~ $1.42) ↑ 1323.3% more
#20 GPT-5.6 Terra
OpenAI
 $1.423250 (rounded ~ $1.42) ↑ 1323.3% more
#21 Claude Sonnet 4.6
Anthropic
 $2.134500 (rounded ~ $2.13) ↑ 2034.5% more
#22 Claude Opus 5.5
Anthropic
 $2.716750 (rounded ~ $2.72) ↑ 2616.8% more
#23 GPT-5.6 Sol
OpenAI
 $2.846000 (rounded ~ $2.85) ↑ 2746% more
#24 Claude Opus 4.7
Anthropic
 $3.557500 (rounded ~ $3.56) ↑ 3457.5% more
#25 Claude Opus 5
Anthropic
 $3.557500 (rounded ~ $3.56) ↑ 3457.5% more
#26 Claude Opus 4.8
Anthropic
 $3.557500 (rounded ~ $3.56) ↑ 3457.5% more
#27 Claude Opus 4.6
Anthropic
 $3.557500 (rounded ~ $3.56) ↑ 3457.5% more
#28 Gemini 2.5 Pro
Google
 $3.558125 (rounded ~ $3.56) ↑ 3458.1% more
#29 GPT-5.5 Instant
OpenAI
 $3.558125 (rounded ~ $3.56) ↑ 3458.1% more
#30 Grok 4.3
xAI
 $5.689000 (rounded ~ $5.69) ↑ 5589% more
#31 GPT-6.1 Sol
OpenAI
 $5.690750 ↑ 5590.8% more
#32 GPT-6 Sol
OpenAI
 $5.690750 ↑ 5590.8% more
#33 Gemini 3.1 Pro
Google
 $5.691500 (rounded ~ $5.69) ↑ 5591.5% more
#34 Claude Fable 5.1
Anthropic
 $6.630313 ↑ 6530.3% more
#35 Claude Mythos 5.1
Anthropic
 $6.630313 ↑ 6530.3% more
#36 GPT-5.4
OpenAI
 $7.114375 (rounded ~ $7.11) ↑ 7014.4% more
#37 GPT-5.4 Thinking
OpenAI
 $7.114375 (rounded ~ $7.11) ↑ 7014.4% more
#38 Claude Fable 5
Anthropic
 $7.115000 (rounded ~ $7.12) ↑ 7015% more
#39 Claude Mythos 5
Anthropic
 $7.115000 (rounded ~ $7.12) ↑ 7015% more
#40 GPT-5.5
OpenAI
 $14.228750 (rounded ~ $14.23) ↑ 14128.8% more
#41 GPT-5.2 Pro
OpenAI
 $14.949375 ↑ 14849.4% more
#42 GPT-6 Astra
OpenAI
 $28.460000 ↑ 28360% more
#43 GPT-6 Astra
OpenAI
 $28.460000 ↑ 28360% more
🏆

Ministral 3 (14B)
Mistral AI

$0.142300 (rounded ~ $0.14)
vs Mistral OCR 3: ↑ 42.3%
🥈

GPT-5.6 Luna
OpenAI

$0.142325 (rounded ~ $0.14)
vs Mistral OCR 3: ↑ 42.3%
🥉

Gemini 3.1 Flash Lite
Google

$0.177906 (rounded ~ $0.18)
vs Mistral OCR 3: ↑ 77.9%
#4

Gemini 3.5 Flash-Lite
Google

$0.213575 (rounded ~ $0.21)
vs Mistral OCR 3: ↑ 113.6%
#5

Gemini 2.5 Flash
Google

$0.213575 (rounded ~ $0.21)
vs Mistral OCR 3: ↑ 113.6%
#6

GPT-6 Luna
OpenAI

$0.284538 (rounded ~ $0.28)
vs Mistral OCR 3: ↑ 184.5%
#7

Mistral Large 3
Mistral AI

$0.355875 (rounded ~ $0.36)
vs Mistral OCR 3: ↑ 255.9%
#8

Gemini 3.8 Flash
Google

$0.533625 (rounded ~ $0.53)
vs Mistral OCR 3: ↑ 433.6%
#9

Gemini 3.6 Flash
Google

$0.533625 (rounded ~ $0.53)
vs Mistral OCR 3: ↑ 433.6%
#10

GPT-5.4 mini
OpenAI

$0.533719 (rounded ~ $0.53)
vs Mistral OCR 3: ↑ 433.7%
#11

Claude Haiku 5.5
Anthropic

$0.711500 (rounded ~ $0.71)
vs Mistral OCR 3: ↑ 611.5%
#12

Claude Haiku 4.5
Anthropic

$0.711500 (rounded ~ $0.71)
vs Mistral OCR 3: ↑ 611.5%
#13

Mistral Large 4
Mistral AI

$0.967993 (rounded ~ $0.97)
vs Mistral OCR 3: ↑ 868%
#14

GPT-5.3 Codex Spark
OpenAI

$1.245781 (rounded ~ $1.25)
vs Mistral OCR 3: ↑ 1145.8%
#15

GPT-5.3 Instant
OpenAI

$1.245781 (rounded ~ $1.25)
vs Mistral OCR 3: ↑ 1145.8%
#16

Claude Sonnet 5.5
Anthropic

$1.358375 (rounded ~ $1.36)
vs Mistral OCR 3: ↑ 1258.4%
#17

Gemini 4 Argon
Google

$1.423000 (rounded ~ $1.42)
vs Mistral OCR 3: ↑ 1323%
#18

Claude Sonnet 5
Anthropic

$1.423000 (rounded ~ $1.42)
vs Mistral OCR 3: ↑ 1323%
#19

Gemini 3.1 Flash
Google

$1.423250 (rounded ~ $1.42)
vs Mistral OCR 3: ↑ 1323.3%
#20

GPT-5.6 Terra
OpenAI

$1.423250 (rounded ~ $1.42)
vs Mistral OCR 3: ↑ 1323.3%
#21

Claude Sonnet 4.6
Anthropic

$2.134500 (rounded ~ $2.13)
vs Mistral OCR 3: ↑ 2034.5%
#22

Claude Opus 5.5
Anthropic

$2.716750 (rounded ~ $2.72)
vs Mistral OCR 3: ↑ 2616.8%
#23

GPT-5.6 Sol
OpenAI

$2.846000 (rounded ~ $2.85)
vs Mistral OCR 3: ↑ 2746%
#24

Claude Opus 4.7
Anthropic

$3.557500 (rounded ~ $3.56)
vs Mistral OCR 3: ↑ 3457.5%
#25

Claude Opus 5
Anthropic

$3.557500 (rounded ~ $3.56)
vs Mistral OCR 3: ↑ 3457.5%
#26

Claude Opus 4.8
Anthropic

$3.557500 (rounded ~ $3.56)
vs Mistral OCR 3: ↑ 3457.5%
#27

Claude Opus 4.6
Anthropic

$3.557500 (rounded ~ $3.56)
vs Mistral OCR 3: ↑ 3457.5%
#28

Gemini 2.5 Pro
Google

$3.558125 (rounded ~ $3.56)
vs Mistral OCR 3: ↑ 3458.1%
#29

GPT-5.5 Instant
OpenAI

$3.558125 (rounded ~ $3.56)
vs Mistral OCR 3: ↑ 3458.1%
#30

Grok 4.3
xAI

$5.689000 (rounded ~ $5.69)
vs Mistral OCR 3: ↑ 5589%
#31

GPT-6.1 Sol
OpenAI

$5.690750
vs Mistral OCR 3: ↑ 5590.8%
#32

GPT-6 Sol
OpenAI

$5.690750
vs Mistral OCR 3: ↑ 5590.8%
#33

Gemini 3.1 Pro
Google

$5.691500 (rounded ~ $5.69)
vs Mistral OCR 3: ↑ 5591.5%
#34

Claude Fable 5.1
Anthropic

$6.630313
vs Mistral OCR 3: ↑ 6530.3%
#35

Claude Mythos 5.1
Anthropic

$6.630313
vs Mistral OCR 3: ↑ 6530.3%
#36

GPT-5.4
OpenAI

$7.114375 (rounded ~ $7.11)
vs Mistral OCR 3: ↑ 7014.4%
#37

GPT-5.4 Thinking
OpenAI

$7.114375 (rounded ~ $7.11)
vs Mistral OCR 3: ↑ 7014.4%
#38

Claude Fable 5
Anthropic

$7.115000 (rounded ~ $7.12)
vs Mistral OCR 3: ↑ 7015%
#39

Claude Mythos 5
Anthropic

$7.115000 (rounded ~ $7.12)
vs Mistral OCR 3: ↑ 7015%
#40

GPT-5.5
OpenAI

$14.228750 (rounded ~ $14.23)
vs Mistral OCR 3: ↑ 14128.8%
#41

GPT-5.2 Pro
OpenAI

$14.949375
vs Mistral OCR 3: ↑ 14849.4%
#42

GPT-6 Astra
OpenAI

$28.460000
vs Mistral OCR 3: ↑ 28360%
#43

GPT-6 Astra
OpenAI

$28.460000
vs Mistral OCR 3: ↑ 28360%
✨ 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 Legacy Archive Digitization

Legacy archives often contain handwritten notes, faded ink, or complex structural layouts that challenge standard OCR engines. When digitizing 10,000 pages monthly, the decision rests on balancing raw throughput against the semantic understanding required to index the data properly for enterprise search.

Mistral OCR 3 is specifically tuned for document structure, making it a specialized choice for archival workflows. Unlike general-purpose vision models that might hallucinate content in low-contrast scans, this model is designed to maintain high fidelity to the original source layout. It is particularly effective for teams that need to preserve metadata, tables, and multi-column formatting alongside text extraction.

However, for archives requiring deep interpretation—such as summarizing handwritten correspondence or identifying historical context—general-purpose reasoning models often provide better results. These models excel at handling irregular handwriting and non-standard form structures that might stump a dedicated OCR engine. Choosing between them depends on whether your priority is rigid structural preservation or semantic enrichment.

Technical writers should consider the downstream integration requirements carefully. If your primary goal is converting images to searchable text for a database, specialized models offer efficient processing. If you need to transform messy, historical logs into clean, structured JSON reports, the reasoning capabilities of a larger frontier model may save engineering hours in the long run. Evaluate the trade-off between structural fidelity and the ability to infer context from damaged documents before committing to a long-term archival pipeline.

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

Mistral OCR 3 currently costs $0.00 / $0.00 per 1M tokens. These are the models worth pricing against it, taken live from the tracked registry.

Other models from the same provider

See every tracked AI pricing change →