GPT-5.2 Codex
GPTSpecialized
ThinkingTool UseVisionStructured Output
About this model
GPT-5.2-Codex is an upgraded version of GPT-5.1-Codex optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks....
Performance Tier
Specialized
GPT-5.2 Codex is a specialized model from GPT : built for a specific domain.
Domain-specific model. Optimized for a particular task such as code generation, image creation, or web search.
Pricing
This model is included in Elosia plansHigh
High pricing. Reserve this level for tasks that demand maximum quality.
| Type | per 1M tokens |
|---|---|
| Input (prompt) | $1.75 |
| Output (completion) | $14.00 |
| Cache read | $0.175 |
Capabilities
Context Length400K
Max Output Tokens128K
TokenizerGPT
Inputtext, image
Outputtext
Release DateJanuary 14, 2026
Benchmarks
Programming
HumanEval
97%
SWE-bench Verified
82.5%
Recommended Use Cases
Coding
Strengths
- Purpose-built for software engineering tasks
- Highest SWE-bench score in the GPT family (82.5%)
- Supports multi-file edits and repository-level reasoning
- Integrated code execution for iterative development
Limitations
- Specialized for code — not ideal for general conversation
- Premium pricing tier
Resources
This model may use your data for training