tokevenClaude · Mid-tier · 200K context window
Claude Sonnet 4.6 pricing for legal analysis
$0.0900 per call at 10,000 input / 4,000 output tokens.
Per call
$0.0900
10K calls/mo
$900
Cache savings
90% off input
Batch savings
50% off all
Calculate your Claude Sonnet 4.6 costs
Adjust token counts, volume, and discount toggles to model your legal analysis spend. Pricing updated weekly.
Configure your usage
Estimated cost
Quick start
Call Claude Sonnet 4.6 with the Anthropic Python SDK:
from anthropic import Anthropic
client = Anthropic()
response = client.messages.create(
model="claude-sonnet-4-6",
max_tokens=4000,
messages=[{"role": "user", "content": "Your prompt here"}]
)
# Cost: ~$0.0900 per call at standard rates
# Input: $3.00/MTok
# Output: $15.00/MTokHow Claude Sonnet 4.6 compares on cost
Per-call cost for all models scoring 50+ on legal analysis benchmarks. Hover for details.
Cheapest viable option: Claude Sonnet 5 at $0.0600/call (33% less, 90/100 quality).
Complete Claude Sonnet 4.6 pricing breakdown
Standard token rates
| Direction | $/MTok | Tokens per call |
|---|---|---|
| Input | $3.00 | 10,000 |
| Output | $15.00 | 4,000 |
Prompt caching: 90% off input tokens
Caching drops input cost from $3.00 to $0.30/MTok. For repeated system prompts, that saves $0.0270 per call.
Batch API: 50% off all tokens
Submit requests asynchronously and receive 50% off all token costs. This works best for offline pipelines where latency requirements are flexible.
Monthly cost projections
| Monthly volume | Cost per call | Standard monthly | Cached monthly | You save with caching |
|---|---|---|---|---|
| 10,000 calls | $0.0900 | $900 | $630 | $270 |
| 50,000 calls | $0.0900 | $4,500 | $3,150 | $1,350 |
| 100,000 calls | $0.0900 | $9,000 | $6,300 | $2,700 |
| 500,000 calls | $0.0900 | $45,000 | $31,500 | $13,500 |
| 1,000,000 calls | $0.0900 | $90,000 | $63,000 | $27,000 |
Claude Sonnet 4.6 quality benchmarks for legal analysis
Claude Sonnet 4.6 is a solid pick for legal analysis
Scores 88/100 (rank #3 of 14). Good balance of quality and cost for legal analysis.
Top-ranked: Claude Fable 5 (98/100) at $0.3000/call
Performance across all task types
Claude Sonnet 4.6 scores by task type. Legal Analysis highlighted.
| Task type | Confidence score | Rank out of 14 |
|---|---|---|
| Code Review | 95/100 | #1 |
| Code Generation | 92/100 | #2 |
| Summarization | 90/100 | #2 |
| Reasoning(current page) | 88/100 | #3 |
| Q&A | 88/100 | #3 |
| Extraction | 86/100 | #3 |
| Creative Writing | 85/100 | #3 |
| Classification | 84/100 | #4 |
Alternative models for legal analysis
8 models score 80+ on legal analysis benchmarks, sorted by input rate. Cheapest: Claude Sonnet 5 (33% less, 90/100 quality).
| Model | Provider | Input $/MTok | Output $/MTok | Quality | Per call | vs Claude |
|---|---|---|---|---|---|---|
| Claude Sonnet 5 | Claude | $2.00 | $10.00 | 90/100 | $0.0600 | 33% cheaper |
| Gemini 3.1 Pro | Gemini | $2.00 | $12.00 | 90/100 | $0.0680 | 24% cheaper |
| GPT 5.4 | GPT | $2.50 | $15.00 | 80/100 | $0.0850 | 6% cheaper |
| GPT 5.6 Terra | GPT | $2.50 | $15.00 | 82/100 | $0.0850 | 6% cheaper |
| Claude Opus 4.8 | Claude | $5.00 | $25.00 | 97/100 | $0.1500 | 67% more |
| GPT 5.5 | GPT | $5.00 | $30.00 | 95/100 | $0.1700 | 89% more |
| GPT 5.6 Sol | GPT | $5.00 | $30.00 | 96/100 | $0.1700 | 89% more |
| Claude Fable 5 | Claude | $10.00 | $50.00 | 98/100 | $0.3000 | 233% more |
About Claude Sonnet 4.6
Provider
Claude
Tier
Mid-tier
Context
200K tokens
Released
May 2026
Other models from Claude
| Model | Tier | Input $/MTok | Output $/MTok | Context |
|---|---|---|---|---|
| Claude Opus 4.8 | Flagship | $5.00 | $25.00 | 200K |
| Claude Haiku 4.5 | Fast / Budget | $1.00 | $5.00 | 200K |
| Claude Sonnet 5 | Mid-tier | $2.00 | $10.00 | 200K |
| Claude Fable 5 | Flagship | $10.00 | $50.00 | 1,000K |
You can compare Claude Sonnet 4.6 head-to-head against any other model on our model comparison pages, or track how pricing has changed over time on the pricing history tracker.
Claude Sonnet 4.6 pricing for other use cases
See how Claude Sonnet 4.6 costs change across different workload types.
Code Generation
$0.0660/call
Unit Test Generation
$0.0840/call
SQL Generation
$0.0195/call
API Generation
$0.0990/call
Code Refactoring
$0.0720/call
Code Review
$0.0450/call
PR Review
$0.0690/call
Security Review
$0.0555/call
Bug Detection
$0.0450/call
Document Summarization
$0.0450/call
PDF Summarization
$0.0675/call
Meeting Notes
$0.0540/call
Email Summarization
$0.0165/call
Chatbot
$0.0210/call
RAG Pipeline
$0.0405/call
Customer Support Bot
$0.0240/call
FAQ Bot
$0.0165/call
Data Extraction
$0.0270/call
JSON Extraction
$0.0210/call
Invoice Parsing
$0.0150/call
Resume Parsing
$0.0195/call
Chain of Thought
$0.0840/call
Math Reasoning
$0.0495/call
Financial Analysis
$0.0840/call
Content Moderation
$0.003000/call
Sentiment Analysis
$0.003000/call
Categorization
$0.004650/call
Intent Detection
$0.002400/call
Copywriting
$0.0315/call
Blog Writing
$0.1230/call
Marketing Copy
$0.0474/call
Product Descriptions
$0.0240/call
Related pages
Frequently asked questions
How much does Claude Sonnet 4.6 cost for legal analysis per API call?
$0.0900 per call at 10,000 input / 4,000 output tokens.
Is Claude Sonnet 4.6 the best model for legal analysis?
Scores 88/100, rank #3 of 14 models. Top-ranked: Claude Fable 5 at 98/100.
What is the cheapest model for legal analysis with good quality?
Claude Sonnet 5 scores 90/100 quality at $2.00/$10.00 per MTok. That is 33% less than Claude Sonnet 4.6 per call.
How can I reduce my Claude Sonnet 4.6 costs for legal analysis?
Three strategies: prompt caching (90% off input), batch API (50% off all tokens), prompt optimization. Combined: $0.0900 drops to about $0.004500 per call.
How does Claude Sonnet 4.6 pricing compare to other Claude models?
Claude also offers: Claude Opus 4.8 at $5.00/$25.00, Claude Haiku 4.5 at $1.00/$5.00, Claude Sonnet 5 at $2.00/$10.00, Claude Fable 5 at $10.00/$50.00.
What context window does Claude Sonnet 4.6 support?
200K tokens total. Typical legal analysis calls use 10,000 plus 4,000 tokens, well within limits.
Track what you spend on AI
This calculator estimates costs based on published rates only. Connect your API usage to see where your money goes and which models drive your spend.