Compare Claude Opus 4.6 from Anthropic and GPT-5.2-Codex from OpenAI on key metrics including benchmarks, price, context length, and other model features. Access both models and hundreds of others through the OpenRouter API.
Claude Opus 4.6 and GPT-5.2-Codex are available through the OpenRouter API, so switching between them takes a model slug change rather than a new integration.
Claude Opus 4.6, from Anthropic, has a 1,000,000-token context window and is priced at $5/M tokens input, $25/M tokens output on OpenRouter.
GPT-5.2-Codex, from OpenAI, has a 400,000-token context window and is priced at $1.75/M tokens input, $14/M tokens output on OpenRouter.
| Claude Opus 4.6 | GPT-5.2-Codex | |
|---|---|---|
| Input price | $5/M tokens | $1.75/M tokens |
| Output price | $25/M tokens | $14/M tokens |
| Context window | 1,000,000 tokens | 400,000 tokens |
| Intelligence Index | 31.9 | 28.5 |
| Coding Index | Not available | Not available |
| Agentic Index | Not available | Not available |
| Latency (p50) | 1.52 s | 2.97 s |
| Throughput (p50) | 42.0 tok/s | 60.0 tok/s |
GPT-5.2-Codex is cheaper than Claude Opus 4.6 on OpenRouter: GPT-5.2-Codex costs $1.75/M tokens input and $14/M tokens output, while Claude Opus 4.6 costs $5/M tokens input and $25/M tokens output.
Claude Opus 4.6 has the longer context window at 1,000,000 tokens, compared with 400,000 tokens for GPT-5.2-Codex.
GPT-5.2-Codex is faster on OpenRouter, generating a median 60.0 tokens per second compared with 42.0 tokens per second for Claude Opus 4.6.