Model Details
Where is GPT-5.2 Codex a perfect fit?
- Long-running coding agents working across hours or sessions
- Large-scale refactoring, migrations, and multi-repo changes
- Autonomous debugging, testing, and iterative improvement loops
- Enterprise engineering workflows with strict security constraints
- Code review, vulnerability detection, and cybersecurity-focused analysis
- Building, modifying, and maintaining complex production systems
Quick Model Estimate
Your GPT-5.2 Codex Cost Estimate
💰 Total Cost
—
for 1000 input + 1000 output tokens
Cost Breakdown
Prices are watched for changes and checked against the provider's own page.
Pricing
Other Models in the GPT-5.2 Family
FAQs about GPT-5.2 Codex
How much does GPT-5.2 Codex cost per 1M tokens?
GPT-5.2 Codex costs between $1.75 and $3.50 per million input tokens, and between $14.00 and $28.00 per million output tokens. The range covers Standard and Priority pricing.
What does a typical workload cost with GPT-5.2 Codex?
1,000 requests of 2,000 input and 500 output tokens each — 2,000,000 input and 500,000 output tokens in total — costs $10.50 with GPT-5.2 Codex at its lowest rates. Use the calculator on this page for your own volumes.
Where can I use GPT-5.2 Codex?
GPT-5.2 Codex is available through OpenAI, from $1.75 per million input tokens.
What is GPT-5.2 Codex's context window?
GPT-5.2 Codex has a context window of 400,000 tokens, and returns up to 128,000 tokens in a single response.
Is GPT-5.2 Codex still available?
GPT-5.2 Codex is deprecated and was retired on 23 July 2026. The replacement is GPT-5.6 Sol.