AiCostCompare

Claude Opus 4.6 vs GPT-5.2-Codex

Side-by-side API pricing and Artificial Analysis performance for Claude Opus 4.6 (Anthropic) and GPT-5.2-Codex (OpenAI). Green cells mark the better value in each row.

Prices updated Nov 15, 2026, 8:45 AM UTC · refreshed nightly

Claude Opus 4.6

Anthropic

GPT-5.2-Codex

OpenAI

Pricing
Input $/1M$5.00$1.75
Output $/1M$25.00$14.00
Blended $/1M (3:1)$10.00$4.81
RAG example (30K in / 2K out)$0.2$0.0805
Quality & speed
Intelligence Index——
Coding Index——
Agentic Index——
Output speed (tok/s)——
Time to first token——
Specs
Context window1M400K
Input modalitiestext, image, filetext, image

FAQ

Which is cheaper, Claude Opus 4.6 or GPT-5.2-Codex?

GPT-5.2-Codex has the lower blended API price at $4.81 per 1M tokens (3:1 input:output mix), versus $10.00 for the other model. Prices are live from OpenRouter and refresh nightly.

Which is better for RAG workloads?

For a typical RAG request (30K input / 2K output tokens), GPT-5.2-Codex costs about $0.0805 per request versus $0.2. Also compare context windows: Claude Opus 4.6 offers 1M and GPT-5.2-Codex offers 400K.

Which scores higher on Artificial Analysis benchmarks?

Intelligence Index scores are unavailable or tied for these two models. Compare coding index, speed, and price on this page to decide.