Claude · Mid-tier · 200K context window
$0.0160 per call at 3,000 input / 1,000 output tokens.
Per call
$0.0160
10K calls/mo
$160
Cache savings
90% off input
Batch savings
50% off all
Adjust token counts, volume, and discount toggles to model your customer support bot spend. Pricing updated weekly.
Call Claude Sonnet 5 with the Anthropic Python SDK:
from anthropic import Anthropic
client = Anthropic()
response = client.messages.create(
model="claude-sonnet-5",
max_tokens=1000,
messages=[{"role": "user", "content": "Your prompt here"}]
)
# Cost: ~$0.0160 per call at standard rates
# Input: $2.00/MTok
# Output: $10.00/MTokPer-call cost for all models scoring 50+ on customer support bot benchmarks. Hover for details.
Cheapest viable option: Gemini 3 Flash at $0.004500/call (72% less, 82/100 quality).
| Direction | $/MTok | Tokens per call |
|---|---|---|
| Input | $2.00 | 3,000 |
| Output | $10.00 | 1,000 |
Caching drops input cost from $2.00 to $0.20/MTok. For repeated system prompts, that saves $0.005400 per call.
Submit requests asynchronously and receive 50% off all token costs. This works best for offline pipelines where latency requirements are flexible.
| Monthly volume | Cost per call | Standard monthly | Cached monthly | You save with caching |
|---|---|---|---|---|
| 10,000 calls | $0.0160 | $160 | $106 | $54 |
| 50,000 calls | $0.0160 | $800 | $530 | $270 |
| 100,000 calls | $0.0160 | $1,600 | $1,060 | $540 |
| 500,000 calls | $0.0160 | $8,000 | $5,300 | $2,700 |
| 1,000,000 calls | $0.0160 | $16,000 | $10,600 | $5,400 |
Claude Sonnet 5 is a solid pick for customer support bot
Scores 89/100 (rank #2 of 14). Good balance of quality and cost for customer support bot.
Top-ranked: GPT 5.6 Terra (92/100) at $0.0225/call
Claude Sonnet 5 scores by task type. Customer Support Bot highlighted.
| Task type | Confidence score | Rank out of 14 |
|---|---|---|
| Code Review | 96/100 | #1 |
| Code Generation | 93/100 | #2 |
| Summarization | 91/100 | #1 |
| Reasoning | 90/100 | #2 |
| Q&A(current page) | 89/100 | #2 |
| Extraction | 88/100 | #2 |
| Creative Writing | 87/100 | #3 |
| Classification | 86/100 | #3 |
12 models score 80+ on customer support bot benchmarks, sorted by input rate. Cheapest: Gemini 3 Flash (72% less, 82/100 quality).
| Model | Provider | Input $/MTok | Output $/MTok | Quality | Per call | vs Claude |
|---|---|---|---|---|---|---|
| Gemini 3 Flash | Gemini | $0.50 | $3.00 | 82/100 | $0.004500 | 72% cheaper |
| Claude Haiku 4.5 | Claude | $1.00 | $5.00 | 86/100 | $0.008000 | 50% cheaper |
| GPT 5.6 Luna | GPT | $1.00 | $6.00 | 85/100 | $0.009000 | 44% cheaper |
| Gemini 3.5 Flash | Gemini | $1.50 | $9.00 | 84/100 | $0.0135 | 16% cheaper |
| Gemini 3.1 Pro | Gemini | $2.00 | $12.00 | 87/100 | $0.0180 | 13% more |
| GPT 5.4 | GPT | $2.50 | $15.00 | 91/100 | $0.0225 | 41% more |
| GPT 5.6 Terra | GPT | $2.50 | $15.00 | 92/100 | $0.0225 | 41% more |
| Claude Sonnet 4.6 | Claude | $3.00 | $15.00 | 88/100 | $0.0240 | 50% more |
| Claude Opus 4.8 | Claude | $5.00 | $25.00 | 85/100 | $0.0400 | 150% more |
| GPT 5.5 | GPT | $5.00 | $30.00 | 90/100 | $0.0450 | 181% more |
| GPT 5.6 Sol | GPT | $5.00 | $30.00 | 91/100 | $0.0450 | 181% more |
| Claude Fable 5 | Claude | $10.00 | $50.00 | 88/100 | $0.0800 | 400% more |
Provider
Claude
Tier
Mid-tier
Context
200K tokens
Released
Jun 2026
Introductory pricing $2/$10 through Aug 31, 2026 (registry reflects the intro rate; standard $3/$15 resumes Sep 1 — tracked revert: KNOWN_ISSUES #34)
| Model | Tier | Input $/MTok | Output $/MTok | Context |
|---|---|---|---|---|
| Claude Opus 4.8 | Flagship | $5.00 | $25.00 | 200K |
| Claude Sonnet 4.6 | Mid-tier | $3.00 | $15.00 | 200K |
| Claude Haiku 4.5 | Fast / Budget | $1.00 | $5.00 | 200K |
| Claude Fable 5 | Flagship | $10.00 | $50.00 | 1,000K |
You can compare Claude Sonnet 5 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.
See how Claude Sonnet 5 costs change across different workload types.
Code Generation
$0.0440/call
Unit Test Generation
$0.0560/call
SQL Generation
$0.0130/call
API Generation
$0.0660/call
Code Refactoring
$0.0480/call
Code Review
$0.0300/call
PR Review
$0.0460/call
Security Review
$0.0370/call
Bug Detection
$0.0300/call
Document Summarization
$0.0300/call
PDF Summarization
$0.0450/call
Meeting Notes
$0.0360/call
Email Summarization
$0.0110/call
Chatbot
$0.0140/call
RAG Pipeline
$0.0270/call
FAQ Bot
$0.0110/call
Data Extraction
$0.0180/call
JSON Extraction
$0.0140/call
Invoice Parsing
$0.010000/call
Resume Parsing
$0.0130/call
Chain of Thought
$0.0560/call
Legal Analysis
$0.0600/call
Math Reasoning
$0.0330/call
Financial Analysis
$0.0560/call
Content Moderation
$0.002000/call
Sentiment Analysis
$0.002000/call
Categorization
$0.003100/call
Intent Detection
$0.001600/call
Copywriting
$0.0210/call
Blog Writing
$0.0820/call
Marketing Copy
$0.0316/call
Product Descriptions
$0.0160/call
$0.0160 per call at 3,000 input / 1,000 output tokens.
Scores 89/100, rank #2 of 14 models. Top-ranked: GPT 5.6 Terra at 92/100.
Gemini 3 Flash scores 82/100 quality at $0.50/$3.00 per MTok. That is 72% less than Claude Sonnet 5 per call.
Three strategies: prompt caching (90% off input), batch API (50% off all tokens), prompt optimization. Combined: $0.0160 drops to about $0.000800 per call.
Claude also offers: Claude Opus 4.8 at $5.00/$25.00, Claude Sonnet 4.6 at $3.00/$15.00, Claude Haiku 4.5 at $1.00/$5.00, Claude Fable 5 at $10.00/$50.00.
200K tokens total. Typical customer support bot calls use 3,000 plus 1,000 tokens, well within limits.
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.