How are image tokens calculated for AI models?

Images are tokenized based on resolution: Low (512px): 85 tokens, Medium (768px): 170 tokens, High (1024px): 255 tokens, Full (2048px): 765 tokens per image. For Gemini 3.5 Flash: 500 images at medium resolution = 85,000 tokens.

What are cached tokens and how do they save money?

Cached tokens are repeated input tokens (like system prompts or conversation history) that providers charge at a discounted rate. Google offers varying discounts for cached tokens (typically 50-80%). Your calculation saves money by applying caching to 20% of input tokens for optimized cost savings.

When should I use Batch API vs real-time API?

Use Batch API for non-realtime processing of large volumes where latency isn't critical (saves up to 40-60%). Use real-time API for interactive applications like chatbots. Batch processing is ideal for data analysis, content generation in bulk, and offline processing.

What should I consider when comparing different AI models?

When comparing AI models, focus on factors such as performance, accuracy, response speed, cost, scalability, and how well the model fits your specific use case. The right choice depends on your workload, budget, and the type of tasks you want the AI to handle. Using an AI cost and time calculator can help you make an informed, data-driven decision.

Gemini 3.5 Flash vs GPT-5.4 mini: 500 Image Captions for Storyboard Frames

Name: GPT-5.4 mini
Brand: OpenAI
Price: 0.05 USD
Availability: InStock
Rating: 4.5 (89 reviews)

Gemini 3.5 Flash vs GPT-5.4 mini

Complete Comparison: 50,000 input tokens × 1,000 output tokens

🖼️ 500 Images ⚡ 20% Cached

Complete comparison of pricing, performance, and capabilities for 2 leading AI models with 500 Images, 20% Cached.

🖼️ Multimodal Input ⚡ Caching Optimized (up to 90% savings) 📊 Batch API

Comparison Criteria	Gemini 3.5 Flash Google	GPT-5.4 mini OpenAI
Calculation Results (Current Inputs) (500 images, 20% cached)
Input Tokens	50,000	50,000
Output Tokens	1,000	1,000
Cost Breakdown
Input Cost	$0.115500 (rounded ~ $0.12)Worst	$0.057750 (rounded ~ $0.06)Best
Output Cost	$0.002250Worst	$0.001125Best
Unit Cost (Audio/OCR)	$0.000000	$0.000000
Service Fees	$0.000000	$0.000000
Total Cost	$0.096960 (rounded ~ $0.10) Most Expensive	$0.048480 (rounded ~ $0.05) Best Value
Processing Time	6 minutes, 21.89 seconds Fastest	10 minutes, 49.08 seconds Slowest
Tokens per Second	850Fastest	500Slowest
Time to First Token	90ms Best	180ms Worst
Cost per 1K tokens	$0.000314Worst	$0.000157Best
Tokens per Dollar	3,186,881Worst Value	6,373,762Best Value
Cost per 1 Million Tokens (Informational)
Input Cost / 1M (Base)	$0.375000 (rounded ~ $0.38)Worst	$0.187500 (rounded ~ $0.19)Best
Output Cost / 1M (Base)	$2.250000Worst	$1.125000 (rounded ~ $1.13)Best
Input Cost / 1M (Optimized)	$0.187500 (rounded ~ $0.19)Worst Optimizations: 50.0% batch	$0.093750 (rounded ~ $0.09)Best Optimizations: 50.0% batch
Output Cost / 1M (Optimized)	$1.125000 (rounded ~ $1.13)Worst Optimizations: 50.0% batch	$0.562500 (rounded ~ $0.56)Best Optimizations: 50.0% batch
Capabilities & Advanced Features
Images Support 500	✓ Supported	✓ Supported
Video Support	✓ Supported	✗ Not Supported
Audio Support	✓ Supported	✗ Not Supported
Caching Support 20	✓ Supported	✓ Supported
Batch API Support	✓ Supported	✓ Supported
Tool Usage Support	✓ Supported	✓ Supported

Scroll horizontally to see all data

🔄 Compare Different AI Models

First Model

Provider

Model

Second Model

Provider

Model

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

Gemini 3.5 Flash Google 1000000

$0.096960 (rounded ~ $0.10)

Total Cost

🖼️ 500 Image (Medium) ⚡ 20% 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) $0.117750 (rounded ~ $0.12) Input: $0.115500 (rounded ~ $0.12)
Output: $0.002250

Optimized Cost $0.096960 (rounded ~ $0.10) Input: $0.115500 (rounded ~ $0.12)
Output: $0.002250
Unit: $0.000000
Fees: $0.000000

Total Savings $0.020790 17.7% discount

Advanced Cost Breakdown (from Plugin)

🖼️ Multimodal Input

$0.000000

258,000 tokens

📊 Batch API

50.0% off

Asynchronous processing discount

Multimodal Input Details

🖼️ Images

Count: 500
Resolution: Medium
Tokens: 258,000
Cost: $0.000000

Detailed Cost Analysis (from Plugin)

For 50,000 input tokens and 1,000 output tokens:

Input Cost: $0.115500 (rounded ~ $0.12)
Output Cost: $0.002250
Total Cost: $0.096960 (rounded ~ $0.10)
Cost per 1K tokens: $0.000314
Tokens per dollar: 3,186,881 tokens
Context Window: 1000000 tokens

Speed & Performance Analysis

With a processing speed of 850 tokens per second and 90ms time to first token:

Processing Time: 6 minutes, 21.89 seconds
Latency: 90 milliseconds to first token
Base Throughput: 850 tokens/second
Effective Throughput: 810 tokens/second (temperature-adjusted)

Best Use Cases

Choose Gemini 3.5 Flash for complexmulti-step visual reasoning or GPT-5.4 mini for high-speedcost-effective batch captioning.

Want this applied to YOUR actual stack?

This calculator shows the math for Gemini 3.5 Flash. 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 →

GPT-5.4 mini OpenAI

$0.048480 (rounded ~ $0.05)

Total Cost

🖼️ 500 Image (Medium) ⚡ 20% 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) $0.058875 (rounded ~ $0.06) Input: $0.057750 (rounded ~ $0.06)
Output: $0.001125

Optimized Cost $0.048480 (rounded ~ $0.05) Input: $0.057750 (rounded ~ $0.06)
Output: $0.001125
Unit: $0.000000
Fees: $0.000000

Total Savings $0.010395 17.7% discount

Advanced Cost Breakdown (from Plugin)

🖼️ Multimodal Input

$0.000000

258,000 tokens

📊 Batch API

50.0% off

Asynchronous processing discount

Multimodal Input Details

🖼️ Images

Count: 500
Resolution: Medium
Tokens: 258,000
Cost: $0.000000

Detailed Cost Analysis (from Plugin)

For 50,000 input tokens and 1,000 output tokens:

Input Cost: $0.057750 (rounded ~ $0.06)
Output Cost: $0.001125
Total Cost: $0.048480 (rounded ~ $0.05)
Cost per 1K tokens: $0.000157
Tokens per dollar: 6,373,762 tokens
Context Window: 400000 tokens

Speed & Performance Analysis

With a processing speed of 500 tokens per second and 180ms time to first token:

Processing Time: 10 minutes, 49.08 seconds
Latency: 180 milliseconds to first token
Base Throughput: 500 tokens/second
Effective Throughput: 476 tokens/second (temperature-adjusted)

Best Use Cases

Choose Gemini 3.5 Flash for complexmulti-step visual reasoning or GPT-5.4 mini for high-speedcost-effective batch captioning.

Want this applied to YOUR actual stack?

This calculator shows the math for GPT-5.4 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 Gemini 3.5 Flash

📋 Active Input Parameters

Input Tokens: 50,000

Output Tokens: 1,000

Batch API: Enabled (50% discount)

Cached Tokens: 20%

Images: 500 (Medium Resolution)

Tools: Enabled

Rank	AI Model & Provider	Total Cost	vs Gemini 3.5 Flash	vs GPT-5.4 mini
🏆	Mistral Small 3 Mistral AI	$0.006389 (rounded ~ $0.01) Best Value	↓ 93.4% cheaper	↓ 86.8% cheaper
🥈	Gemini 3.1 Flash Lite Google	$0.016160 (rounded ~ $0.02)	↓ 83.3% cheaper	↓ 66.7% cheaper
🥉	Gemini 3.5 Flash-Lite Google	$0.019567	↓ 79.8% cheaper	↓ 59.6% cheaper
#4	Gemini 2.5 Flash Google	$0.019567	↓ 79.8% cheaper	↓ 59.6% cheaper
#5	Mistral Large 3 Mistral AI	$0.032195 (rounded ~ $0.03)	↓ 66.8% cheaper	↓ 33.6% cheaper
#6	Gemini 3.8 Flash Google	$0.048293 (rounded ~ $0.05)	↓ 50.2% cheaper	↓ 0.4% cheaper
#7	GPT-5.4 mini OpenAI	$0.048480 (rounded ~ $0.05)	↓ 50% cheaper	Same price
#8	o4-mini Deep Research OpenAI	$0.064140 (rounded ~ $0.06)	↓ 33.8% cheaper	↑ 32.3% more
#9	Claude Haiku 4.5 Anthropic	$0.064390 (rounded ~ $0.06)	↓ 33.6% cheaper	↑ 32.8% more
#10	GPT-5.6 Luna OpenAI	$0.064640 (rounded ~ $0.06)	↓ 33.3% cheaper	↑ 33.3% more
#11	o4-mini OpenAI	$0.070554	↓ 27.2% cheaper	↑ 45.5% more
#12	Gemini 3.6 Flash Google	$0.096585 (rounded ~ $0.10)	↓ 0.4% cheaper	↑ 99.2% more
#13	GPT-5.3 Codex Spark OpenAI	$0.113995 (rounded ~ $0.11)	↑ 17.6% more	↑ 135.1% more
#14	GPT-5.3 Instant OpenAI	$0.113995 (rounded ~ $0.11)	↑ 17.6% more	↑ 135.1% more
#15	Claude Sonnet 5 Anthropic	$0.128780 (rounded ~ $0.13)	↑ 32.8% more	↑ 165.6% more
#16	Gemini 3.1 Flash Google	$0.129280	↑ 33.3% more	↑ 166.7% more
#17	GPT-5.6 Terra OpenAI	$0.161600 (rounded ~ $0.16)	↑ 66.7% more	↑ 233.3% more
#18	Claude Sonnet 4.6 Anthropic	$0.193170 (rounded ~ $0.19)	↑ 99.2% more	↑ 298.5% more
#19	Claude Opus 4.7 Anthropic	$0.321950 (rounded ~ $0.32)	↑ 232% more	↑ 564.1% more
#20	Claude Opus 5 Anthropic	$0.321950 (rounded ~ $0.32)	↑ 232% more	↑ 564.1% more
#21	Claude Opus 4.8 Anthropic	$0.321950 (rounded ~ $0.32)	↑ 232% more	↑ 564.1% more
#22	Claude Opus 4.6 Anthropic	$0.321950 (rounded ~ $0.32)	↑ 232% more	↑ 564.1% more
#23	Gemini 2.5 Pro Google	$0.323200 (rounded ~ $0.32)	↑ 233.3% more	↑ 566.7% more
#24	GPT-5.5 Instant OpenAI	$0.323200 (rounded ~ $0.32)	↑ 233.3% more	↑ 566.7% more
#25	GPT-5.6 Sol OpenAI	$0.323200 (rounded ~ $0.32)	↑ 233.3% more	↑ 566.7% more
#26	Grok 4.3 xAI	$0.509120	↑ 425.1% more	↑ 950.2% more
#27	Gemini 3.1 Pro Google	$0.514120 (rounded ~ $0.51)	↑ 430.2% more	↑ 960.5% more
#28	Claude Fable 5.1 Anthropic	$0.632350 (rounded ~ $0.63)	↑ 552.2% more	↑ 1204.4% more
#29	Claude Mythos 5.1 Anthropic	$0.632350 (rounded ~ $0.63)	↑ 552.2% more	↑ 1204.4% more
#30	o3 Deep Research OpenAI	$0.641400 (rounded ~ $0.64)	↑ 561.5% more	↑ 1223% more
#31	GPT-5.4 OpenAI	$0.642650 (rounded ~ $0.64)	↑ 562.8% more	↑ 1225.6% more
#32	GPT-5.4 Thinking OpenAI	$0.642650 (rounded ~ $0.64)	↑ 562.8% more	↑ 1225.6% more
#33	Claude Fable 5 Anthropic	$0.643900 (rounded ~ $0.64)	↑ 564.1% more	↑ 1228.2% more
#34	Claude Mythos 5 Anthropic	$0.643900 (rounded ~ $0.64)	↑ 564.1% more	↑ 1228.2% more
#35	o3 Pro OpenAI	$1.282800 (rounded ~ $1.28)	↑ 1223% more	↑ 2546% more
#36	GPT-5.5 OpenAI	$1.285300 (rounded ~ $1.29)	↑ 1225.6% more	↑ 2551.2% more
#37	GPT-5.2 Pro OpenAI	$1.367940 (rounded ~ $1.37)	↑ 1310.8% more	↑ 2721.7% more
#38	GPT-6 Astra OpenAI	$2.575600 (rounded ~ $2.58)	↑ 2556.4% more	↑ 5212.7% more
#39	GPT-6 Astra OpenAI	$2.575600 (rounded ~ $2.58)	↑ 2556.4% more	↑ 5212.7% more

🏆

Mistral Small 3
Mistral AI

$0.006389 (rounded ~ $0.01)

vs Gemini 3.5 Flash: ↓ 93.4%

vs GPT-5.4 mini: ↓ 86.8%

🥈

Gemini 3.1 Flash Lite
Google

$0.016160 (rounded ~ $0.02)

vs Gemini 3.5 Flash: ↓ 83.3%

vs GPT-5.4 mini: ↓ 66.7%

🥉

Gemini 3.5 Flash-Lite
Google

$0.019567

vs Gemini 3.5 Flash: ↓ 79.8%

vs GPT-5.4 mini: ↓ 59.6%

Gemini 2.5 Flash
Google

$0.019567

vs Gemini 3.5 Flash: ↓ 79.8%

vs GPT-5.4 mini: ↓ 59.6%

Mistral Large 3
Mistral AI

$0.032195 (rounded ~ $0.03)

vs Gemini 3.5 Flash: ↓ 66.8%

vs GPT-5.4 mini: ↓ 33.6%

Gemini 3.8 Flash
Google

$0.048293 (rounded ~ $0.05)

vs Gemini 3.5 Flash: ↓ 50.2%

vs GPT-5.4 mini: ↓ 0.4%

GPT-5.4 mini
OpenAI

$0.048480 (rounded ~ $0.05)

vs Gemini 3.5 Flash: ↓ 50%

vs GPT-5.4 mini: Same

o4-mini Deep Research
OpenAI

$0.064140 (rounded ~ $0.06)

vs Gemini 3.5 Flash: ↓ 33.8%

vs GPT-5.4 mini: ↑ 32.3%

Claude Haiku 4.5
Anthropic

$0.064390 (rounded ~ $0.06)

vs Gemini 3.5 Flash: ↓ 33.6%

vs GPT-5.4 mini: ↑ 32.8%

#10

GPT-5.6 Luna
OpenAI

$0.064640 (rounded ~ $0.06)

vs Gemini 3.5 Flash: ↓ 33.3%

vs GPT-5.4 mini: ↑ 33.3%

#11

o4-mini
OpenAI

$0.070554

vs Gemini 3.5 Flash: ↓ 27.2%

vs GPT-5.4 mini: ↑ 45.5%

#12

Gemini 3.6 Flash
Google

$0.096585 (rounded ~ $0.10)

vs Gemini 3.5 Flash: ↓ 0.4%

vs GPT-5.4 mini: ↑ 99.2%

#13

GPT-5.3 Codex Spark
OpenAI

$0.113995 (rounded ~ $0.11)

vs Gemini 3.5 Flash: ↑ 17.6%

vs GPT-5.4 mini: ↑ 135.1%

#14

GPT-5.3 Instant
OpenAI

$0.113995 (rounded ~ $0.11)

vs Gemini 3.5 Flash: ↑ 17.6%

vs GPT-5.4 mini: ↑ 135.1%

#15

Claude Sonnet 5
Anthropic

$0.128780 (rounded ~ $0.13)

vs Gemini 3.5 Flash: ↑ 32.8%

vs GPT-5.4 mini: ↑ 165.6%

#16

Gemini 3.1 Flash
Google

$0.129280

vs Gemini 3.5 Flash: ↑ 33.3%

vs GPT-5.4 mini: ↑ 166.7%

#17

GPT-5.6 Terra
OpenAI

$0.161600 (rounded ~ $0.16)

vs Gemini 3.5 Flash: ↑ 66.7%

vs GPT-5.4 mini: ↑ 233.3%

#18

Claude Sonnet 4.6
Anthropic

$0.193170 (rounded ~ $0.19)

vs Gemini 3.5 Flash: ↑ 99.2%

vs GPT-5.4 mini: ↑ 298.5%

#19

Claude Opus 4.7
Anthropic

$0.321950 (rounded ~ $0.32)

vs Gemini 3.5 Flash: ↑ 232%

vs GPT-5.4 mini: ↑ 564.1%

#20

Claude Opus 5
Anthropic

$0.321950 (rounded ~ $0.32)

vs Gemini 3.5 Flash: ↑ 232%

vs GPT-5.4 mini: ↑ 564.1%

#21

Claude Opus 4.8
Anthropic

$0.321950 (rounded ~ $0.32)

vs Gemini 3.5 Flash: ↑ 232%

vs GPT-5.4 mini: ↑ 564.1%

#22

Claude Opus 4.6
Anthropic

$0.321950 (rounded ~ $0.32)

vs Gemini 3.5 Flash: ↑ 232%

vs GPT-5.4 mini: ↑ 564.1%

#23

Gemini 2.5 Pro
Google

$0.323200 (rounded ~ $0.32)

vs Gemini 3.5 Flash: ↑ 233.3%

vs GPT-5.4 mini: ↑ 566.7%

#24

GPT-5.5 Instant
OpenAI

$0.323200 (rounded ~ $0.32)

vs Gemini 3.5 Flash: ↑ 233.3%

vs GPT-5.4 mini: ↑ 566.7%

#25

GPT-5.6 Sol
OpenAI

$0.323200 (rounded ~ $0.32)

vs Gemini 3.5 Flash: ↑ 233.3%

vs GPT-5.4 mini: ↑ 566.7%

#26

Grok 4.3
xAI

$0.509120

vs Gemini 3.5 Flash: ↑ 425.1%

vs GPT-5.4 mini: ↑ 950.2%

#27

Gemini 3.1 Pro
Google

$0.514120 (rounded ~ $0.51)

vs Gemini 3.5 Flash: ↑ 430.2%

vs GPT-5.4 mini: ↑ 960.5%

#28

Claude Fable 5.1
Anthropic

$0.632350 (rounded ~ $0.63)

vs Gemini 3.5 Flash: ↑ 552.2%

vs GPT-5.4 mini: ↑ 1204.4%

#29

Claude Mythos 5.1
Anthropic

$0.632350 (rounded ~ $0.63)

vs Gemini 3.5 Flash: ↑ 552.2%

vs GPT-5.4 mini: ↑ 1204.4%

#30

o3 Deep Research
OpenAI

$0.641400 (rounded ~ $0.64)

vs Gemini 3.5 Flash: ↑ 561.5%

vs GPT-5.4 mini: ↑ 1223%

#31

GPT-5.4
OpenAI

$0.642650 (rounded ~ $0.64)

vs Gemini 3.5 Flash: ↑ 562.8%

vs GPT-5.4 mini: ↑ 1225.6%

#32

GPT-5.4 Thinking
OpenAI

$0.642650 (rounded ~ $0.64)

vs Gemini 3.5 Flash: ↑ 562.8%

vs GPT-5.4 mini: ↑ 1225.6%

#33

Claude Fable 5
Anthropic

$0.643900 (rounded ~ $0.64)

vs Gemini 3.5 Flash: ↑ 564.1%

vs GPT-5.4 mini: ↑ 1228.2%

#34

Claude Mythos 5
Anthropic

$0.643900 (rounded ~ $0.64)

vs Gemini 3.5 Flash: ↑ 564.1%

vs GPT-5.4 mini: ↑ 1228.2%

#35

o3 Pro
OpenAI

$1.282800 (rounded ~ $1.28)

vs Gemini 3.5 Flash: ↑ 1223%

vs GPT-5.4 mini: ↑ 2546%

#36

GPT-5.5
OpenAI

$1.285300 (rounded ~ $1.29)

vs Gemini 3.5 Flash: ↑ 1225.6%

vs GPT-5.4 mini: ↑ 2551.2%

#37

GPT-5.2 Pro
OpenAI

$1.367940 (rounded ~ $1.37)

vs Gemini 3.5 Flash: ↑ 1310.8%

vs GPT-5.4 mini: ↑ 2721.7%

#38

GPT-6 Astra
OpenAI

$2.575600 (rounded ~ $2.58)

vs Gemini 3.5 Flash: ↑ 2556.4%

vs GPT-5.4 mini: ↑ 5212.7%

#39

GPT-6 Astra
OpenAI

$2.575600 (rounded ~ $2.58)

vs Gemini 3.5 Flash: ↑ 2556.4%

vs GPT-5.4 mini: ↑ 5212.7%

✨ 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.

For developers building storyboard tools, the choice between Gemini 3.5 Flash and GPT-5.4 mini often hinges on your specific multimodal pipeline requirements. Both models excel at vision-based tasks, making them ideal for interpreting rough sketches or generated storyboard frames. Gemini 3.5 Flash is particularly adept at handling multi-step agentic workflows where your app needs to do more than just caption; it can reason about the scene, suggest camera angles, or verify visual consistency across a sequence of frames. Its tight integration into Google’s agentic framework makes it a strong contender if your storyboard app plans to incorporate proactive planning agents.

GPT-5.4 mini, conversely, shines as a highly efficient, low-latency engine for high-volume batch processing. If your app’s primary value is rapid, repetitive captioning of large catalogs of frames, GPT-5.4 mini provides a balance of speed and reliability that is hard to beat. It is optimized for responsiveness, which is critical for a mobile experience where users expect near-instant feedback when they upload or generate content. While both models handle image inputs effectively, developers often find that Gemini 3.5 Flash offers slightly more nuance in visual interpretation for complex scenes, whereas GPT-5.4 mini is the superior choice for simple, high-throughput tasks where minimizing latency is the ultimate goal. Choosing between them depends on whether your app prioritizes deep visual reasoning or sheer execution speed.

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.

Gemini 3.5 Flash vs GPT-5.4 mini: 500 Image Captions for Storyboard Frames

🔄 Compare Different AI Models

First Model

Second Model

Select AI Model

Gemini 3.5 Flash

Calculate Token Costs

📊 Advanced Cost Breakdown

Processing Speed

Model Comparison

Model Information

🔄 Advanced Options

⚡ Optimization

🧠 Reasoning & Thinking

🔧 Special Modes

📚 Research & Citations

🎤 Realtime Audio & Video

Gemini 3.5 Flash Google 1000000

💰 Total Cost Calculation (from Plugin)

Advanced Cost Breakdown (from Plugin)

Multimodal Input Details

Detailed Cost Analysis (from Plugin)

Speed & Performance Analysis

Best Use Cases

Want this applied to YOUR actual stack?

GPT-5.4 mini OpenAI

💰 Total Cost Calculation (from Plugin)

Advanced Cost Breakdown (from Plugin)

Multimodal Input Details

Detailed Cost Analysis (from Plugin)

Speed & Performance Analysis

Best Use Cases

Want this applied to YOUR actual stack?

✨ Market Recommendations AI Model Registry

Mistral Small 3 Mistral AI

Gemini 3.1 Flash Lite Google

Gemini 3.5 Flash-Lite Google

Gemini 2.5 Flash Google

Mistral Large 3 Mistral AI

Gemini 3.8 Flash Google

GPT-5.4 mini OpenAI

o4-mini Deep Research OpenAI

Claude Haiku 4.5 Anthropic

GPT-5.6 Luna OpenAI

o4-mini OpenAI

Gemini 3.6 Flash Google

GPT-5.3 Codex Spark OpenAI

GPT-5.3 Instant OpenAI

Claude Sonnet 5 Anthropic

Gemini 3.1 Flash Google

GPT-5.6 Terra OpenAI

Claude Sonnet 4.6 Anthropic

Claude Opus 4.7 Anthropic

Claude Opus 5 Anthropic

Claude Opus 4.8 Anthropic

Claude Opus 4.6 Anthropic

Gemini 2.5 Pro Google

GPT-5.5 Instant OpenAI

GPT-5.6 Sol OpenAI

Grok 4.3 xAI

Gemini 3.1 Pro Google

Claude Fable 5.1 Anthropic

Claude Mythos 5.1 Anthropic

o3 Deep Research OpenAI

GPT-5.4 OpenAI

GPT-5.4 Thinking OpenAI

Claude Fable 5 Anthropic

Claude Mythos 5 Anthropic

o3 Pro OpenAI

GPT-5.5 OpenAI

GPT-5.2 Pro OpenAI

GPT-6 Astra OpenAI

GPT-6 Astra OpenAI

Frequently Asked Questions

Related model pricing

Compare across providers

Other models from the same provider

Mistral Small 3
Mistral AI

Gemini 3.1 Flash Lite
Google

Gemini 3.5 Flash-Lite
Google

Gemini 2.5 Flash
Google

Mistral Large 3
Mistral AI

Gemini 3.8 Flash
Google

GPT-5.4 mini
OpenAI

o4-mini Deep Research
OpenAI

Claude Haiku 4.5
Anthropic

GPT-5.6 Luna
OpenAI

o4-mini
OpenAI

Gemini 3.6 Flash
Google

GPT-5.3 Codex Spark
OpenAI

GPT-5.3 Instant
OpenAI

Claude Sonnet 5
Anthropic

Gemini 3.1 Flash
Google

GPT-5.6 Terra
OpenAI

Claude Sonnet 4.6
Anthropic

Claude Opus 4.7
Anthropic

Claude Opus 5
Anthropic

Claude Opus 4.8
Anthropic

Claude Opus 4.6
Anthropic

Gemini 2.5 Pro
Google

GPT-5.5 Instant
OpenAI

GPT-5.6 Sol
OpenAI

Grok 4.3
xAI

Gemini 3.1 Pro
Google

Claude Fable 5.1
Anthropic

Claude Mythos 5.1
Anthropic

o3 Deep Research
OpenAI

GPT-5.4
OpenAI

GPT-5.4 Thinking
OpenAI

Claude Fable 5
Anthropic

Claude Mythos 5
Anthropic

o3 Pro
OpenAI

GPT-5.5
OpenAI

GPT-5.2 Pro
OpenAI

GPT-6 Astra
OpenAI

GPT-6 Astra
OpenAI