token.app › Compare › GPT-5.2-Codex vs Claude Sonnet 5
GPT-5.2-Codex vs Claude Sonnet 5
Claude Sonnet 5 is 1.2× cheaper per token on a blended 3:1 basis. Claude Sonnet 5 accepts the larger context window (1M).
Head to head
Blended price uses a 3:1 input:output mix
| GPT-5.2-Codex | Claude Sonnet 5 | |
|---|---|---|
| Provider | OpenAI | Anthropic |
| Input $/1M | $1.75 | $2.00 |
| Output $/1M | $14.00 | $10.00 |
| Blended $/1M | $4.81 | $4.00 |
| Context window | 400K | 1M |
| Max output | 128K | 128K |
| Released | Jan 2026 | Jun 2026 |
| Licence | Proprietary | Proprietary |
Choose GPT-5.2-Codex if…
- No clear advantage on the data we hold.
Choose Claude Sonnet 5 if…
- Costs less per token — $4.00 vs $4.81 blended
- Larger context window (1M)
- Newer model (released Jun 2026)
FAQ
Which is better, GPT-5.2-Codex or Claude Sonnet 5?
We do not hold independently-run benchmark scores covering both GPT-5.2-Codex and Claude Sonnet 5, so we make no quality claim. Their pricing and specifications are compared on this page.
Is GPT-5.2-Codex cheaper than Claude Sonnet 5?
Claude Sonnet 5 is cheaper: $4.00 versus $4.81 per million tokens blended at 3:1 input:output. Input alone: $1.75 vs $2.00. Output alone: $14.00 vs $10.00.
What context windows do GPT-5.2-Codex and Claude Sonnet 5 have?
GPT-5.2-Codex: 400,000 tokens. Claude Sonnet 5: 1,000,000 tokens.
Who makes GPT-5.2-Codex and Claude Sonnet 5?
GPT-5.2-Codex is made by OpenAI. Claude Sonnet 5 is made by Anthropic.