Compare AI models

Specifications
Context window
1M400k
API pricing
Input price
$2.00$0.25
Output price
$10.00$2.00
Cached input price
$0.10$0.025
Cheapest input
$2.00Amazon Bedrock$0.125OpenAI
Cheapest output
$10.00Amazon Bedrock$1.00OpenAI
$900Anthropic list price$150OpenAI list price
Benchmarks
Humanity's Last Exam · no tools
56.9%16.7%
Overview
CompanyAnthropicOpenAI
Release dateSep 28 2026Aug 7 2025
AccessClosedClosed
Model detailsView modelView model

Frequently asked questions

Claude Sonnet 5.5 leads GPT-5 mini on 1 of the 1 benchmark they both report (Humanity's Last Exam). GPT-5 mini is cheaper on both input and output: $0.25 vs $2.00 per million input tokens, and $2.00 vs $10.00 per million output tokens. GPT-5 mini shipped 417 days before Claude Sonnet 5.5, so benchmark comparisons should account for the intervening progress.

Context windows are 1M (Claude Sonnet 5.5) vs 400k (GPT-5 mini).

On Humanity's Last Exam · no tools, Claude Sonnet 5.5 leads at 56.9% vs GPT-5 mini at 16.7%.