Financial Extraction: 100K-Token 10-K Analysis with GPT-5.4 Thinking

Complete Analysis: 105,000 tokens for GPT-5.4 Thinking
⚡ 80% Cached

Complete analysis of pricing, performance, and use cases for OpenAI's GPT-5.4 Thinking model with 80% Cached.

⚡ Caching Optimized (up to 90% savings) 📊 Batch API
$0.072500 (rounded ~ $0.07) Total Cost
105,000 Total Tokens
4 minutes, 25.31 seconds Processing Time
396 Effective Tokens/Sec

Click Recalculate to update after making changes

Select AI Model

GPT-5.4 Thinking
OpenAIMax Context: 1,024,000 tokens
$2.5 / $15 per 1M tokens (Standard)
State-dependent pricing active. Current tier: Standard
▼
▼
Use Batch API (50% discount)
80%
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

$0.072500 Total Cost
$0.025000 Input Cost
$0.037500 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
$0.000690Cost per 1K
1,448,276Tokens per $
🔄 Cliff Pricing Active: Using Standard pricing (standard) based on token volume.
📊 Advanced Cost Breakdown

Processing Speed

4m 25s Processing Time
400 Tokens/Second
220ms Time to First Token
396 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

GPT-5.4 Thinking OpenAI 1024000

$0.072500 (rounded ~ $0.07)
Total Cost
⚡ 80% Cached 📊 Batch API 🔧 Tools
👁️
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) $0.162500 (rounded ~ $0.16) Input: $0.125000 (rounded ~ $0.13)
Output: $0.037500 (rounded ~ $0.04)
Optimized Cost $0.072500 (rounded ~ $0.07) Input: $0.125000 (rounded ~ $0.13)
Output: $0.037500 (rounded ~ $0.04)
Unit: $0.000000
Fees: $0.000000
Total Savings $0.090000 55.4% discount

Advanced Cost Breakdown (from Plugin)

📊 Batch API
50.0% off
Asynchronous processing discount
📊 Cliff Pricing
Standard
standard pricing (threshold: 272,000)

Detailed Cost Analysis (from Plugin)

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

  • Input Cost: $0.125000 (rounded ~ $0.13)
  • Output Cost: $0.037500 (rounded ~ $0.04)
  • Total Cost: $0.072500 (rounded ~ $0.07)
  • Cost per 1K tokens: $0.000690
  • Tokens per dollar: 1,448,276 tokens
  • Context Window: 1024000 tokens

Speed & Performance Analysis

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

  • Processing Time: 4 minutes, 25.31 seconds
  • Latency: 220 milliseconds to first token
  • Base Throughput: 400 tokens/second
  • Effective Throughput: 396 tokens/second (temperature-adjusted)

Best Use Cases

Recommended for complexlogic-heavy document extraction tasks where accuracy and chain-of-thought consistency are required for financial reporting.

Want this applied to YOUR actual stack?

This calculator shows the math for GPT-5.4 Thinking. 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 GPT-5.4 Thinking
📋 Active Input Parameters
Input Tokens: 100,000
Output Tokens: 5,000
Batch API: Enabled (50% discount)
Cached Tokens: 80%
Tools: Enabled
Rank AI Model & Provider Total Cost vs GPT-5.4 Thinking
🏆 Mistral Small 3
Mistral AI
 $0.001075 Best Value ↓ 98.5% cheaper
🥈 Gemini 3.1 Flash Lite
Google
 $0.003625 ↓ 95% cheaper
🥉 Gemini 3.5 Flash-Lite
Google
 $0.005225 (rounded ~ $0.01) ↓ 92.8% cheaper
#4 Gemini 2.5 Flash
Google
 $0.005225 (rounded ~ $0.01) ↓ 92.8% cheaper
#5 Mistral Large 3
Mistral AI
 $0.005375 (rounded ~ $0.01) ↓ 92.6% cheaper
#6 Gemini 3.8 Flash
Google
 $0.009938 ↓ 86.3% cheaper
#7 GPT-5.4 mini
OpenAI
 $0.010875 ↓ 85% cheaper
#8 o4-mini Deep Research
OpenAI
 $0.012000 (rounded ~ $0.01) ↓ 83.4% cheaper
#9 o4-mini
OpenAI
 $0.013200 (rounded ~ $0.01) ↓ 81.8% cheaper
#10 Claude Haiku 4.5
Anthropic
 $0.013250 (rounded ~ $0.01) ↓ 81.7% cheaper
#11 Gemini 3.1 Flash
Google
 $0.014500 (rounded ~ $0.01) ↓ 80% cheaper
#12 GPT-5.6 Luna
OpenAI
 $0.014500 (rounded ~ $0.01) ↓ 80% cheaper
#13 Gemini 3.6 Flash
Google
 $0.019875 ↓ 72.6% cheaper
#14 Gemini 3.5 Flash
Google
 $0.021750 (rounded ~ $0.02) ↓ 70% cheaper
#15 Claude Sonnet 5
Anthropic
 $0.026500 (rounded ~ $0.03) ↓ 63.4% cheaper
#16 GPT-5.3 Codex Spark
OpenAI
 $0.029750 ↓ 59% cheaper
#17 GPT-5.3 Instant
OpenAI
 $0.029750 ↓ 59% cheaper
#18 GPT-5.6 Terra
OpenAI
 $0.036250 (rounded ~ $0.04) ↓ 50% cheaper
#19 Grok 4.3
xAI
 $0.038000 (rounded ~ $0.04) ↓ 47.6% cheaper
#20 Grok 4.20 Beta
xAI
 $0.038000 (rounded ~ $0.04) ↓ 47.6% cheaper
#21 Claude Sonnet 4.6
Anthropic
 $0.039750 ↓ 45.2% cheaper
#22 Gemini 2.5 Pro
Google
 $0.042500 (rounded ~ $0.04) ↓ 41.4% cheaper
#23 Gemini 3.1 Pro
Google
 $0.058000 (rounded ~ $0.06) ↓ 20% cheaper
#24 Claude Opus 4.7
Anthropic
 $0.066250 (rounded ~ $0.07) ↓ 8.6% cheaper
#25 Claude Opus 5
Anthropic
 $0.066250 (rounded ~ $0.07) ↓ 8.6% cheaper
#26 Claude Opus 4.8
Anthropic
 $0.066250 (rounded ~ $0.07) ↓ 8.6% cheaper
#27 Claude Opus 4.6
Anthropic
 $0.066250 (rounded ~ $0.07) ↓ 8.6% cheaper
#28 GPT-5.4
OpenAI
 $0.072500 (rounded ~ $0.07) Same price
#29 GPT-5.5 Instant
OpenAI
 $0.072500 (rounded ~ $0.07) Same price
#30 GPT-5.6 Sol
OpenAI
 $0.072500 (rounded ~ $0.07) Same price
#31 Claude Fable 5.1
Anthropic
 $0.117500 (rounded ~ $0.12) ↑ 62.1% more
#32 Claude Mythos 5.1
Anthropic
 $0.117500 (rounded ~ $0.12) ↑ 62.1% more
#33 o3 Deep Research
OpenAI
 $0.120000 ↑ 65.5% more
#34 Claude Fable 5
Anthropic
 $0.132500 (rounded ~ $0.13) ↑ 82.8% more
#35 Claude Mythos 5
Anthropic
 $0.132500 (rounded ~ $0.13) ↑ 82.8% more
#36 GPT-5.5
OpenAI
 $0.145000 (rounded ~ $0.15) ↑ 100% more
#37 o3 Pro
OpenAI
 $0.240000 ↑ 231% more
#38 GPT-6 Astra
OpenAI
 $0.265000 (rounded ~ $0.27) ↑ 265.5% more
#39 GPT-5.2 Pro
OpenAI
 $0.357000 (rounded ~ $0.36) ↑ 392.4% more
#40 GPT-5.2 Pro
OpenAI
 $0.357000 (rounded ~ $0.36) ↑ 392.4% more
🏆

Mistral Small 3
Mistral AI

$0.001075
vs GPT-5.4 Thinking: ↓ 98.5%
🥈

Gemini 3.1 Flash Lite
Google

$0.003625
vs GPT-5.4 Thinking: ↓ 95%
🥉

Gemini 3.5 Flash-Lite
Google

$0.005225 (rounded ~ $0.01)
vs GPT-5.4 Thinking: ↓ 92.8%
#4

Gemini 2.5 Flash
Google

$0.005225 (rounded ~ $0.01)
vs GPT-5.4 Thinking: ↓ 92.8%
#5

Mistral Large 3
Mistral AI

$0.005375 (rounded ~ $0.01)
vs GPT-5.4 Thinking: ↓ 92.6%
#6

Gemini 3.8 Flash
Google

$0.009938
vs GPT-5.4 Thinking: ↓ 86.3%
#7

GPT-5.4 mini
OpenAI

$0.010875
vs GPT-5.4 Thinking: ↓ 85%
#8

o4-mini Deep Research
OpenAI

$0.012000 (rounded ~ $0.01)
vs GPT-5.4 Thinking: ↓ 83.4%
#9

o4-mini
OpenAI

$0.013200 (rounded ~ $0.01)
vs GPT-5.4 Thinking: ↓ 81.8%
#10

Claude Haiku 4.5
Anthropic

$0.013250 (rounded ~ $0.01)
vs GPT-5.4 Thinking: ↓ 81.7%
#11

Gemini 3.1 Flash
Google

$0.014500 (rounded ~ $0.01)
vs GPT-5.4 Thinking: ↓ 80%
#12

GPT-5.6 Luna
OpenAI

$0.014500 (rounded ~ $0.01)
vs GPT-5.4 Thinking: ↓ 80%
#13

Gemini 3.6 Flash
Google

$0.019875
vs GPT-5.4 Thinking: ↓ 72.6%
#14

Gemini 3.5 Flash
Google

$0.021750 (rounded ~ $0.02)
vs GPT-5.4 Thinking: ↓ 70%
#15

Claude Sonnet 5
Anthropic

$0.026500 (rounded ~ $0.03)
vs GPT-5.4 Thinking: ↓ 63.4%
#16

GPT-5.3 Codex Spark
OpenAI

$0.029750
vs GPT-5.4 Thinking: ↓ 59%
#17

GPT-5.3 Instant
OpenAI

$0.029750
vs GPT-5.4 Thinking: ↓ 59%
#18

GPT-5.6 Terra
OpenAI

$0.036250 (rounded ~ $0.04)
vs GPT-5.4 Thinking: ↓ 50%
#19

Grok 4.3
xAI

$0.038000 (rounded ~ $0.04)
vs GPT-5.4 Thinking: ↓ 47.6%
#20

Grok 4.20 Beta
xAI

$0.038000 (rounded ~ $0.04)
vs GPT-5.4 Thinking: ↓ 47.6%
#21

Claude Sonnet 4.6
Anthropic

$0.039750
vs GPT-5.4 Thinking: ↓ 45.2%
#22

Gemini 2.5 Pro
Google

$0.042500 (rounded ~ $0.04)
vs GPT-5.4 Thinking: ↓ 41.4%
#23

Gemini 3.1 Pro
Google

$0.058000 (rounded ~ $0.06)
vs GPT-5.4 Thinking: ↓ 20%
#24

Claude Opus 4.7
Anthropic

$0.066250 (rounded ~ $0.07)
vs GPT-5.4 Thinking: ↓ 8.6%
#25

Claude Opus 5
Anthropic

$0.066250 (rounded ~ $0.07)
vs GPT-5.4 Thinking: ↓ 8.6%
#26

Claude Opus 4.8
Anthropic

$0.066250 (rounded ~ $0.07)
vs GPT-5.4 Thinking: ↓ 8.6%
#27

Claude Opus 4.6
Anthropic

$0.066250 (rounded ~ $0.07)
vs GPT-5.4 Thinking: ↓ 8.6%
#28

GPT-5.4
OpenAI

$0.072500 (rounded ~ $0.07)
vs GPT-5.4 Thinking: Same
#29

GPT-5.5 Instant
OpenAI

$0.072500 (rounded ~ $0.07)
vs GPT-5.4 Thinking: Same
#30

GPT-5.6 Sol
OpenAI

$0.072500 (rounded ~ $0.07)
vs GPT-5.4 Thinking: Same
#31

Claude Fable 5.1
Anthropic

$0.117500 (rounded ~ $0.12)
vs GPT-5.4 Thinking: ↑ 62.1%
#32

Claude Mythos 5.1
Anthropic

$0.117500 (rounded ~ $0.12)
vs GPT-5.4 Thinking: ↑ 62.1%
#33

o3 Deep Research
OpenAI

$0.120000
vs GPT-5.4 Thinking: ↑ 65.5%
#34

Claude Fable 5
Anthropic

$0.132500 (rounded ~ $0.13)
vs GPT-5.4 Thinking: ↑ 82.8%
#35

Claude Mythos 5
Anthropic

$0.132500 (rounded ~ $0.13)
vs GPT-5.4 Thinking: ↑ 82.8%
#36

GPT-5.5
OpenAI

$0.145000 (rounded ~ $0.15)
vs GPT-5.4 Thinking: ↑ 100%
#37

o3 Pro
OpenAI

$0.240000
vs GPT-5.4 Thinking: ↑ 231%
#38

GPT-6 Astra
OpenAI

$0.265000 (rounded ~ $0.27)
vs GPT-5.4 Thinking: ↑ 265.5%
#39

GPT-5.2 Pro
OpenAI

$0.357000 (rounded ~ $0.36)
vs GPT-5.4 Thinking: ↑ 392.4%
#40

GPT-5.2 Pro
OpenAI

$0.357000 (rounded ~ $0.36)
vs GPT-5.4 Thinking: ↑ 392.4%
✨ 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.

Parsing 10-K filings involves navigating complex accounting standards, risk disclosures, and massive footnotes. GPT-5.4 Thinking is uniquely positioned for this workload because of its dedicated reasoning-first approach. Unlike models that prioritize fast, reactive responses, GPT-5.4 Thinking is designed to spend computational cycles upfront to plan its approach before attempting complex extraction tasks. For a 100,000-token 10-K document, this means the model can create a structured extraction plan, identifying key tables and narrative summaries before it begins pulling the data into your required output format. This reduces the need for iterative prompting and manual cleanup, which is critical when you are parsing hundreds of filings in a batch.

This model is particularly effective when you have ambiguous or variable filing formats. Because it uses a chain-of-thought approach, it can self-correct when it encounters non-standard reporting structures, leading to more predictable output quality. If your financial analysis pipeline requires high-precision data retrieval—such as pulling exact revenue figures or specific risk categories—the Thinking model’s ability to maintain logical consistency across a 100,000-token context is a major advantage. It treats the extraction task as a multi-step analytical problem rather than a simple pattern-matching exercise, making it a robust choice for heavy-duty, document-intensive financial workflows.

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

GPT-5.4 Thinking currently costs $2.50 / $15.00 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 →