Skip to content
OpenKey

GPT-5.2 Chat

OpenAIReleased Dec 10, 2025

GPT-5.2 Chat (AKA Instant) is the fast, lightweight member of the 5.2 family, optimized for low-latency chat while retaining strong general intelligence. It uses adaptive reasoning to selectively “think” on...

Try in playground
Context window
128K tokens
Max output
16K tokens
Input
file, image, text
Output
text
Tokenizer
GPT
Released
Dec 10, 2025

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

Supported parameters

  • max_completion_tokens
  • max_tokens
  • 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-chat.

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-chat",
    "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-chat",
    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-chat",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);

Questions

How much does GPT-5.2 Chat cost via API?
Through OpenKey, GPT-5.2 Chat 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 Chat's context window?
GPT-5.2 Chat accepts up to 128K tokens of context and returns up to 16K tokens per request.
Is GPT-5.2 Chat OpenAI-compatible?
Yes. Send requests to OpenKey's /v1/chat/completions endpoint with model "openai/gpt-5.2-chat" using any OpenAI SDK — only the base URL and API key change.
What inputs does GPT-5.2 Chat support?
GPT-5.2 Chat accepts file, image, text input and produces text output.

More from OpenAI

All OpenAI models →