TechCompare LogoTechCompare

Claude Sonnet 4.6 API Pricing & Cost Calculator

Claude Sonnet 4.6 is the gold standard for software development. Prompt caching makes multi-turn chat loops extremely affordable despite the flagship reasoning tier.

Claude Sonnet 4.6 is the industry workhorse for software engineering and multi-file codebase tasks.

By TechCompare · Updated

Input tokens
100,000
per request
Output tokens
5,000
per request
Volume
100 / monthly
Standard API

Calculator

Cost Comparison

Based on 100,000 input tokens (50% cached), 5,000 output tokens, and 100 requests.

Same 100,000 in / 5,000 out (50% cached) scenario, pre-loaded. Adjust tokens, caching, or swap models.
Edit in the full tool

How this is calculated

Claude Sonnet 4.6 is priced at $3.00 per million input tokens and $15.00 per million output tokens, supporting a 90% caching discount ($0.30 per million) and a 50% batch discount ($1.50 per million inputs, $7.50 per million outputs).

Verdict

Sonnet 4.6 lands at $3/M input and $15/M output, with cached input at $0.30/M and batch at $1.50/$7.50. The economics favor agentic coding workflows specifically: every call that reuses a stable system prompt plus tool definitions (typical for code agents) cuts roughly 90% off the input cost, which against a multi-turn chat loop compounds quickly. Output pricing matches GPT-5.4's $15/M, so tool-call-heavy loops cost about the same on both, and Anthropic's mature tool-use ergonomics are the deciding factor.

More API Standalones scenarios

GPT-5.5 Pricing
Single-model gpt-5.5 cost estimate
View details ➜
GPT-5.4 Pricing
Single-model gpt-5.4 cost estimate
View details ➜
Claude Opus 4.8 Pricing
Single-model claude-opus-4.8 cost estimate
View details ➜

Related guides

Context window explained
How a model context window caps prompt size.
View guide ➜
BPE tokenization explained
How tokenizers chunk text into the units VRAM serves.
View guide ➜

Frequently asked questions

Does Claude Sonnet 4.6 support prompt caching?
Yes, Anthropic offers a 90% discount on cached input tokens, reducing the input price to $0.30 per million for matches.
How much does Claude Sonnet 4.6 cost per million output tokens?
Claude Sonnet 4.6 charges $15.00 per million output tokens at standard pricing. With the 50% batch discount, that drops to $7.50 per million. The 90% prompt caching discount brings cached input to $0.30 per million, which is what makes multi-turn coding agents affordable on a long session.
Why is Sonnet 4.6 considered the best coding model?
Instruction following and tool-use ergonomics. Sonnet 4.6 charges $3/M input and $15/M output, competitive with GPT-5.4's $2.50/$15. Anthropic's tool-calling API is tighter than OpenAI's for complex multi-file edits and agent loops. The 90% prompt caching discount compounds the advantage for repetitive codebase context.

Related tools

LLM VRAM Calculator

Calculate the VRAM needed to run or fine-tune any LLM at any quantization.

Use tool ➜

Power Cost Estimator

Estimate annual electricity costs for your PC, Server, or TV.

Use tool ➜

Data Transfer Calculator

Estimate transfer times for files over USB, WiFi, Ethernet, and more.

Use tool ➜

JSON Formatter

Validate, format, and minify JSON data with syntax highlighting.

Use tool ➜