OpenAI: GPT-5.2-Codex
The OpenAI GPT-5.2-Codex model supports both text and image inputs, with an impressive context length of 400,000 tokens and the ability to reason and integrate tools for more dynamic responses. It excels in handling complex tasks by leveraging its robust processing capabilities. This model is best suited for organizations requiring a versatile AI solution that can process extensive amounts of data and perform multiple modalities, including image analysis, alongside text. Given its blended benchmark score of 67.5 across one independent benchmark, it offers solid performance but may not be the top choice if you prioritize the highest scores. Considering its pricing at $1.75 per million input tokens and $14.0 per million output tokens, it provides a balanced option for those seeking effective AI tools without breaking the bank.
Benchmark results
Independent, published benchmarks. Blended score 67.5 across 1 benchmark, last refreshed 2026-08-13. How scoring works →
| Benchmark | Measures | Score |
|---|---|---|
| AI Index | broad capability composite | 68.0 |
- Model ID
- openai/gpt-5.2-codex
- Vendor
- openai
- Released
- January 2026
- Tokenizer
- GPT
- Input Modalities
- text, image
- Output Modalities
- text
- Max Output
- 128,000 tokens
- Tool Calling
- ✓ supported
- Structured Output
- ✓ supported
- Reasoning Mode
- ✓ supported
- Vision
- ✓ accepts images
- Audio
- no
- Moderated
- no
What it costs in practice
Computed from the current $1.75/M input and $14.00/M output rates. Run your own numbers →
| Job | Tokens | Cost |
|---|---|---|
| Summarize a 50-page report | 30k in / 1.5k out | $0.07 |
| Classify 1,000 customer emails | 500k in / 50k out | $1.58 |
| A month of a busy support chatbot | 5M in / 2M out | $36.75 |
Similar models
OpenAI: GPT-5 Image Mini
OpenAI: GPT-4o-mini (batch)
OpenAI: GPT-4o-mini
OpenAI: GPT-4o-mini (2024-07-18)
OpenAI: GPT-5.1-Codex-Max
OpenAI: GPT-5.1-Codex
Quick answers
- How much does OpenAI: GPT-5.2-Codex cost?
- $1.75 per million input tokens and $14.00 per million output tokens.
- What is OpenAI: GPT-5.2-Codex's context window?
- 400,000 tokens, roughly 600 pages of text in a single request.
- Does OpenAI: GPT-5.2-Codex support tool calling?
- It supports tool calling, structured output, a reasoning mode.
- Can OpenAI: GPT-5.2-Codex process images?
- Yes, it accepts image input.