Side-by-side comparison
Claude Sonnet 4.6 vs GPT-5.2-Codex
Anthropic
Claude Sonnet 4.6
👁 Vision
🔧 Tools
{} JSON
Input / 1M
$3.0000
Output / 1M
$15.0000
OpenAI
GPT-5.2-Codex
👁 Vision
🔧 Tools
{} JSON
Input / 1M
$1.7500
Output / 1M
$14.0000
| Claude Sonnet 4.6 | GPT-5.2-Codex | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Context window Maximum tokens (input + output) the model can process in a single request. Glossary → | 1,000,000 | 400,000 |
| Capabilities Optional capabilities the model advertises: vision (images), tools (function calling), json_mode (structured output). | vision, tools, json_mode | vision, tools, json_mode |
| Input $ / 1M tokens Cost for tokens you send (prompt + context). Cheaper side highlighted. Glossary → | 3.0000 | 1.7500 |
| Output $ / 1M tokens Cost for tokens the model generates. Output is normally 3–5× pricier than input. Glossary → | 15.0000 | 14.0000 |
Frequently asked questions
Which is cheaper, Claude Sonnet 4.6 or GPT-5.2-Codex?
GPT-5.2-Codex is cheaper than Claude Sonnet 4.6 on a 50/50 input/output blend by about $1.125 per 1M tokens. Exact savings depend on your input-vs-output ratio — use the cost calculator on this page for a workload-specific estimate.
Which has a larger context window, Claude Sonnet 4.6 or GPT-5.2-Codex?
Claude Sonnet 4.6 has the larger context window at 1M tokens versus 400k tokens for GPT-5.2-Codex. That means Claude Sonnet 4.6 can ingest about 2.5x as much text per request.
What is the difference between Claude Sonnet 4.6 and GPT-5.2-Codex?
Claude Sonnet 4.6 comes from Anthropic; GPT-5.2-Codex comes from OpenAI. They differ in pricing, context window, and supported capabilities — see the side-by-side table on this page for the exact figures, refreshed nightly.