TechCompare LogoTechCompare

Claude Sonnet 5 API Pricing & Cost Calculator

By TechCompare · Updated · How we check

Sonnet 5 is the new coding model in the same capability tier as Sonnet 4.6, at a lower price. With cached input at $0.20 and batch rates of $1/$5, long agentic loops stay affordable.

Calculator

Cost Comparison

Based on 100,000 input tokens (50% cached), 5,000 output tokens, and 100 requests.Prices come live from OpenRouter at each maker's own price where it's listed. Temporary deals are left out.

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

Claude Sonnet 5 succeeds Sonnet 4.6 as Anthropic's coding and agentic model, below Claude Opus 5 in the Claude lineup.

Anthropic: Claude Sonnet 5

Anthropic's own price

Input
$2
Output
$10
Cached
$0.20

per 1M tokens

Batch available

Price checked 2026-11-12

How this is calculated

Claude Sonnet 5 is priced at $2.00 per million input tokens and $10.00 per million output tokens, 33% cheaper than Claude Sonnet 4.6's $3.00/$15.00 across the board. It supports a prompt caching discount of 90% ($0.20 per million) and a batch discount of 50% ($1.00 per million inputs, $5.00 per million outputs) via Anthropic's Message Batches API.

Verdict

Sonnet 5 lands at $2/M input and $10/M output, below Sonnet 4.6's $3/$15 on both rows, with cached input at $0.20/M (90% discount) and batch at $1/M input and $5/M output (50% discount). The case for migrating from 4.6 to 5 is the simplest in the lineup: same lineage, same tool-use ergonomics, lower price on every row, and (per Anthropic) improved capability.

Long agentic coding loops see both the cached-input rate drop and the per-output cost drop, so the per-call total falls 33% without changing the workflow.

More API Standalones scenarios

Claude Opus 5 vs Claude Sonnet 5
The two top Claude tiers from the same lineage. Compare rates, caching, and the work each one suits.
View details
Claude Sonnet 5 vs Claude Sonnet 4.6
Same lineage, two generations. Compare list rates, cache reads, and what the newer model adds.
View details
Grok 4.5 vs Claude Sonnet 5
Two mid-tier workhorses from different ecosystems. Compare input and output rates side by side.
View details

Related guides

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

Frequently asked questions

Is Claude Sonnet 5 cheaper than Claude Sonnet 4.6?
Yes. Sonnet 5 costs $2.00/$10.00 per million vs Sonnet 4.6's $3.00/$15.00, 33% lower across the board. Both get the same 90% cache discount, and both offer batch pricing.
How much does Claude Sonnet 5 cost per million output tokens?
Claude Sonnet 5 charges $10.00 per million output tokens at standard pricing, 33% cheaper than Sonnet 4.6's $15/M. Through the Message Batches API, that drops to $5.00 per million. The 90% prompt caching discount brings cached input to $0.20 per million, useful for high-volume agentic and coding workloads.
Is Claude Sonnet 5 cheaper than Sonnet 4.6?
Yes across the board. Sonnet 5 is $2/M input and $10/M output, versus Sonnet 4.6's $3/$15. The cache discount applies at 90%, dropping cached input to $0.20/M (off $2) versus Sonnet 4.6's $0.30/M. Both offer batch pricing and 1M context. Sonnet 5 is a strict upgrade on price and capability if you're already on Sonnet 4.6.

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. Browse it as a tree, run JSONPath queries, compare two documents, or validate against a JSON Schema.

Use tool