Claude Sonnet 4.6 vs Claude Sonnet 5

Anthropic's Claude Sonnet 4.6 against Anthropic's Claude Sonnet 5 — price, context and what each is best at. Both are available through one OpenAI-compatible API.

AnyModel — you pay	Claude Sonnet 4.6	Claude Sonnet 5
Vendor	Anthropic	Anthropic
Input / 1M	$0.24	$0.16
Output / 1M	$0.24	$0.16
Context	1M	1M
Best for	Claude Code	Coding agents

Claude Sonnet 4.6

The balanced Claude — fast, smart, affordable.

Claude Sonnet 4.6 hits the sweet spot of speed, intelligence and price, with the context window now grown to 1M tokens. It's the default Claude for coding agents and most production workloads.

More about Claude Sonnet 4.6 →

Claude Sonnet 5

The new mid-tier Claude 5 — intro-priced by the vendor until September.

Claude Sonnet 5 is the first mid-tier model of the Claude 5 family: stronger than Sonnet 4.6 with the same 1M-token window. Anthropic lists it at an intro $2/$10 per 1M until 2026-09-01 (then $3/$15).

More about Claude Sonnet 5 →

Quick take: Claude Sonnet 5 is cheaper on output tokens ($0.16 vs $0.24 per 1M). Compare their strengths and context for your task; you can switch the model id at any time.

FAQ

Which is cheaper, Claude Sonnet 4.6 or Claude Sonnet 5?

Claude Sonnet 5 is cheaper on output tokens ($0.16 vs $0.24 per 1M).

Which has a larger context window, Claude Sonnet 4.6 or Claude Sonnet 5?

Claude Sonnet 4.6: 1M; Claude Sonnet 5: 1M.