Skip to main content
Core.Today
|
OpenAIMediumUltra

GPT-5.2 Codex

Latest Codex generation built on the GPT-5.2 base. Brings GPT-5.2's stronger reasoning to agentic coding harnesses, served via the OpenAI Responses API.

3,251.5/26,012credits
input / output ยท per 1M tokens
Latest Codex generation on the GPT-5.2 base
Optimized for agentic coding harnesses (Codex-style)
Served via the Responses API - this gateway routes Codex models to /v1/responses, not chat completions
400K context window
Cached input tokens for cost savings on repeated context

Run it right now

Test this model instantly in the Console Playground โ€” no code required

Sign in to try

Use with AI Assistant

Copy usage instructions for Claude, ChatGPT, or other AI

Model Specifications

Context Window
400K
tokens
Max Output
128K
tokens
Training Cutoff
2025-03
Compatible SDK
OpenAI

Capabilities

Vision
Function Calling
Streaming
JSON Mode
System Prompt

Token Pricing (per 1M tokens)

Token TypeCreditsUSD Equivalent
Input Tokens3,251.5$2.17
Output Tokens26,012$17.34
Cached Tokens325.15$0.22

* 1,500 credits โ‰ˆ $1 (actual charges may vary based on usage)

Quick Start

curl -X POST "https://api.core.today/llm/openai/v1/responses" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer cdt_your_api_key" \
  -d '{
  "model": "gpt-5.2-codex",
  "input": "Diagnose why this async job queue occasionally drops tasks under load, then propose and implement a fix:\n\n<code snippet>",
  "max_output_tokens": 6000
}'

Parameters

ParameterTypeRequiredDefaultDescription
modelstringYesgpt-5.2-codexModel identifier
inputstring | arrayYes-Responses API input: a plain string or an array of input items (messages, tool results)
instructionsstringNo-System-level instructions for the run
max_output_tokensintegerNo-Maximum tokens in the response (Responses API field; not max_tokens)
streambooleanNofalseEnable Server-Sent Events streaming

Examples

Complex Coding Task

Responses API request using the newest Codex generation

curl -X POST "https://api.core.today/llm/openai/v1/responses" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer cdt_your_api_key" \
  -d '{
  "model": "gpt-5.2-codex",
  "input": "Diagnose why this async job queue occasionally drops tasks under load, then propose and implement a fix:\n\n<code snippet>",
  "max_output_tokens": 6000
}'

Tips & Best Practices

1Works with the OpenAI SDK - set base_url to https://ai.api.core.today/llm/openai/v1 and use client.responses.create()
2Codex models are served via the Responses API (POST /llm/openai/v1/responses), not chat completions
3Cached input tokens are billed at a ~10x discount - reuse long repository context across turns
4Use GPT-5.1 Codex Mini for lighter tasks - GPT-5.2 Codex is priced for the hardest work

Use Cases

Hardest coding tasks needing the newest Codex reasoning
Coding agents and autonomous dev loops
Complex debugging and architecture-level changes
Code review automation with high accuracy requirements