Skip to content
OpenKey

GPT-4o Search Preview

OpenAIReleased Mar 12, 2025

GPT-4o Search Previewis a specialized model for web search in Chat Completions. It is trained to understand and execute web search queries.

Try in playground
Context window
128K tokens
Max output
16K tokens
Input
text
Output
text
Tokenizer
GPT
Knowledge cutoff
Oct 31, 2023
Released
Mar 12, 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$2.50$0.075$2.58
Output$10.00$0.300$10.30

Supported parameters

  • max_tokens
  • response_format
  • structured_outputs
  • web_search_options

Call it

OpenAI-compatible: point your SDK at api.openkey.ai/v1 and use model openai/gpt-4o-search-preview.

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-4o-search-preview",
    "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-4o-search-preview",
    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-4o-search-preview",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);

Questions

How much does GPT-4o Search Preview cost via API?
Through OpenKey, GPT-4o Search Preview costs $2.58 per 1M input tokens and $10.30 per 1M output tokens. That is the provider price ($2.50 / $10.00) plus a flat 3% fee — nothing else.
What is GPT-4o Search Preview's context window?
GPT-4o Search Preview accepts up to 128K tokens of context and returns up to 16K tokens per request.
Is GPT-4o Search Preview OpenAI-compatible?
Yes. Send requests to OpenKey's /v1/chat/completions endpoint with model "openai/gpt-4o-search-preview" using any OpenAI SDK — only the base URL and API key change.
What inputs does GPT-4o Search Preview support?
GPT-4o Search Preview accepts text input and produces text output. Its knowledge cutoff is Oct 31, 2023.

More from OpenAI

All OpenAI models →