Claude Sonnet 4.6 vs GPT-5.4

Anthropic's Claude Sonnet 4.6 against OpenAI's GPT-5.4 — price, context and what each is best at. Both are available through one OpenAI-compatible API.

AnyModel — you pay	Claude Sonnet 4.6	GPT-5.4
Vendor	Anthropic	OpenAI
Input / 1M	$0.12	$0.1
Output / 1M	$0.12	$0.1
Context	1M	400K
Best for	Claude Code	Production apps

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 →

GPT-5.4

Production workhorse — near-flagship quality at half the price.

GPT-5.4 is the volume tier of the GPT-5 line: strong coding and agent performance with lower latency and cost than GPT-5.5. A great default for production apps and day-to-day engineering.

More about GPT-5.4 →

Quick take: pick GPT-5.4 when cost matters most; pick Claude Sonnet 4.6 when you need the largest context. With AnyModel you don't have to choose up front — switch the model id any time.

FAQ

Which is cheaper, Claude Sonnet 4.6 or GPT-5.4?

GPT-5.4 is cheaper on output tokens ($0.1 vs $0.12 per 1M).

Which has a larger context window, Claude Sonnet 4.6 or GPT-5.4?

Claude Sonnet 4.6 has the larger context window (1M).