Claude Sonnet 5 Pricing: 8K-Token Customer Support Sessions

Claude Sonnet 5 has been replaced by Claude Sonnet 5.5

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 5.5 pricing →  ·  All recent pricing changes

Complete Analysis: 10,000 tokens for Claude Sonnet 5
⚡ 30% Cached

Complete analysis of pricing, performance, and use cases for Anthropic's Claude Sonnet 5 model with 30% Cached.

⚡ Caching Optimized (up to 90% savings)
$0.031680 (rounded ~ $0.03) Total Cost
10,000 Total Tokens
23.44 seconds Processing Time
430 Effective Tokens/Sec

Click Recalculate to update after making changes

Select AI Model

Claude Sonnet 5

AnthropicMax Context: 1,000,000 tokens
$2 / $10 per 1M tokens
30%
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

$0.031680 Total Cost
$0.011200 Input Cost
$0.020000 Output Cost
$0.000000 Unit Cost
$0.000000 Search Cost
$0.000000 Request Fee
$0.000000 Tool Fee
$0.000000 Code Execution
10,000Total Tokens
$0.003168Cost per 1K
315,657Tokens per $

📊 Advanced Cost Breakdown

Processing Speed

23.44s Processing Time
460 Tokens/Second
195ms Time to First Token
430 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

📚 Research & Citations

Fee per source cited

🎤 Realtime Audio & Video

Session length for billing

Claude Sonnet 5 Anthropic 1000000

$0.031680 (rounded ~ $0.03)
Total Cost
⚡ 30% 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) $0.036000 (rounded ~ $0.04) Input: $0.016000 (rounded ~ $0.02)
Output: $0.020000
Optimized Cost $0.031680 (rounded ~ $0.03) Input: $0.016000 (rounded ~ $0.02)
Output: $0.020000
Unit: $0.000000
Fees: $0.000000
Total Savings $0.004320 12.0% discount

Detailed Cost Analysis (from Plugin)

For 8,000 input tokens and 2,000 output tokens:

  • Input Cost: $0.016000 (rounded ~ $0.02)
  • Output Cost: $0.020000
  • Total Cost: $0.031680 (rounded ~ $0.03)
  • Cost per 1K tokens: $0.003168
  • Tokens per dollar: 315,657 tokens
  • Context Window: 1000000 tokens

Speed & Performance Analysis

With a processing speed of 460 tokens per second and 195ms time to first token:

  • Processing Time: 23.44 seconds
  • Latency: 195 milliseconds to first token
  • Base Throughput: 460 tokens/second
  • Effective Throughput: 430 tokens/second (temperature-adjusted)

Best Use Cases

Best for high-stakes customer support where consistent tone and complex instruction following are required.

Want this applied to YOUR actual stack?

This calculator shows the math for Claude Sonnet 5. 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 5
📋 Active Input Parameters
Input Tokens: 8,000
Output Tokens: 2,000
Cached Tokens: 30%
Tools: Enabled
Rank AI Model & Provider Total Cost vs Claude Sonnet 5
🏆 Claude Haiku 5.5
Anthropic
 $0.001584 Best Value ↓ 95% cheaper
🥈 GPT-6 Luna
OpenAI
 $0.001584 ↓ 95% cheaper
🥉 GPT-5.6 Luna
OpenAI
 $0.003568 ↓ 88.7% cheaper
#4 Grok Code Fast 1
xAI
 $0.004168 ↓ 86.8% cheaper
#5 Gemini 3.1 Flash Lite
Google
 $0.004460 ↓ 85.9% cheaper
#6 Mistral Large 3
Mistral AI
 $0.005920 (rounded ~ $0.01) ↓ 81.3% cheaper
#7 Gemini 3.5 Flash-Lite
Google
 $0.006752 (rounded ~ $0.01) ↓ 78.7% cheaper
#8 Gemini 2.5 Flash
Google
 $0.006752 (rounded ~ $0.01) ↓ 78.7% cheaper
#9 Gemini 3.1 Flash
Google
 $0.008920 (rounded ~ $0.01) ↓ 71.8% cheaper
#10 Grok Build 0.1
xAI
 $0.009840 ↓ 68.9% cheaper
#11 Gemini 3.8 Flash
Google
 $0.011880 (rounded ~ $0.01) ↓ 62.5% cheaper
#12 Gemini 3.6 Flash
Google
 $0.011880 (rounded ~ $0.01) ↓ 62.5% cheaper
#13 Grok 4.3
xAI
 $0.012300 (rounded ~ $0.01) ↓ 61.2% cheaper
#14 Grok 4.20 Beta
xAI
 $0.012300 (rounded ~ $0.01) ↓ 61.2% cheaper
#15 GPT-5.4 mini
OpenAI
 $0.013380 (rounded ~ $0.01) ↓ 57.8% cheaper
#16 Claude Haiku 4.5
Anthropic
 $0.015840 (rounded ~ $0.02) ↓ 50% cheaper
#17 Mistral Large 4
Mistral AI
 $0.016302 (rounded ~ $0.02) ↓ 48.5% cheaper
#18 Grok 4.7
xAI
 $0.023680 (rounded ~ $0.02) ↓ 25.3% cheaper
#19 Grok 4.6
xAI
 $0.023680 (rounded ~ $0.02) ↓ 25.3% cheaper
#20 Grok 4.5
xAI
 $0.023680 (rounded ~ $0.02) ↓ 25.3% cheaper
#21 Gemini 2.5 Pro
Google
 $0.027300 (rounded ~ $0.03) ↓ 13.8% cheaper
#22 Claude Sonnet 5.5
Anthropic
 $0.031440 (rounded ~ $0.03) ↓ 0.8% cheaper
#23 Gemini 4 Argon
Google
 $0.031680 (rounded ~ $0.03) Same price
#24 GPT-6.1 Sol
OpenAI
 $0.031680 (rounded ~ $0.03) Same price
#25 GPT-6 Sol
OpenAI
 $0.031680 (rounded ~ $0.03) Same price
#26 Kimi K3.1 Pro
Moonshot AI
 $0.032016 (rounded ~ $0.03) ↑ 1.1% more
#27 Gemini 3.1 Pro
Google
 $0.035680 (rounded ~ $0.04) ↑ 12.6% more
#28 GPT-5.6 Terra
OpenAI
 $0.035680 (rounded ~ $0.04) ↑ 12.6% more
#29 GPT-5.3 Codex Spark
OpenAI
 $0.038220 (rounded ~ $0.04) ↑ 20.6% more
#30 GPT-5.3 Instant
OpenAI
 $0.038220 (rounded ~ $0.04) ↑ 20.6% more
#31 GPT-5.4
OpenAI
 $0.044600 (rounded ~ $0.04) ↑ 40.8% more
#32 GPT-5.4 Thinking
OpenAI
 $0.044600 (rounded ~ $0.04) ↑ 40.8% more
#33 Claude Sonnet 4.6
Anthropic
 $0.047520 (rounded ~ $0.05) ↑ 50% more
#34 Kimi K3
Moonshot AI
 $0.048024 (rounded ~ $0.05) ↑ 51.6% more
#35 Claude Opus 5.5
Anthropic
 $0.062880 (rounded ~ $0.06) ↑ 98.5% more
#36 GPT-5.6 Sol
OpenAI
 $0.063360 (rounded ~ $0.06) ↑ 100% more
#37 Muse Wonder 1.0
Meta AI
 $0.072000 (rounded ~ $0.07) ↑ 127.3% more
#38 Claude Opus 4.7
Anthropic
 $0.079200 ↑ 150% more
#39 Claude Opus 5
Anthropic
 $0.079200 ↑ 150% more
#40 Claude Opus 4.8
Anthropic
 $0.079200 ↑ 150% more
#41 Claude Opus 4.6
Anthropic
 $0.079200 ↑ 150% more
#42 GPT-5.5
OpenAI
 $0.089200 ↑ 181.6% more
#43 GPT-5.5 Instant
OpenAI
 $0.089200 ↑ 181.6% more
#44 Claude Fable 5.1
Anthropic
 $0.156600 (rounded ~ $0.16) ↑ 394.3% more
#45 Claude Mythos 5.1
Anthropic
 $0.156600 (rounded ~ $0.16) ↑ 394.3% more
#46 Claude Fable 5
Anthropic
 $0.158400 (rounded ~ $0.16) ↑ 400% more
#47 Claude Mythos 5
Anthropic
 $0.158400 (rounded ~ $0.16) ↑ 400% more
#48 GPT-6 Astra
OpenAI
 $0.158400 (rounded ~ $0.16) ↑ 400% more
#49 GPT-5.2 Pro
OpenAI
 $0.458640 (rounded ~ $0.46) ↑ 1347.7% more
#50 GPT-5.2 Pro
OpenAI
 $0.458640 (rounded ~ $0.46) ↑ 1347.7% more
🏆

Claude Haiku 5.5
Anthropic

$0.001584
vs Claude Sonnet 5: ↓ 95%
🥈

GPT-6 Luna
OpenAI

$0.001584
vs Claude Sonnet 5: ↓ 95%
🥉

GPT-5.6 Luna
OpenAI

$0.003568
vs Claude Sonnet 5: ↓ 88.7%
#4

Grok Code Fast 1
xAI

$0.004168
vs Claude Sonnet 5: ↓ 86.8%
#5

Gemini 3.1 Flash Lite
Google

$0.004460
vs Claude Sonnet 5: ↓ 85.9%
#6

Mistral Large 3
Mistral AI

$0.005920 (rounded ~ $0.01)
vs Claude Sonnet 5: ↓ 81.3%
#7

Gemini 3.5 Flash-Lite
Google

$0.006752 (rounded ~ $0.01)
vs Claude Sonnet 5: ↓ 78.7%
#8

Gemini 2.5 Flash
Google

$0.006752 (rounded ~ $0.01)
vs Claude Sonnet 5: ↓ 78.7%
#9

Gemini 3.1 Flash
Google

$0.008920 (rounded ~ $0.01)
vs Claude Sonnet 5: ↓ 71.8%
#10

Grok Build 0.1
xAI

$0.009840
vs Claude Sonnet 5: ↓ 68.9%
#11

Gemini 3.8 Flash
Google

$0.011880 (rounded ~ $0.01)
vs Claude Sonnet 5: ↓ 62.5%
#12

Gemini 3.6 Flash
Google

$0.011880 (rounded ~ $0.01)
vs Claude Sonnet 5: ↓ 62.5%
#13

Grok 4.3
xAI

$0.012300 (rounded ~ $0.01)
vs Claude Sonnet 5: ↓ 61.2%
#14

Grok 4.20 Beta
xAI

$0.012300 (rounded ~ $0.01)
vs Claude Sonnet 5: ↓ 61.2%
#15

GPT-5.4 mini
OpenAI

$0.013380 (rounded ~ $0.01)
vs Claude Sonnet 5: ↓ 57.8%
#16

Claude Haiku 4.5
Anthropic

$0.015840 (rounded ~ $0.02)
vs Claude Sonnet 5: ↓ 50%
#17

Mistral Large 4
Mistral AI

$0.016302 (rounded ~ $0.02)
vs Claude Sonnet 5: ↓ 48.5%
#18

Grok 4.7
xAI

$0.023680 (rounded ~ $0.02)
vs Claude Sonnet 5: ↓ 25.3%
#19

Grok 4.6
xAI

$0.023680 (rounded ~ $0.02)
vs Claude Sonnet 5: ↓ 25.3%
#20

Grok 4.5
xAI

$0.023680 (rounded ~ $0.02)
vs Claude Sonnet 5: ↓ 25.3%
#21

Gemini 2.5 Pro
Google

$0.027300 (rounded ~ $0.03)
vs Claude Sonnet 5: ↓ 13.8%
#22

Claude Sonnet 5.5
Anthropic

$0.031440 (rounded ~ $0.03)
vs Claude Sonnet 5: ↓ 0.8%
#23

Gemini 4 Argon
Google

$0.031680 (rounded ~ $0.03)
vs Claude Sonnet 5: Same
#24

GPT-6.1 Sol
OpenAI

$0.031680 (rounded ~ $0.03)
vs Claude Sonnet 5: Same
#25

GPT-6 Sol
OpenAI

$0.031680 (rounded ~ $0.03)
vs Claude Sonnet 5: Same
#26

Kimi K3.1 Pro
Moonshot AI

$0.032016 (rounded ~ $0.03)
vs Claude Sonnet 5: ↑ 1.1%
#27

Gemini 3.1 Pro
Google

$0.035680 (rounded ~ $0.04)
vs Claude Sonnet 5: ↑ 12.6%
#28

GPT-5.6 Terra
OpenAI

$0.035680 (rounded ~ $0.04)
vs Claude Sonnet 5: ↑ 12.6%
#29

GPT-5.3 Codex Spark
OpenAI

$0.038220 (rounded ~ $0.04)
vs Claude Sonnet 5: ↑ 20.6%
#30

GPT-5.3 Instant
OpenAI

$0.038220 (rounded ~ $0.04)
vs Claude Sonnet 5: ↑ 20.6%
#31

GPT-5.4
OpenAI

$0.044600 (rounded ~ $0.04)
vs Claude Sonnet 5: ↑ 40.8%
#32

GPT-5.4 Thinking
OpenAI

$0.044600 (rounded ~ $0.04)
vs Claude Sonnet 5: ↑ 40.8%
#33

Claude Sonnet 4.6
Anthropic

$0.047520 (rounded ~ $0.05)
vs Claude Sonnet 5: ↑ 50%
#34

Kimi K3
Moonshot AI

$0.048024 (rounded ~ $0.05)
vs Claude Sonnet 5: ↑ 51.6%
#35

Claude Opus 5.5
Anthropic

$0.062880 (rounded ~ $0.06)
vs Claude Sonnet 5: ↑ 98.5%
#36

GPT-5.6 Sol
OpenAI

$0.063360 (rounded ~ $0.06)
vs Claude Sonnet 5: ↑ 100%
#37

Muse Wonder 1.0
Meta AI

$0.072000 (rounded ~ $0.07)
vs Claude Sonnet 5: ↑ 127.3%
#38

Claude Opus 4.7
Anthropic

$0.079200
vs Claude Sonnet 5: ↑ 150%
#39

Claude Opus 5
Anthropic

$0.079200
vs Claude Sonnet 5: ↑ 150%
#40

Claude Opus 4.8
Anthropic

$0.079200
vs Claude Sonnet 5: ↑ 150%
#41

Claude Opus 4.6
Anthropic

$0.079200
vs Claude Sonnet 5: ↑ 150%
#42

GPT-5.5
OpenAI

$0.089200
vs Claude Sonnet 5: ↑ 181.6%
#43

GPT-5.5 Instant
OpenAI

$0.089200
vs Claude Sonnet 5: ↑ 181.6%
#44

Claude Fable 5.1
Anthropic

$0.156600 (rounded ~ $0.16)
vs Claude Sonnet 5: ↑ 394.3%
#45

Claude Mythos 5.1
Anthropic

$0.156600 (rounded ~ $0.16)
vs Claude Sonnet 5: ↑ 394.3%
#46

Claude Fable 5
Anthropic

$0.158400 (rounded ~ $0.16)
vs Claude Sonnet 5: ↑ 400%
#47

Claude Mythos 5
Anthropic

$0.158400 (rounded ~ $0.16)
vs Claude Sonnet 5: ↑ 400%
#48

GPT-6 Astra
OpenAI

$0.158400 (rounded ~ $0.16)
vs Claude Sonnet 5: ↑ 400%
#49

GPT-5.2 Pro
OpenAI

$0.458640 (rounded ~ $0.46)
vs Claude Sonnet 5: ↑ 1347.7%
#50

GPT-5.2 Pro
OpenAI

$0.458640 (rounded ~ $0.46)
vs Claude Sonnet 5: ↑ 1347.7%
✨ 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.

Claude Sonnet 5 for Customer Support

Managing high-volume customer support pipelines requires a balance of speed, reasoning, and consistent output. Claude Sonnet 5 is frequently selected by SaaS teams for its exceptional reasoning capabilities and ability to follow complex, multi-turn instructions without deviating from defined brand guidelines. For ecommerce owners scaling their support operations, this model offers a distinct advantage in handling nuanced queries that require more than simple FAQ retrieval.

When deploying in a multi-turn support context, Claude Sonnet 5 excels at maintaining state across long conversations. Its ability to synthesize information from previous turns ensures that the resolution path remains coherent, reducing the likelihood of hallucinations or repetitive responses. This reliability is critical when managing thousands of customer interactions that require high accuracy.

While many models can generate conversational text, the differentiator for this model is its structural integrity in instruction-heavy environments. Teams often find that the time saved in manual review and the reduction in escalation rates offset the investment in higher-capability models. As you scale, focusing on a model that prioritizes logical consistency can significantly streamline your support workflow and improve overall customer satisfaction metrics.

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 5 currently costs $2.00 / $10.00 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 →