Anthropic Claude 3.5 Sonnet & Haiku Cost Estimator

CLAUDE MODEL & TOKEN USAGE

Select Anthropic Claude Model

Monthly API Requests

Input Tokens / Req

Output Tokens / Req

Enable Prompt Cache Reads (90% discount on cached inputs)

ANTHROPIC API COST ESTIMATE

$480.00

Est. Monthly Cost

$0.0096

Cost / Request

130M

Total Tokens/Mo

Cost Distribution

Input Tokens Cost (100M): $30.00 / mo

Output Tokens Cost (30M): $450.00 / mo

Annual Equivalent API Spend: $5,760.00 / yr

Anthropic Claude API Pricing & Prompt Caching Guide

Anthropic offers models tailored for heavy coding tasks (Claude 3.5 Sonnet), rapid lightweight sub-agents (Claude 3.5 Haiku), and complex reasoning (Claude 3 Opus).

Anthropic Pricing Rates (per 1,000,000 Tokens)

Claude 3.5 Sonnet: $3.00 Input / $0.30 Cached Read / $15.00 Output
Claude 3.5 Haiku: $0.80 Input / $0.08 Cached Read / $4.00 Output
Claude 3 Opus: $15.00 Input / $1.50 Cached Read / $75.00 Output

Related AI Tools

Calculate OpenAI API costs with the OpenAI Cost Estimator, compare model pricing with the OpenAI Cost Estimator, or build MCP configs with the Claude Desktop MCP Maker.

Frequently Asked Questions

Common questions about this tool.

What are the current pricing rates for Anthropic Claude 3.5 Sonnet? ▼

Claude 3.5 Sonnet costs $3.00 per 1M input tokens ($0.30 per 1M prompt cache write / $0.30 read) and $15.00 per 1M output tokens.

How much cheaper is Claude 3.5 Haiku compared to Sonnet? ▼

Claude 3.5 Haiku costs $0.80 per 1M input tokens and $4.00 per 1M output tokens, providing ultra-fast execution for lightweight agent tasks.

How does Anthropic Prompt Caching work? ▼

Prompt caching allows you to cache static context (like system instructions or codebases) for 5 minutes. Cache reads receive an 90% discount ($0.30 vs $3.00 per 1M input tokens).

What is the maximum context window supported by Claude 3.5 Sonnet? ▼

Claude 3.5 Sonnet supports a 200,000 token context window with up to 8,192 output tokens per request.

How do batch request discounts work with Anthropic Messages Batch API? ▼

Anthropic Message Batches provide a 50% discount on input and output tokens for non-urgent tasks processed asynchronously within 24 hours.