Claude Sonnet 4.6 vs Gemini 3.1 Pro for 50M-Token Multi-Agent Workflows

Claude Sonnet 4.6 has been replaced by Claude Sonnet 5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 Gemini 3.1 Pro
Complete Comparison: 50,000 input tokens × 800 output tokens
Comparison Mode
⚡ 60% Cached

Complete comparison of pricing, performance, and capabilities for 2 leading AI models with 60% Cached.

⚡ Caching Optimized (up to 90% savings) 📊 Batch API
Comparison Criteria Claude Sonnet 4.6
Anthropic
Gemini 3.1 Pro
Google
Calculation Results (Current Inputs) (60% cached)
Input Tokens 50,000 50,000
Output Tokens 800 800
Cost Breakdown
Input Cost $0.037500 (rounded ~ $0.04)Best $0.050000Worst
Output Cost $0.003000Best $0.004800Worst
Unit Cost (Audio/OCR) $0.000000 $0.000000
Service Fees $0.000000 $0.000000
Total Cost $0.020250 Best Value $0.027800 (rounded ~ $0.03) Most Expensive
Processing Time 2 minutes, 0.97 seconds Fastest 2 minutes, 16.07 seconds Slowest
Tokens per Second 450Fastest 400Slowest
Time to First Token 200ms Best 220ms Worst
Cost per 1K tokens $0.000399Best $0.000547Worst
Tokens per Dollar 2,508,642Best Value 1,827,338Worst Value
Cost per 1 Million Tokens (Informational)
Input Cost / 1M (Base) $0.750000Best $1.000000Worst
Output Cost / 1M (Base) $3.750000Best $6.000000Worst
Input Cost / 1M (Optimized) $0.375000 (rounded ~ $0.38)Best
Optimizations: 50.0% batch
$0.500000Worst
Optimizations: 50.0% batch
Output Cost / 1M (Optimized) $1.875000 (rounded ~ $1.88)Best
Optimizations: 50.0% batch
$3.000000Worst
Optimizations: 50.0% batch
Capabilities & Advanced Features
Images Support ✓ Supported ✓ Supported
Video Support ✗ Not Supported ✓ Supported
Audio Support ✗ Not Supported ✓ Supported
Caching Support
60
✓ Supported ✓ Supported
Batch API Support ✓ Supported ✓ Supported
Tool Usage Support ✓ Supported ✓ Supported
Scroll horizontally to see all data

🔄 Compare Different AI Models

1

First Model

2

Second Model

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

Click Recalculate to update after making changes

Select AI Model

Claude Sonnet 4.6
AnthropicMax Context: 1,000,000 tokens
$3 / $15 per 1M tokens
▼
▼
Use Batch API (50% discount)
60%
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

$0.020250 Total Cost
$0.015000 Input Cost
$0.003000 Output Cost
$0.000000 Unit Cost
$0.000000 Search Cost
$0.000000 Request Fee
$0.000000 Tool Fee
$0.000000 Code Execution
50,800Total Tokens
$0.000399Cost per 1K
2,508,642Tokens per $
📊 Advanced Cost Breakdown

Processing Speed

2m 0s Processing Time
450 Tokens/Second
200ms Time to First Token
421 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
📊 Multiple Models Detected: This page contains data for 2 models. See the detailed comparison table above, and switch between models using tabs below.

Claude Sonnet 4.6 Anthropic 1000000

$0.020250
Total Cost
⚡ 60% 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) $0.040500 Input: $0.037500 (rounded ~ $0.04)
Output: $0.003000
Optimized Cost $0.020250 Input: $0.037500 (rounded ~ $0.04)
Output: $0.003000
Unit: $0.000000
Fees: $0.000000
Total Savings $0.020250 50.0% discount

Advanced Cost Breakdown (from Plugin)

📊 Batch API
50.0% off
Asynchronous processing discount

Detailed Cost Analysis (from Plugin)

For 50,000 input tokens and 800 output tokens:

  • Input Cost: $0.037500 (rounded ~ $0.04)
  • Output Cost: $0.003000
  • Total Cost: $0.020250
  • Cost per 1K tokens: $0.000399
  • Tokens per dollar: 2,508,642 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: 2 minutes, 0.97 seconds
  • Latency: 200 milliseconds to first token
  • Base Throughput: 450 tokens/second
  • Effective Throughput: 421 tokens/second (temperature-adjusted)

Best Use Cases

Claude Sonnet 4.6 for complex executor agents; Gemini 3.1 Pro for high-context analyst agents.

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 →

Gemini 3.1 Pro Google 1000000

$0.027800 (rounded ~ $0.03)
Total Cost
⚡ 60% 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) $0.054800 (rounded ~ $0.05) Input: $0.050000
Output: $0.004800
Optimized Cost $0.027800 (rounded ~ $0.03) Input: $0.050000
Output: $0.004800
Unit: $0.000000
Fees: $0.000000
Total Savings $0.027000 (rounded ~ $0.03) 49.3% discount

Advanced Cost Breakdown (from Plugin)

📊 Batch API
50.0% off
Asynchronous processing discount
📊 Dynamic Tier
Standard
tier1 pricing based on 0 tokens

Detailed Cost Analysis (from Plugin)

For 50,000 input tokens and 800 output tokens:

  • Input Cost: $0.050000
  • Output Cost: $0.004800
  • Total Cost: $0.027800 (rounded ~ $0.03)
  • Cost per 1K tokens: $0.000547
  • Tokens per dollar: 1,827,338 tokens
  • Context Window: 1000000 tokens

Speed & Performance Analysis

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

  • Processing Time: 2 minutes, 16.07 seconds
  • Latency: 220 milliseconds to first token
  • Base Throughput: 400 tokens/second
  • Effective Throughput: 374 tokens/second (temperature-adjusted)

Best Use Cases

Claude Sonnet 4.6 for complex executor agents; Gemini 3.1 Pro for high-context analyst agents.

Want this applied to YOUR actual stack?

This calculator shows the math for Gemini 3.1 Pro. 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: 50,000
Output Tokens: 800
Batch API: Enabled (50% discount)
Cached Tokens: 60%
Tools: Enabled
Rank AI Model & Provider Total Cost vs Claude Sonnet 4.6 vs Gemini 3.1 Pro
🏆 Mistral Small 3
Mistral AI
 $0.000635 Best Value ↓ 96.9% cheaper ↓ 97.7% cheaper
🥈 Gemini 3.1 Flash Lite
Google
 $0.001738 ↓ 91.4% cheaper ↓ 93.8% cheaper
🥉 Gemini 3.5 Flash-Lite
Google
 $0.002225 ↓ 89% cheaper ↓ 92% cheaper
#4 Gemini 2.5 Flash
Google
 $0.002225 ↓ 89% cheaper ↓ 92% cheaper
#5 Mistral Large 3
Mistral AI
 $0.003175 ↓ 84.3% cheaper ↓ 88.6% cheaper
#6 Gemini 3.8 Flash
Google
 $0.005063 (rounded ~ $0.01) ↓ 75% cheaper ↓ 81.8% cheaper
#7 GPT-5.4 mini
OpenAI
 $0.005213 (rounded ~ $0.01) ↓ 74.3% cheaper ↓ 81.3% cheaper
#8 o4-mini Deep Research
OpenAI
 $0.006550 (rounded ~ $0.01) ↓ 67.7% cheaper ↓ 76.4% cheaper
#9 Claude Haiku 4.5
Anthropic
 $0.006750 (rounded ~ $0.01) ↓ 66.7% cheaper ↓ 75.7% cheaper
#10 Gemini 3.1 Flash
Google
 $0.006950 (rounded ~ $0.01) ↓ 65.7% cheaper ↓ 75% cheaper
#11 GPT-5.6 Luna
OpenAI
 $0.006950 (rounded ~ $0.01) ↓ 65.7% cheaper ↓ 75% cheaper
#12 o4-mini
OpenAI
 $0.007205 (rounded ~ $0.01) ↓ 64.4% cheaper ↓ 74.1% cheaper
#13 Gemini 3.6 Flash
Google
 $0.010125 ↓ 50% cheaper ↓ 63.6% cheaper
#14 Gemini 3.5 Flash
Google
 $0.010425 ↓ 48.5% cheaper ↓ 62.5% cheaper
#15 GPT-5.3 Codex Spark
OpenAI
 $0.012863 (rounded ~ $0.01) ↓ 36.5% cheaper ↓ 53.7% cheaper
#16 GPT-5.3 Instant
OpenAI
 $0.012863 (rounded ~ $0.01) ↓ 36.5% cheaper ↓ 53.7% cheaper
#17 Claude Sonnet 5
Anthropic
 $0.013500 (rounded ~ $0.01) ↓ 33.3% cheaper ↓ 51.4% cheaper
#18 GPT-5.6 Terra
OpenAI
 $0.017375 (rounded ~ $0.02) ↓ 14.2% cheaper ↓ 37.5% cheaper
#19 Gemini 2.5 Pro
Google
 $0.018375 (rounded ~ $0.02) ↓ 9.3% cheaper ↓ 33.9% cheaper
#20 Grok 4.3
xAI
 $0.024600 (rounded ~ $0.02) ↑ 21.5% more ↓ 11.5% cheaper
#21 Grok 4.20 Beta
xAI
 $0.024600 (rounded ~ $0.02) ↑ 21.5% more ↓ 11.5% cheaper
#22 Gemini 3.1 Pro
Google
 $0.027800 (rounded ~ $0.03) ↑ 37.3% more Same price
#23 Claude Opus 4.7
Anthropic
 $0.033750 (rounded ~ $0.03) ↑ 66.7% more ↑ 21.4% more
#24 Claude Opus 5
Anthropic
 $0.033750 (rounded ~ $0.03) ↑ 66.7% more ↑ 21.4% more
#25 Claude Opus 4.8
Anthropic
 $0.033750 (rounded ~ $0.03) ↑ 66.7% more ↑ 21.4% more
#26 Claude Opus 4.6
Anthropic
 $0.033750 (rounded ~ $0.03) ↑ 66.7% more ↑ 21.4% more
#27 GPT-5.4
OpenAI
 $0.034750 (rounded ~ $0.03) ↑ 71.6% more ↑ 25% more
#28 GPT-5.4 Thinking
OpenAI
 $0.034750 (rounded ~ $0.03) ↑ 71.6% more ↑ 25% more
#29 GPT-5.5 Instant
OpenAI
 $0.034750 (rounded ~ $0.03) ↑ 71.6% more ↑ 25% more
#30 GPT-5.6 Sol
OpenAI
 $0.034750 (rounded ~ $0.03) ↑ 71.6% more ↑ 25% more
#31 Claude Fable 5.1
Anthropic
 $0.061875 (rounded ~ $0.06) ↑ 205.6% more ↑ 122.6% more
#32 Claude Mythos 5.1
Anthropic
 $0.061875 (rounded ~ $0.06) ↑ 205.6% more ↑ 122.6% more
#33 o3 Deep Research
OpenAI
 $0.065500 (rounded ~ $0.07) ↑ 223.5% more ↑ 135.6% more
#34 Claude Fable 5
Anthropic
 $0.067500 (rounded ~ $0.07) ↑ 233.3% more ↑ 142.8% more
#35 Claude Mythos 5
Anthropic
 $0.067500 (rounded ~ $0.07) ↑ 233.3% more ↑ 142.8% more
#36 GPT-5.5
OpenAI
 $0.069500 ↑ 243.2% more ↑ 150% more
#37 o3 Pro
OpenAI
 $0.131000 (rounded ~ $0.13) ↑ 546.9% more ↑ 371.2% more
#38 GPT-6 Astra
OpenAI
 $0.135000 (rounded ~ $0.14) ↑ 566.7% more ↑ 385.6% more
#39 GPT-5.2 Pro
OpenAI
 $0.154350 (rounded ~ $0.15) ↑ 662.2% more ↑ 455.2% more
#40 GPT-5.2 Pro
OpenAI
 $0.154350 (rounded ~ $0.15) ↑ 662.2% more ↑ 455.2% more
🏆

Mistral Small 3
Mistral AI

$0.000635
vs Claude Sonnet 4.6: ↓ 96.9%
vs Gemini 3.1 Pro: ↓ 97.7%
🥈

Gemini 3.1 Flash Lite
Google

$0.001738
vs Claude Sonnet 4.6: ↓ 91.4%
vs Gemini 3.1 Pro: ↓ 93.8%
🥉

Gemini 3.5 Flash-Lite
Google

$0.002225
vs Claude Sonnet 4.6: ↓ 89%
vs Gemini 3.1 Pro: ↓ 92%
#4

Gemini 2.5 Flash
Google

$0.002225
vs Claude Sonnet 4.6: ↓ 89%
vs Gemini 3.1 Pro: ↓ 92%
#5

Mistral Large 3
Mistral AI

$0.003175
vs Claude Sonnet 4.6: ↓ 84.3%
vs Gemini 3.1 Pro: ↓ 88.6%
#6

Gemini 3.8 Flash
Google

$0.005063 (rounded ~ $0.01)
vs Claude Sonnet 4.6: ↓ 75%
vs Gemini 3.1 Pro: ↓ 81.8%
#7

GPT-5.4 mini
OpenAI

$0.005213 (rounded ~ $0.01)
vs Claude Sonnet 4.6: ↓ 74.3%
vs Gemini 3.1 Pro: ↓ 81.3%
#8

o4-mini Deep Research
OpenAI

$0.006550 (rounded ~ $0.01)
vs Claude Sonnet 4.6: ↓ 67.7%
vs Gemini 3.1 Pro: ↓ 76.4%
#9

Claude Haiku 4.5
Anthropic

$0.006750 (rounded ~ $0.01)
vs Claude Sonnet 4.6: ↓ 66.7%
vs Gemini 3.1 Pro: ↓ 75.7%
#10

Gemini 3.1 Flash
Google

$0.006950 (rounded ~ $0.01)
vs Claude Sonnet 4.6: ↓ 65.7%
vs Gemini 3.1 Pro: ↓ 75%
#11

GPT-5.6 Luna
OpenAI

$0.006950 (rounded ~ $0.01)
vs Claude Sonnet 4.6: ↓ 65.7%
vs Gemini 3.1 Pro: ↓ 75%
#12

o4-mini
OpenAI

$0.007205 (rounded ~ $0.01)
vs Claude Sonnet 4.6: ↓ 64.4%
vs Gemini 3.1 Pro: ↓ 74.1%
#13

Gemini 3.6 Flash
Google

$0.010125
vs Claude Sonnet 4.6: ↓ 50%
vs Gemini 3.1 Pro: ↓ 63.6%
#14

Gemini 3.5 Flash
Google

$0.010425
vs Claude Sonnet 4.6: ↓ 48.5%
vs Gemini 3.1 Pro: ↓ 62.5%
#15

GPT-5.3 Codex Spark
OpenAI

$0.012863 (rounded ~ $0.01)
vs Claude Sonnet 4.6: ↓ 36.5%
vs Gemini 3.1 Pro: ↓ 53.7%
#16

GPT-5.3 Instant
OpenAI

$0.012863 (rounded ~ $0.01)
vs Claude Sonnet 4.6: ↓ 36.5%
vs Gemini 3.1 Pro: ↓ 53.7%
#17

Claude Sonnet 5
Anthropic

$0.013500 (rounded ~ $0.01)
vs Claude Sonnet 4.6: ↓ 33.3%
vs Gemini 3.1 Pro: ↓ 51.4%
#18

GPT-5.6 Terra
OpenAI

$0.017375 (rounded ~ $0.02)
vs Claude Sonnet 4.6: ↓ 14.2%
vs Gemini 3.1 Pro: ↓ 37.5%
#19

Gemini 2.5 Pro
Google

$0.018375 (rounded ~ $0.02)
vs Claude Sonnet 4.6: ↓ 9.3%
vs Gemini 3.1 Pro: ↓ 33.9%
#20

Grok 4.3
xAI

$0.024600 (rounded ~ $0.02)
vs Claude Sonnet 4.6: ↑ 21.5%
vs Gemini 3.1 Pro: ↓ 11.5%
#21

Grok 4.20 Beta
xAI

$0.024600 (rounded ~ $0.02)
vs Claude Sonnet 4.6: ↑ 21.5%
vs Gemini 3.1 Pro: ↓ 11.5%
#22

Gemini 3.1 Pro
Google

$0.027800 (rounded ~ $0.03)
vs Claude Sonnet 4.6: ↑ 37.3%
vs Gemini 3.1 Pro: Same
#23

Claude Opus 4.7
Anthropic

$0.033750 (rounded ~ $0.03)
vs Claude Sonnet 4.6: ↑ 66.7%
vs Gemini 3.1 Pro: ↑ 21.4%
#24

Claude Opus 5
Anthropic

$0.033750 (rounded ~ $0.03)
vs Claude Sonnet 4.6: ↑ 66.7%
vs Gemini 3.1 Pro: ↑ 21.4%
#25

Claude Opus 4.8
Anthropic

$0.033750 (rounded ~ $0.03)
vs Claude Sonnet 4.6: ↑ 66.7%
vs Gemini 3.1 Pro: ↑ 21.4%
#26

Claude Opus 4.6
Anthropic

$0.033750 (rounded ~ $0.03)
vs Claude Sonnet 4.6: ↑ 66.7%
vs Gemini 3.1 Pro: ↑ 21.4%
#27

GPT-5.4
OpenAI

$0.034750 (rounded ~ $0.03)
vs Claude Sonnet 4.6: ↑ 71.6%
vs Gemini 3.1 Pro: ↑ 25%
#28

GPT-5.4 Thinking
OpenAI

$0.034750 (rounded ~ $0.03)
vs Claude Sonnet 4.6: ↑ 71.6%
vs Gemini 3.1 Pro: ↑ 25%
#29

GPT-5.5 Instant
OpenAI

$0.034750 (rounded ~ $0.03)
vs Claude Sonnet 4.6: ↑ 71.6%
vs Gemini 3.1 Pro: ↑ 25%
#30

GPT-5.6 Sol
OpenAI

$0.034750 (rounded ~ $0.03)
vs Claude Sonnet 4.6: ↑ 71.6%
vs Gemini 3.1 Pro: ↑ 25%
#31

Claude Fable 5.1
Anthropic

$0.061875 (rounded ~ $0.06)
vs Claude Sonnet 4.6: ↑ 205.6%
vs Gemini 3.1 Pro: ↑ 122.6%
#32

Claude Mythos 5.1
Anthropic

$0.061875 (rounded ~ $0.06)
vs Claude Sonnet 4.6: ↑ 205.6%
vs Gemini 3.1 Pro: ↑ 122.6%
#33

o3 Deep Research
OpenAI

$0.065500 (rounded ~ $0.07)
vs Claude Sonnet 4.6: ↑ 223.5%
vs Gemini 3.1 Pro: ↑ 135.6%
#34

Claude Fable 5
Anthropic

$0.067500 (rounded ~ $0.07)
vs Claude Sonnet 4.6: ↑ 233.3%
vs Gemini 3.1 Pro: ↑ 142.8%
#35

Claude Mythos 5
Anthropic

$0.067500 (rounded ~ $0.07)
vs Claude Sonnet 4.6: ↑ 233.3%
vs Gemini 3.1 Pro: ↑ 142.8%
#36

GPT-5.5
OpenAI

$0.069500
vs Claude Sonnet 4.6: ↑ 243.2%
vs Gemini 3.1 Pro: ↑ 150%
#37

o3 Pro
OpenAI

$0.131000 (rounded ~ $0.13)
vs Claude Sonnet 4.6: ↑ 546.9%
vs Gemini 3.1 Pro: ↑ 371.2%
#38

GPT-6 Astra
OpenAI

$0.135000 (rounded ~ $0.14)
vs Claude Sonnet 4.6: ↑ 566.7%
vs Gemini 3.1 Pro: ↑ 385.6%
#39

GPT-5.2 Pro
OpenAI

$0.154350 (rounded ~ $0.15)
vs Claude Sonnet 4.6: ↑ 662.2%
vs Gemini 3.1 Pro: ↑ 455.2%
#40

GPT-5.2 Pro
OpenAI

$0.154350 (rounded ~ $0.15)
vs Claude Sonnet 4.6: ↑ 662.2%
vs Gemini 3.1 Pro: ↑ 455.2%
✨ 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.

As multi-agent systems move from experimental pilots to production, engineers must decide between Claude Sonnet 4.6 and Gemini 3.1 Pro for high-throughput orchestration. Claude Sonnet 4.6 is widely favored for agentic workflows involving complex tool use and reliable instruction following, making it a robust default for implementor agents within a pipeline. Developers often select Sonnet 4.6 when the priority is consistent, high-quality output that minimizes hallucination in multi-step chains. Conversely, Gemini 3.1 Pro stands out for workflows requiring massive context handling or native multimodal ingestion. Its efficiency in large-scale context retrieval makes it a powerful choice for agents that need to process extensive documentation, call logs, or long-running conversation histories in a single pass. For voice teams, Gemini’s ability to process audio and video inputs natively provides a latency advantage by avoiding complex transcoding pipelines. However, teams building modular orchestrators that rely heavily on ‘agent-to-agent’ chatter often find Sonnet’s latency consistency and structured output more predictable for integration. When designing for 50 million tokens, the choice often hinges on whether your agents act more as ‘analysts’ (favoring Gemini’s context) or ‘executors’ (favoring Sonnet’s tool-calling precision). Both models support the 1M-token context windows essential for maintaining long-term agent memory without frequent re-summarization.

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

Claude Sonnet 4.6 currently costs $3.00 / $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 →