Per-Unit Benchmark: 100K Tokens of Archive Correction with o4-mini

Complete Analysis: 105,000 tokens for o4-mini
⚡ 50% Cached

Complete analysis of pricing, performance, and use cases for OpenAI's o4-mini model with 50% Cached.

⚡ Caching Optimized (up to 90% savings) 📊 Batch API
$0.020625 Total Cost
105,000 Total Tokens
10 minutes, 6.85 seconds Processing Time
173 Effective Tokens/Sec

Click Recalculate to update after making changes

Select AI Model

o4-mini
OpenAIMax Context: 200,000 tokens
$1.1 / $4.4 per 1M tokens
▼
▼
Use Batch API (50% discount)
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.

Calculate Token Costs

$0.020625 Total Cost
$0.013750 Input Cost
$0.005500 Output Cost
$0.000000 Unit Cost
$0.000000 Search Cost
$0.000000 Request Fee
$0.000000 Tool Fee
$0.000000 Code Execution
105,000Total Tokens
$0.000196Cost per 1K
5,090,909Tokens per $
📊 Advanced Cost Breakdown

Processing Speed

10m 6s Processing Time
180 Tokens/Second
280ms Time to First Token
173 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

o4-mini OpenAI

$0.020625
Total Cost
⚡ 50% Cached 📊 Batch API
👁️
Vision/Images
✓ Available
🎧
Audio Processing
✗ Not Available
🎥
Video Analysis
✗ Not Available
🔧
Tool Usage
✓ Available
📄
OCR Support
✗ Not Available
📊
Batch API
✓ Available
⚡
Caching
✓ Available
90% savings

💰 Total Cost Calculation (from Plugin)

Base Cost (No Optimizations) $0.033000 (rounded ~ $0.03) Input: $0.027500 (rounded ~ $0.03)
Output: $0.005500 (rounded ~ $0.01)
Optimized Cost $0.020625 Input: $0.027500 (rounded ~ $0.03)
Output: $0.005500 (rounded ~ $0.01)
Unit: $0.000000
Fees: $0.000000
Total Savings $0.012375 (rounded ~ $0.01) 37.5% discount

Advanced Cost Breakdown (from Plugin)

📊 Batch API
50.0% off
Asynchronous processing discount

Detailed Cost Analysis (from Plugin)

For 100,000 input tokens and 5,000 output tokens:

  • Input Cost: $0.027500 (rounded ~ $0.03)
  • Output Cost: $0.005500 (rounded ~ $0.01)
  • Total Cost: $0.020625
  • Cost per 1K tokens: $0.000196
  • Tokens per dollar: 5,090,909 tokens
  • Context Window: 200000 tokens

Speed & Performance Analysis

With a processing speed of 180 tokens per second and 280ms time to first token:

  • Processing Time: 10 minutes, 6.85 seconds
  • Latency: 280 milliseconds to first token
  • Base Throughput: 180 tokens/second
  • Effective Throughput: 173 tokens/second (temperature-adjusted)

Best Use Cases

Reasoning-heavy correction of OCR errors and normalization of historical archival text.

Want this applied to YOUR actual stack?

This calculator shows the math for o4-mini. 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 o4-mini
📋 Active Input Parameters
Input Tokens: 100,000
Output Tokens: 5,000
Batch API: Enabled (50% discount)
Cached Tokens: 50%
Rank AI Model & Provider Total Cost vs o4-mini
🏆 Mistral Small 3
Mistral AI
 $0.001750 Best Value ↓ 91.5% cheaper
🥈 Devstral Small 2
Mistral AI
 $0.001750 ↓ 91.5% cheaper
🥉 Grok Code Fast 1
xAI
 $0.004625 ↓ 77.6% cheaper
#4 Nemotron 3 Super
Mistral AI
 $0.005150 (rounded ~ $0.01) ↓ 75% cheaper
#5 Gemini 3.1 Flash Lite
Google
 $0.005313 (rounded ~ $0.01) ↓ 74.2% cheaper
#6 Devstral 2
Mistral AI
 $0.006625 (rounded ~ $0.01) ↓ 67.9% cheaper
#7 Gemini 2.5 Flash
Google
 $0.007250 (rounded ~ $0.01) ↓ 64.8% cheaper
#8 Mistral Large 3
Mistral AI
 $0.008750 (rounded ~ $0.01) ↓ 57.6% cheaper
#9 GPT-5.4 mini
OpenAI
 $0.015938 (rounded ~ $0.02) ↓ 22.7% cheaper
#10 o4-mini Deep Research
OpenAI
 $0.018750 (rounded ~ $0.02) ↓ 9.1% cheaper
#11 Claude Haiku 4.5
Anthropic
 $0.020000 ↓ 3% cheaper
#12 Grok 4.3
xAI
 $0.020313 ↓ 1.5% cheaper
#13 Gemini 3.1 Flash
Google
 $0.021250 (rounded ~ $0.02) ↑ 3% more
#14 Gemini 3.5 Flash
Google
 $0.031875 (rounded ~ $0.03) ↑ 54.5% more
#15 Magistral Medium
Mistral AI
 $0.033750 (rounded ~ $0.03) ↑ 63.6% more
#16 Grok 4.20 Beta
xAI
 $0.035000 (rounded ~ $0.04) ↑ 69.7% more
#17 GPT-5.3 Codex Spark
OpenAI
 $0.041563 (rounded ~ $0.04) ↑ 101.5% more
#18 GPT-5.3 Instant
OpenAI
 $0.041563 (rounded ~ $0.04) ↑ 101.5% more
#19 Gemini 2.5 Pro
Google
 $0.059375 ↑ 187.9% more
#20 Claude Sonnet 4.6
Anthropic
 $0.060000 ↑ 190.9% more
#21 Gemini 3.1 Pro
Google
 $0.085000 (rounded ~ $0.09) ↑ 312.1% more
#22 Claude Opus 4.7
Anthropic
 $0.100000 ↑ 384.8% more
#23 Claude Opus 4.8
Anthropic
 $0.100000 ↑ 384.8% more
#24 Claude Opus 4.6
Anthropic
 $0.100000 ↑ 384.8% more
#25 GPT-5.4
OpenAI
 $0.106250 (rounded ~ $0.11) ↑ 415.2% more
#26 GPT-5.4 Thinking
OpenAI
 $0.106250 (rounded ~ $0.11) ↑ 415.2% more
#27 GPT-5.5 Instant
OpenAI
 $0.106250 (rounded ~ $0.11) ↑ 415.2% more
#28 o3 Deep Research
OpenAI
 $0.187500 (rounded ~ $0.19) ↑ 809.1% more
#29 GPT-5.5
OpenAI
 $0.212500 (rounded ~ $0.21) ↑ 930.3% more
#30 o3 Pro
OpenAI
 $0.375000 (rounded ~ $0.38) ↑ 1718.2% more
#31 GPT-5.2 Pro
OpenAI
 $0.498750 (rounded ~ $0.50) ↑ 2318.2% more
#32 GPT-5.2 Pro
OpenAI
 $0.498750 (rounded ~ $0.50) ↑ 2318.2% more
🏆

Mistral Small 3
Mistral AI

$0.001750
vs o4-mini: ↓ 91.5%
🥈

Devstral Small 2
Mistral AI

$0.001750
vs o4-mini: ↓ 91.5%
🥉

Grok Code Fast 1
xAI

$0.004625
vs o4-mini: ↓ 77.6%
#4

Nemotron 3 Super
Mistral AI

$0.005150 (rounded ~ $0.01)
vs o4-mini: ↓ 75%
#5

Gemini 3.1 Flash Lite
Google

$0.005313 (rounded ~ $0.01)
vs o4-mini: ↓ 74.2%
#6

Devstral 2
Mistral AI

$0.006625 (rounded ~ $0.01)
vs o4-mini: ↓ 67.9%
#7

Gemini 2.5 Flash
Google

$0.007250 (rounded ~ $0.01)
vs o4-mini: ↓ 64.8%
#8

Mistral Large 3
Mistral AI

$0.008750 (rounded ~ $0.01)
vs o4-mini: ↓ 57.6%
#9

GPT-5.4 mini
OpenAI

$0.015938 (rounded ~ $0.02)
vs o4-mini: ↓ 22.7%
#10

o4-mini Deep Research
OpenAI

$0.018750 (rounded ~ $0.02)
vs o4-mini: ↓ 9.1%
#11

Claude Haiku 4.5
Anthropic

$0.020000
vs o4-mini: ↓ 3%
#12

Grok 4.3
xAI

$0.020313
vs o4-mini: ↓ 1.5%
#13

Gemini 3.1 Flash
Google

$0.021250 (rounded ~ $0.02)
vs o4-mini: ↑ 3%
#14

Gemini 3.5 Flash
Google

$0.031875 (rounded ~ $0.03)
vs o4-mini: ↑ 54.5%
#15

Magistral Medium
Mistral AI

$0.033750 (rounded ~ $0.03)
vs o4-mini: ↑ 63.6%
#16

Grok 4.20 Beta
xAI

$0.035000 (rounded ~ $0.04)
vs o4-mini: ↑ 69.7%
#17

GPT-5.3 Codex Spark
OpenAI

$0.041563 (rounded ~ $0.04)
vs o4-mini: ↑ 101.5%
#18

GPT-5.3 Instant
OpenAI

$0.041563 (rounded ~ $0.04)
vs o4-mini: ↑ 101.5%
#19

Gemini 2.5 Pro
Google

$0.059375
vs o4-mini: ↑ 187.9%
#20

Claude Sonnet 4.6
Anthropic

$0.060000
vs o4-mini: ↑ 190.9%
#21

Gemini 3.1 Pro
Google

$0.085000 (rounded ~ $0.09)
vs o4-mini: ↑ 312.1%
#22

Claude Opus 4.7
Anthropic

$0.100000
vs o4-mini: ↑ 384.8%
#23

Claude Opus 4.8
Anthropic

$0.100000
vs o4-mini: ↑ 384.8%
#24

Claude Opus 4.6
Anthropic

$0.100000
vs o4-mini: ↑ 384.8%
#25

GPT-5.4
OpenAI

$0.106250 (rounded ~ $0.11)
vs o4-mini: ↑ 415.2%
#26

GPT-5.4 Thinking
OpenAI

$0.106250 (rounded ~ $0.11)
vs o4-mini: ↑ 415.2%
#27

GPT-5.5 Instant
OpenAI

$0.106250 (rounded ~ $0.11)
vs o4-mini: ↑ 415.2%
#28

o3 Deep Research
OpenAI

$0.187500 (rounded ~ $0.19)
vs o4-mini: ↑ 809.1%
#29

GPT-5.5
OpenAI

$0.212500 (rounded ~ $0.21)
vs o4-mini: ↑ 930.3%
#30

o3 Pro
OpenAI

$0.375000 (rounded ~ $0.38)
vs o4-mini: ↑ 1718.2%
#31

GPT-5.2 Pro
OpenAI

$0.498750 (rounded ~ $0.50)
vs o4-mini: ↑ 2318.2%
#32

GPT-5.2 Pro
OpenAI

$0.498750 (rounded ~ $0.50)
vs o4-mini: ↑ 2318.2%
✨ 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.

Refining Messy Archival Text

Even the best OCR processes can leave behind artifacts, typos, and structural errors that hinder the educational value of a document. o4-mini is a specialized reasoning model that excels at the complex task of correcting and normalizing messy text extracted from legacy archives. When processing 100,000 tokens of archival data, the model’s ability to ‘think’ through the context of a sentence allows it to make more accurate corrections than standard fast-chat models.

For creators, the qualitative benefit of using a reasoning-focused model like o4-mini lies in its deductive capabilities. If a historical document contains archaic spelling or damaged text, o4-mini can often infer the correct meaning based on the surrounding educational context. This level of logic is particularly useful for building high-quality textbooks or digital libraries where factual precision is non-negotiable. While the model may take more time to process each request compared to non-reasoning counterparts, the reduction in manual proofreading time for the creator is substantial. This makes it an excellent choice for small-scale projects where the goal is to produce professional-grade educational materials from imperfect historical sources.

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.