Verified 2025-09-22 · sourced from Anthropic
Claude Sonnet 4 Token Calculator & Cost Guide
Estimate Anthropic Claude Sonnet 4 API usage in dollars before you send a single request. Standard pricing is $3.00 per million input tokens and $15.00 per million output tokens with a 200K token context window.
Context window
200,000 tokens
Input price
$3.00 / 1M
Output price
$15.00 / 1M
Cached input
$0.300 / 1M
Usage scenarios
Compare standard and cached pricing (where available) across common workloads.
| Scenario | Tokens in | Tokens out | Total tokens | Standard cost | Cached cost |
|---|---|---|---|---|---|
Quick chat reply Single user question with a short assistant answer | 650 | 220 | 870 | $0.0052 | $0.0035 |
Coding assistant session Multi-turn pair programming exchange (≈6 turns) | 2,600 | 1,400 | 4,000 | $0.0288 | $0.0218 |
Knowledge base response Retrieval-augmented answer referencing multiple passages | 12,000 | 3,000 | 15,000 | $0.0810 | $0.0486 |
Near-max context run Large document processing approaching the 200K token limit | 176,000 | 24,000 | 200,000 | $0.888 | $0.413 |
Daily & monthly budgeting
Translate usage into predictable operating expenses across popular deployment sizes.
| Profile | Requests/day | Tokens/day | Daily cost | Monthly cost | Cached daily | Cached monthly |
|---|---|---|---|---|---|---|
| Team pilot | 25 | 75,000 | $0.525 | $15.75 | $0.390 | $11.70 |
| Product launch | 100 | 500,000 | $3.30 | $99.00 | $2.35 | $70.65 |
| Enterprise scale | 500 | 3,000,000 | $21.00 | $630.00 | $15.60 | $468.00 |
Pricing notes
- Input/Output pricing applies to prompts ≤ 200K tokens: input $3/MTok, output $15/MTok.
- For prompts > 200K tokens: input $6/MTok, output $22.50/MTok.
- Prompt caching (≤ 200K): write $3.75/MTok, read $0.30/MTok.
- Prompt caching (> 200K): write $7.50/MTok, read $0.60/MTok.
Frequently asked questions
How much does Claude Sonnet 4 cost per 1,000 tokens?
At the published rates of $3.00 per million input tokens and $15.00 per million output tokens, a typical 1,000 token request (≈70% input, 30% output) costs about $0.0066.
Does Claude Sonnet 4 offer cached input discounts?
Claude Sonnet 4 drops input costs to $0.300 per million cached tokens. Using cached contexts, that same 1,000 token call totals $0.0047, a significant saving for chatbots and RAG systems.
What is the context window for Claude Sonnet 4?
Claude Sonnet 4 supports up to 200,000 tokens (200K), allowing large prompts and retrieval-augmented payloads in a single call.
How fresh is the Claude Sonnet 4 pricing data?
Pricing is sourced from https://claude.com/pricing#api and was last verified on 2025-09-22. The calculator updates automatically when models.json is refreshed.