GPT-5.2-Codex vs GPT-5.3-Instant
GPT-5.3-Instant is cheaper on output tokens, while GPT-5.2-Codex offers a larger context window. Choose GPT-5.2-Codex or GPT-5.3-Instant based on the trade-off between cost, context, and the benchmarks that matter for your use case.
| Spec | GPT-5.2-Codex | GPT-5.3-Instant |
|---|---|---|
| Provider | OpenAI | Poe |
| Input / 1M tokens | $1.75 | $1.60 |
| Output / 1M tokens | $14.00 | $13.00 |
| Context window | 400K | 128K |
| Parameters | — | — |
| Open weights | No | No |
| Released | Dec 2025 | Mar 2026 |
| LiveBench score | 74.3 | 59.8 |
| SWE-bench Verified score | 72.8 | — |
| SWE-bench Multilingual score | 66.3 | — |
| LMArena WebDev Elo score | 1338 | — |
FAQ
Is GPT-5.2-Codex or GPT-5.3-Instant cheaper?
GPT-5.3-Instant is cheaper on output tokens ($13.00 vs $14.00 per 1M).
Which has the larger context window, GPT-5.2-Codex or GPT-5.3-Instant?
GPT-5.2-Codex has the larger context window (400K tokens).
Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.