Skip to content
OpenKey

GPT-5.2-Codex

OpenAIReleased Jan 14, 2026

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....

Try in playground
Context window
400K tokens
Max output
128K tokens
Input
text, image
Output
text
Tokenizer
GPT
Released
Jan 14, 2026
Reasoning
always on

Pricing

Per 1M tokens. The provider price and our flat 3% fee are separate columns — what you pay is their sum.

Per 1M tokensProvider+ 3% feeYou pay
Input$1.75$0.052$1.80
Output$14.00$0.420$14.42
Cache read$0.175$0.0052$0.180

Benchmarks

Design Arena

CategoryEloWin rateRank
androidnativeagents117647.5%#15
Full-stackagents106037%#27
godotgamedevagents118748%#12
Mobile appsagents117247.7%#24
Web appsagents112540.4%#22

Head-to-head preference voting. How we filter and rank

Supported parameters

  • include_reasoning
  • max_completion_tokens
  • max_tokens
  • reasoning
  • response_format
  • seed
  • structured_outputs
  • tool_choice
  • tools

Call it

OpenAI-compatible: point your SDK at api.openkey.ai/v1 and use model openai/gpt-5.2-codex.

Code sample language
curl https://api.openkey.ai/v1/chat/completions \
  -H "Authorization: Bearer $OPENKEY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-5.2-codex",
    "messages": [{"role": "user", "content": "Hello"}]
  }'
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.openkey.ai/v1",
    api_key=os.environ["OPENKEY_API_KEY"],
)

completion = client.chat.completions.create(
    model="openai/gpt-5.2-codex",
    messages=[{"role": "user", "content": "Hello"}],
)
print(completion.choices[0].message.content)
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.openkey.ai/v1",
  apiKey: process.env.OPENKEY_API_KEY,
});

const completion = await client.chat.completions.create({
  model: "openai/gpt-5.2-codex",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);

Questions

How much does GPT-5.2-Codex cost via API?
Through OpenKey, GPT-5.2-Codex costs $1.80 per 1M input tokens and $14.42 per 1M output tokens. That is the provider price ($1.75 / $14.00) plus a flat 3% fee — nothing else.
What is GPT-5.2-Codex's context window?
GPT-5.2-Codex accepts up to 400K tokens of context and returns up to 128K tokens per request.
Is GPT-5.2-Codex OpenAI-compatible?
Yes. Send requests to OpenKey's /v1/chat/completions endpoint with model "openai/gpt-5.2-codex" using any OpenAI SDK — only the base URL and API key change.
What inputs does GPT-5.2-Codex support?
GPT-5.2-Codex accepts text, image input and produces text output.

More from OpenAI

All OpenAI models →