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. Anthropic 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.

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.

Code Review Efficiency: Claude Sonnet 4.6 vs Devstral 2 for 100K-Token PR Diffs

Name: Devstral 2
Brand: Mistral AI
Price: 0.03 USD
Availability: InStock
Rating: 4.5 (89 reviews)

Claude Sonnet 4.6 has been replaced by Claude Sonnet 5

The pricing shown below is for the older model and is kept for reference. If you are choosing a model today, use the current version — its rate and context window differ.

See current Claude Sonnet 5 pricing → · All recent pricing changes

Claude Sonnet 4.6 vs Devstral 2

Complete Comparison: 100,000 input tokens × 2,000 output tokens

⚡ 20% Cached

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

⚡ Caching Optimized (up to 90% savings)

Comparison Criteria	Claude Sonnet 4.6 Anthropic	Devstral 2 Mistral AI
Calculation Results (Current Inputs) (20% cached)
Input Tokens	100,000	100,000
Output Tokens	2,000	2,000
Cost Breakdown
Input Cost	$0.300000Worst	$0.040000Best
Output Cost	$0.030000Worst	$0.001800Best
Unit Cost (Audio/OCR)	$0.000000	$0.000000
Service Fees	$0.000000	$0.000000
Total Cost	$0.276000 (rounded ~ $0.28) Most Expensive	$0.034600 (rounded ~ $0.03) Best Value
Processing Time	4 minutes, 2.71 seconds	4 minutes, 2.71 seconds
Tokens per Second	450	450
Time to First Token	200ms Worst	180ms Best
Cost per 1K tokens	$0.002706Worst	$0.000339Best
Tokens per Dollar	369,565Worst Value	2,947,977Best Value
Cost per 1 Million Tokens (Informational)
Input Cost / 1M (Base)	$3.000000Worst	$0.400000Best
Output Cost / 1M (Base)	$15.000000Worst	$0.900000Best
Input Cost / 1M (Optimized)	$3.000000Worst Optimizations: No optimizations applied	$0.400000Best Optimizations: No optimizations applied
Output Cost / 1M (Optimized)	$15.000000Worst Optimizations: No optimizations applied	$0.900000Best Optimizations: No optimizations applied
Capabilities & Advanced Features
Images 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.

Claude Sonnet 4.6 Anthropic 1000000

$0.276000 (rounded ~ $0.28)

Total Cost

⚡ 20% Cached 🔧 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) $0.330000 Input: $0.300000
Output: $0.030000

Optimized Cost $0.276000 (rounded ~ $0.28) Input: $0.300000
Output: $0.030000
Unit: $0.000000
Fees: $0.000000

Total Savings $0.054000 (rounded ~ $0.05) 16.4% discount

Detailed Cost Analysis (from Plugin)

For 100,000 input tokens and 2,000 output tokens:

Input Cost: $0.300000
Output Cost: $0.030000
Total Cost: $0.276000 (rounded ~ $0.28)
Cost per 1K tokens: $0.002706
Tokens per dollar: 369,565 tokens
Context Window: 1000000 tokens

Speed & Performance Analysis

With a processing speed of 450 tokens per second and 200ms time to first token:

Processing Time: 4 minutes, 2.71 seconds
Latency: 200 milliseconds to first token
Base Throughput: 450 tokens/second
Effective Throughput: 421 tokens/second (temperature-adjusted)

Best Use Cases

Use Claude Sonnet 4.6 for complexnuanced code critiques and Devstral 2 for high-speedspecialized automated linting and PR summarization.

Want this applied to YOUR actual stack?

This calculator shows the math for Claude Sonnet 4.6. 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 →

Devstral 2 Mistral AI

$0.034600 (rounded ~ $0.03)

Total Cost

⚡ 20% Cached 🔧 Tools

👁️

Vision/Images

✗ Not 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) $0.041800 (rounded ~ $0.04) Input: $0.040000
Output: $0.001800

Optimized Cost $0.034600 (rounded ~ $0.03) Input: $0.040000
Output: $0.001800
Unit: $0.000000
Fees: $0.000000

Total Savings $0.007200 (rounded ~ $0.01) 17.2% discount

Detailed Cost Analysis (from Plugin)

For 100,000 input tokens and 2,000 output tokens:

Input Cost: $0.040000
Output Cost: $0.001800
Total Cost: $0.034600 (rounded ~ $0.03)
Cost per 1K tokens: $0.000339
Tokens per dollar: 2,947,977 tokens
Context Window: 256000 tokens

Speed & Performance Analysis

With a processing speed of 450 tokens per second and 180ms time to first token:

Processing Time: 4 minutes, 2.71 seconds
Latency: 180 milliseconds to first token
Base Throughput: 450 tokens/second
Effective Throughput: 421 tokens/second (temperature-adjusted)

Best Use Cases

Use Claude Sonnet 4.6 for complexnuanced code critiques and Devstral 2 for high-speedspecialized automated linting and PR summarization.

Want this applied to YOUR actual stack?

This calculator shows the math for Devstral 2. 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 Claude Sonnet 4.6

📋 Active Input Parameters

Input Tokens: 100,000

Output Tokens: 2,000

Cached Tokens: 20%

Tools: Enabled

Rank	AI Model & Provider	Total Cost	vs Claude Sonnet 4.6	vs Devstral 2
🏆	Mistral Small 3 Mistral AI	$0.008800 (rounded ~ $0.01) Best Value	↓ 96.8% cheaper	↓ 74.6% cheaper
🥈	Grok Code Fast 1 xAI	$0.019400	↓ 93% cheaper	↓ 43.9% cheaper
🥉	Gemini 3.1 Flash Lite Google	$0.023500 (rounded ~ $0.02)	↓ 91.5% cheaper	↓ 32.1% cheaper
#4	Gemini 3.5 Flash-Lite Google	$0.029600	↓ 89.3% cheaper	↓ 14.5% cheaper
#5	Gemini 2.5 Flash Google	$0.029600	↓ 89.3% cheaper	↓ 14.5% cheaper
#6	Mistral Large 3 Mistral AI	$0.044000 (rounded ~ $0.04)	↓ 84.1% cheaper	↑ 27.2% more
#7	Gemini 3.1 Flash Google	$0.047000 (rounded ~ $0.05)	↓ 83% cheaper	↑ 35.8% more
#8	Kimi K2.5 Moonshot AI	$0.056040 (rounded ~ $0.06)	↓ 79.7% cheaper	↑ 62% more
#9	Gemini 3.8 Flash Google	$0.069000 (rounded ~ $0.07)	↓ 75% cheaper	↑ 99.4% more
#10	GPT-5.4 mini OpenAI	$0.070500	↓ 74.5% cheaper	↑ 103.8% more
#11	Grok Build 0.1 xAI	$0.086000 (rounded ~ $0.09)	↓ 68.8% cheaper	↑ 148.6% more
#12	Kimi K2.6 Moonshot AI	$0.087230 (rounded ~ $0.09)	↓ 68.4% cheaper	↑ 152.1% more
#13	Kimi K2.7 Code Moonshot AI	$0.087230 (rounded ~ $0.09)	↓ 68.4% cheaper	↑ 152.1% more
#14	o4-mini Deep Research OpenAI	$0.090000	↓ 67.4% cheaper	↑ 160.1% more
#15	Claude Haiku 4.5 Anthropic	$0.092000 (rounded ~ $0.09)	↓ 66.7% cheaper	↑ 165.9% more
#16	GPT-5.6 Luna OpenAI	$0.094000 (rounded ~ $0.09)	↓ 65.9% cheaper	↑ 171.7% more
#17	o4-mini OpenAI	$0.099000	↓ 64.1% cheaper	↑ 186.1% more
#18	Grok 4.3 xAI	$0.107500 (rounded ~ $0.11)	↓ 61.1% cheaper	↑ 210.7% more
#19	Grok 4.20 Beta xAI	$0.107500 (rounded ~ $0.11)	↓ 61.1% cheaper	↑ 210.7% more
#20	Gemini 2.5 Pro Google	$0.122500 (rounded ~ $0.12)	↓ 55.6% cheaper	↑ 254% more
#21	Gemini 3.6 Flash Google	$0.138000 (rounded ~ $0.14)	↓ 50% cheaper	↑ 298.8% more
#22	Gemini 3.5 Flash Google	$0.141000 (rounded ~ $0.14)	↓ 48.9% cheaper	↑ 307.5% more
#23	GPT-5.3 Codex Spark OpenAI	$0.171500 (rounded ~ $0.17)	↓ 37.9% cheaper	↑ 395.7% more
#24	GPT-5.3 Instant OpenAI	$0.171500 (rounded ~ $0.17)	↓ 37.9% cheaper	↑ 395.7% more
#25	Grok 4.6 xAI	$0.176000 (rounded ~ $0.18)	↓ 36.2% cheaper	↑ 408.7% more
#26	Grok 4.5 xAI	$0.176000 (rounded ~ $0.18)	↓ 36.2% cheaper	↑ 408.7% more
#27	Claude Sonnet 5 Anthropic	$0.184000 (rounded ~ $0.18)	↓ 33.3% cheaper	↑ 431.8% more
#28	Gemini 3.1 Pro Google	$0.188000 (rounded ~ $0.19)	↓ 31.9% cheaper	↑ 443.4% more
#29	GPT-5.4 OpenAI	$0.235000 (rounded ~ $0.24)	↓ 14.9% cheaper	↑ 579.2% more
#30	GPT-5.4 Thinking OpenAI	$0.235000 (rounded ~ $0.24)	↓ 14.9% cheaper	↑ 579.2% more
#31	GPT-5.6 Terra OpenAI	$0.235000 (rounded ~ $0.24)	↓ 14.9% cheaper	↑ 579.2% more
#32	Claude Opus 4.7 Anthropic	$0.460000	↑ 66.7% more	↑ 1229.5% more
#33	Claude Opus 5 Anthropic	$0.460000	↑ 66.7% more	↑ 1229.5% more
#34	Claude Opus 4.8 Anthropic	$0.460000	↑ 66.7% more	↑ 1229.5% more
#35	Claude Opus 4.6 Anthropic	$0.460000	↑ 66.7% more	↑ 1229.5% more
#36	GPT-5.5 OpenAI	$0.470000	↑ 70.3% more	↑ 1258.4% more
#37	GPT-5.5 Instant OpenAI	$0.470000	↑ 70.3% more	↑ 1258.4% more
#38	GPT-5.6 Sol OpenAI	$0.470000	↑ 70.3% more	↑ 1258.4% more
#39	o3 Deep Research OpenAI	$0.900000	↑ 226.1% more	↑ 2501.2% more
#40	Claude Fable 5.1 Anthropic	$0.905000 (rounded ~ $0.91)	↑ 227.9% more	↑ 2515.6% more
#41	Claude Mythos 5.1 Anthropic	$0.905000 (rounded ~ $0.91)	↑ 227.9% more	↑ 2515.6% more
#42	Claude Fable 5 Anthropic	$0.920000	↑ 233.3% more	↑ 2559% more
#43	Claude Mythos 5 Anthropic	$0.920000	↑ 233.3% more	↑ 2559% more
#44	GPT-6 Astra OpenAI	$0.920000	↑ 233.3% more	↑ 2559% more
#45	o3 Pro OpenAI	$1.800000	↑ 552.2% more	↑ 5102.3% more
#46	GPT-5.2 Pro OpenAI	$2.058000 (rounded ~ $2.06)	↑ 645.7% more	↑ 5848% more
#47	GPT-5.2 Pro OpenAI	$2.058000 (rounded ~ $2.06)	↑ 645.7% more	↑ 5848% more

🏆

Mistral Small 3
Mistral AI

$0.008800 (rounded ~ $0.01)

vs Claude Sonnet 4.6: ↓ 96.8%

vs Devstral 2: ↓ 74.6%

🥈

Grok Code Fast 1
xAI

$0.019400

vs Claude Sonnet 4.6: ↓ 93%

vs Devstral 2: ↓ 43.9%

🥉

Gemini 3.1 Flash Lite
Google

$0.023500 (rounded ~ $0.02)

vs Claude Sonnet 4.6: ↓ 91.5%

vs Devstral 2: ↓ 32.1%

Gemini 3.5 Flash-Lite
Google

$0.029600

vs Claude Sonnet 4.6: ↓ 89.3%

vs Devstral 2: ↓ 14.5%

Gemini 2.5 Flash
Google

$0.029600

vs Claude Sonnet 4.6: ↓ 89.3%

vs Devstral 2: ↓ 14.5%

Mistral Large 3
Mistral AI

$0.044000 (rounded ~ $0.04)

vs Claude Sonnet 4.6: ↓ 84.1%

vs Devstral 2: ↑ 27.2%

Gemini 3.1 Flash
Google

$0.047000 (rounded ~ $0.05)

vs Claude Sonnet 4.6: ↓ 83%

vs Devstral 2: ↑ 35.8%

Kimi K2.5
Moonshot AI

$0.056040 (rounded ~ $0.06)

vs Claude Sonnet 4.6: ↓ 79.7%

vs Devstral 2: ↑ 62%

Gemini 3.8 Flash
Google

$0.069000 (rounded ~ $0.07)

vs Claude Sonnet 4.6: ↓ 75%

vs Devstral 2: ↑ 99.4%

#10

GPT-5.4 mini
OpenAI

$0.070500

vs Claude Sonnet 4.6: ↓ 74.5%

vs Devstral 2: ↑ 103.8%

#11

Grok Build 0.1
xAI

$0.086000 (rounded ~ $0.09)

vs Claude Sonnet 4.6: ↓ 68.8%

vs Devstral 2: ↑ 148.6%

#12

Kimi K2.6
Moonshot AI

$0.087230 (rounded ~ $0.09)

vs Claude Sonnet 4.6: ↓ 68.4%

vs Devstral 2: ↑ 152.1%

#13

Kimi K2.7 Code
Moonshot AI

$0.087230 (rounded ~ $0.09)

vs Claude Sonnet 4.6: ↓ 68.4%

vs Devstral 2: ↑ 152.1%

#14

o4-mini Deep Research
OpenAI

$0.090000

vs Claude Sonnet 4.6: ↓ 67.4%

vs Devstral 2: ↑ 160.1%

#15

Claude Haiku 4.5
Anthropic

$0.092000 (rounded ~ $0.09)

vs Claude Sonnet 4.6: ↓ 66.7%

vs Devstral 2: ↑ 165.9%

#16

GPT-5.6 Luna
OpenAI

$0.094000 (rounded ~ $0.09)

vs Claude Sonnet 4.6: ↓ 65.9%

vs Devstral 2: ↑ 171.7%

#17

o4-mini
OpenAI

$0.099000

vs Claude Sonnet 4.6: ↓ 64.1%

vs Devstral 2: ↑ 186.1%

#18

Grok 4.3
xAI

$0.107500 (rounded ~ $0.11)

vs Claude Sonnet 4.6: ↓ 61.1%

vs Devstral 2: ↑ 210.7%

#19

Grok 4.20 Beta
xAI

$0.107500 (rounded ~ $0.11)

vs Claude Sonnet 4.6: ↓ 61.1%

vs Devstral 2: ↑ 210.7%

#20

Gemini 2.5 Pro
Google

$0.122500 (rounded ~ $0.12)

vs Claude Sonnet 4.6: ↓ 55.6%

vs Devstral 2: ↑ 254%

#21

Gemini 3.6 Flash
Google

$0.138000 (rounded ~ $0.14)

vs Claude Sonnet 4.6: ↓ 50%

vs Devstral 2: ↑ 298.8%

#22

Gemini 3.5 Flash
Google

$0.141000 (rounded ~ $0.14)

vs Claude Sonnet 4.6: ↓ 48.9%

vs Devstral 2: ↑ 307.5%

#23

GPT-5.3 Codex Spark
OpenAI

$0.171500 (rounded ~ $0.17)

vs Claude Sonnet 4.6: ↓ 37.9%

vs Devstral 2: ↑ 395.7%

#24

GPT-5.3 Instant
OpenAI

$0.171500 (rounded ~ $0.17)

vs Claude Sonnet 4.6: ↓ 37.9%

vs Devstral 2: ↑ 395.7%

#25

Grok 4.6
xAI

$0.176000 (rounded ~ $0.18)

vs Claude Sonnet 4.6: ↓ 36.2%

vs Devstral 2: ↑ 408.7%

#26

Grok 4.5
xAI

$0.176000 (rounded ~ $0.18)

vs Claude Sonnet 4.6: ↓ 36.2%

vs Devstral 2: ↑ 408.7%

#27

Claude Sonnet 5
Anthropic

$0.184000 (rounded ~ $0.18)

vs Claude Sonnet 4.6: ↓ 33.3%

vs Devstral 2: ↑ 431.8%

#28

Gemini 3.1 Pro
Google

$0.188000 (rounded ~ $0.19)

vs Claude Sonnet 4.6: ↓ 31.9%

vs Devstral 2: ↑ 443.4%

#29

GPT-5.4
OpenAI

$0.235000 (rounded ~ $0.24)

vs Claude Sonnet 4.6: ↓ 14.9%

vs Devstral 2: ↑ 579.2%

#30

GPT-5.4 Thinking
OpenAI

$0.235000 (rounded ~ $0.24)

vs Claude Sonnet 4.6: ↓ 14.9%

vs Devstral 2: ↑ 579.2%

#31

GPT-5.6 Terra
OpenAI

$0.235000 (rounded ~ $0.24)

vs Claude Sonnet 4.6: ↓ 14.9%

vs Devstral 2: ↑ 579.2%

#32

Claude Opus 4.7
Anthropic

$0.460000

vs Claude Sonnet 4.6: ↑ 66.7%

vs Devstral 2: ↑ 1229.5%

#33

Claude Opus 5
Anthropic

$0.460000

vs Claude Sonnet 4.6: ↑ 66.7%

vs Devstral 2: ↑ 1229.5%

#34

Claude Opus 4.8
Anthropic

$0.460000

vs Claude Sonnet 4.6: ↑ 66.7%

vs Devstral 2: ↑ 1229.5%

#35

Claude Opus 4.6
Anthropic

$0.460000

vs Claude Sonnet 4.6: ↑ 66.7%

vs Devstral 2: ↑ 1229.5%

#36

GPT-5.5
OpenAI

$0.470000

vs Claude Sonnet 4.6: ↑ 70.3%

vs Devstral 2: ↑ 1258.4%

#37

GPT-5.5 Instant
OpenAI

$0.470000

vs Claude Sonnet 4.6: ↑ 70.3%

vs Devstral 2: ↑ 1258.4%

#38

GPT-5.6 Sol
OpenAI

$0.470000

vs Claude Sonnet 4.6: ↑ 70.3%

vs Devstral 2: ↑ 1258.4%

#39

o3 Deep Research
OpenAI

$0.900000

vs Claude Sonnet 4.6: ↑ 226.1%

vs Devstral 2: ↑ 2501.2%

#40

Claude Fable 5.1
Anthropic

$0.905000 (rounded ~ $0.91)

vs Claude Sonnet 4.6: ↑ 227.9%

vs Devstral 2: ↑ 2515.6%

#41

Claude Mythos 5.1
Anthropic

$0.905000 (rounded ~ $0.91)

vs Claude Sonnet 4.6: ↑ 227.9%

vs Devstral 2: ↑ 2515.6%

#42

Claude Fable 5
Anthropic

$0.920000

vs Claude Sonnet 4.6: ↑ 233.3%

vs Devstral 2: ↑ 2559%

#43

Claude Mythos 5
Anthropic

$0.920000

vs Claude Sonnet 4.6: ↑ 233.3%

vs Devstral 2: ↑ 2559%

#44

GPT-6 Astra
OpenAI

$0.920000

vs Claude Sonnet 4.6: ↑ 233.3%

vs Devstral 2: ↑ 2559%

#45

o3 Pro
OpenAI

$1.800000

vs Claude Sonnet 4.6: ↑ 552.2%

vs Devstral 2: ↑ 5102.3%

#46

GPT-5.2 Pro
OpenAI

$2.058000 (rounded ~ $2.06)

vs Claude Sonnet 4.6: ↑ 645.7%

vs Devstral 2: ↑ 5848%

#47

GPT-5.2 Pro
OpenAI

$2.058000 (rounded ~ $2.06)

vs Claude Sonnet 4.6: ↑ 645.7%

vs Devstral 2: ↑ 5848%

✨ 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 an indie developer building a code review assistant, the choice between Claude Sonnet 4.6 and Devstral 2 hinges on the balance between frontier-level reasoning and specialized developer workflow optimization. Code reviews for large diffs require not just syntax checking, but a deep understanding of architectural impact, security vulnerabilities, and logical flow across multiple files.

Claude Sonnet 4.6 is widely recognized for its exceptional instruction following and ability to synthesize complex, multi-file changes into actionable feedback. When your pull requests reach the 100K-token scale, its large context window ensures that it maintains consistent oversight of file states and definitions, which is critical for identifying subtle bugs in large-scale refactors or new feature implementations. It excels at providing natural, explanatory critiques that feel like a senior engineer’s review.

On the other hand, Devstral 2 represents a more focused, specialized approach to the developer lifecycle. If your assistant’s primary goal is rapid integration into a CI/CD pipeline where latency is the bottleneck, Devstral 2’s architecture is specifically tuned to recognize code patterns, common boilerplate, and programming pitfalls with high throughput. It is designed to handle multi-file orchestration, allowing it to navigate codebase dependencies effectively without the computational overhead of more generalized reasoning models.

Choosing between these two depends on your UI and user experience goals. If your assistant provides deep, conversational, and explanatory critiques, Claude Sonnet 4.6 provides a more human-like interaction. If you are building a snappy, automated linter-on-steroids, Devstral 2 offers a more specialized path. Prototyping with both is recommended to see which aligns better with your specific codebase and feedback style.

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.

Code Review Efficiency: Claude Sonnet 4.6 vs Devstral 2 for 100K-Token PR Diffs

🔄 Compare Different AI Models

First Model

Second Model

Select AI Model

Claude Sonnet 4.6

Calculate Token Costs

📊 Advanced Cost Breakdown

Processing Speed

Model Comparison

Model Information

🔄 Advanced Options

⚡ Optimization

🧠 Reasoning & Thinking

🔧 Special Modes

📚 Research & Citations

🎤 Realtime Audio & Video

Claude Sonnet 4.6 Anthropic 1000000

💰 Total Cost Calculation (from Plugin)

Detailed Cost Analysis (from Plugin)

Speed & Performance Analysis

Best Use Cases

Want this applied to YOUR actual stack?

Devstral 2 Mistral AI

💰 Total Cost Calculation (from Plugin)

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

Grok Code Fast 1 xAI

Gemini 3.1 Flash Lite Google

Gemini 3.5 Flash-Lite Google

Gemini 2.5 Flash Google

Mistral Large 3 Mistral AI

Gemini 3.1 Flash Google

Kimi K2.5 Moonshot AI

Gemini 3.8 Flash Google

GPT-5.4 mini OpenAI

Grok Build 0.1 xAI

Kimi K2.6 Moonshot AI

Kimi K2.7 Code Moonshot AI

o4-mini Deep Research OpenAI

Claude Haiku 4.5 Anthropic

GPT-5.6 Luna OpenAI

o4-mini OpenAI

Grok 4.3 xAI

Grok 4.20 Beta xAI

Gemini 2.5 Pro Google

Gemini 3.6 Flash Google

Gemini 3.5 Flash Google

GPT-5.3 Codex Spark OpenAI

GPT-5.3 Instant OpenAI

Grok 4.6 xAI

Grok 4.5 xAI

Claude Sonnet 5 Anthropic

Gemini 3.1 Pro Google

GPT-5.4 OpenAI

GPT-5.4 Thinking OpenAI

GPT-5.6 Terra OpenAI

Claude Opus 4.7 Anthropic

Claude Opus 5 Anthropic

Claude Opus 4.8 Anthropic

Claude Opus 4.6 Anthropic

GPT-5.5 OpenAI

GPT-5.5 Instant OpenAI

GPT-5.6 Sol OpenAI

o3 Deep Research OpenAI

Claude Fable 5.1 Anthropic

Claude Mythos 5.1 Anthropic

Claude Fable 5 Anthropic

Claude Mythos 5 Anthropic

GPT-6 Astra OpenAI

o3 Pro OpenAI

GPT-5.2 Pro OpenAI

GPT-5.2 Pro OpenAI

Frequently Asked Questions

Related model pricing

Compare across providers

Mistral Small 3
Mistral AI

Grok Code Fast 1
xAI

Gemini 3.1 Flash Lite
Google

Gemini 3.5 Flash-Lite
Google

Gemini 2.5 Flash
Google

Mistral Large 3
Mistral AI

Gemini 3.1 Flash
Google

Kimi K2.5
Moonshot AI

Gemini 3.8 Flash
Google

GPT-5.4 mini
OpenAI

Grok Build 0.1
xAI

Kimi K2.6
Moonshot AI

Kimi K2.7 Code
Moonshot AI

o4-mini Deep Research
OpenAI

Claude Haiku 4.5
Anthropic

GPT-5.6 Luna
OpenAI

o4-mini
OpenAI

Grok 4.3
xAI

Grok 4.20 Beta
xAI

Gemini 2.5 Pro
Google

Gemini 3.6 Flash
Google

Gemini 3.5 Flash
Google

GPT-5.3 Codex Spark
OpenAI

GPT-5.3 Instant
OpenAI

Grok 4.6
xAI

Grok 4.5
xAI

Claude Sonnet 5
Anthropic

Gemini 3.1 Pro
Google

GPT-5.4
OpenAI

GPT-5.4 Thinking
OpenAI

GPT-5.6 Terra
OpenAI

Claude Opus 4.7
Anthropic

Claude Opus 5
Anthropic

Claude Opus 4.8
Anthropic

Claude Opus 4.6
Anthropic

GPT-5.5
OpenAI

GPT-5.5 Instant
OpenAI

GPT-5.6 Sol
OpenAI

o3 Deep Research
OpenAI

Claude Fable 5.1
Anthropic

Claude Mythos 5.1
Anthropic

Claude Fable 5
Anthropic

Claude Mythos 5
Anthropic

GPT-6 Astra
OpenAI

o3 Pro
OpenAI

GPT-5.2 Pro
OpenAI

GPT-5.2 Pro
OpenAI