Anthropic: Claude Sonnet 4.5 vs OpenAI: GPT-4o

Side-by-side specs, pricing, and benchmarks. Pick a winner for your team's use case.

Use it in a Space

Spin up a Switchy Space with either model — your whole team @-mentions it with shared context, pooled credits, one memory.

Pricing
Anthropic: Claude Sonnet 4.5OpenAI: GPT-4o
Input $/Mtok$3.00 · $2.50
Output $/Mtok$15.00 · $10.00
Context window
Anthropic: Claude Sonnet 4.5OpenAI: GPT-4o
Anthropic: Claude Sonnet 4.51000K tokens
OpenAI: GPT-4o128K tokens

Bars use square-root scaling so a 1M-token window doesn't crush a 200K one.

Release timeline
Anthropic: Claude Sonnet 4.5OpenAI: GPT-4o
2025-09-29
2024-05-13
2024-04-13today

Anthropic: Claude Sonnet 4.5

Provider
anthropic
Context
1000k
Input $/Mtok
$3.00
Output $/Mtok
$15.00
Max output
64000
Modalities
text, image, file

OpenAI: GPT-4o

Provider
openai
Context
128k
Input $/Mtok
$2.50
Output $/Mtok
$10.00
Max output
16384
Modalities
text, image, file

Price delta

Anthropic: Claude Sonnet 4.5 is $0.50/Mtok more expensive than OpenAI: GPT-4o on input. Output: Anthropic: Claude Sonnet 4.5 is $5.00/Mtok more expensive than OpenAI: GPT-4o.

Which to pick

Pick **Claude Sonnet 4.5** when output quality is what you're paying for — coding turns, writing, structured reasoning, multi-step planning. Sonnet leads GPT-4o on most reasoning and code evals, and the 200k context (vs GPT-4o's 128k) covers most full-repo or long-document workflows. Pick **GPT-4o** for vision-heavy or audio-bound work: chart and screenshot interpretation, document-layout extraction, integrated voice modes. It's slightly cheaper at $2.50 in / $10 out per Mtok versus Sonnet's $3 / $15, but the real reason to choose GPT-4o is multimodality. Text-only? Sonnet wins on quality.
Data last verified 1 hour ago.Sources aggregated hourly to weekly. See docs/architecture/model-directory.md.