- Home
- All models
- GPT-5.2-Codex
GPT-5.2-Codex: price, performance and context
Proprietary GPT-5.2-Codex by OpenAI costs $1.75 per 1M input and $14.00 per 1M output tokens, handles up to 400K tokens in one request (≈ 1,200 pages of text) and scores 28.5 points on the AgentKernel performance index, rank 52 of 212.
Privacy: zero data retention with one provider, not in the EU. Availability over the last 24 h: 100%.
Updated Oct 09, 2026, 16:45 UTC · openai/gpt-5.2-codex
Open in the interactive comparison
Key facts
- Licence
- Proprietary: no public weights, only through a provider API
- Input / 1M tokens
- $1.75
- Output / 1M tokens
- $14.00
- Context window
- 400K tokens
- Max. output
- 128K tokens
- Performance index
- 28.5 points · rank 52 of 212
- Coding index
- n/a
- Agentic index
- n/a
- Cost at your usage
- $5.25 / month
- Knowledge cutoff
- n/a
- In the catalog since
- Jan 14, 2026
- Capabilities
- Reasoning, Vision, Tool Calling
What do you get for $10.00?
Rules of thumb from the cost calculator, base rates without caching or taxes.
| Task | Cost per task | For $10.00 |
|---|
| Chat repliesA question with a short history, a detailed answer | $0.008 | 1,300 |
| Email draftsBullet points in, a finished email out | $0.006 | 1,700 |
| Document summariesRead 10 pages, write a one-page summary | $0.013 | 780 |
| Code reviewsReview and comment on 500 lines of code | $0.024 | 420 |
| Book analysesAnalyse a 300-page book in one go | $0.203 | 49 |
Cheaper with similar performance
Stronger models
Open alternatives
AGENTKERNEL