Logo
Back to all models

GPT-4o Search Preview - In-Depth Overview

OpenAI · GPT-4o

preview
Latest in family

Model ID: gpt-4o-search-preview

Get all the details on GPT-4o Search Preview, an AI model from OpenAI. This page covers its token limits, pricing structure, key capabilities such as web_browsing_via_tool, function_calling, available API code samples, and performance strengths.

Key Metrics

Input Limit

128K tokens

Output Limit

16.4K tokens

Input Cost

$2.50/1M

Output Cost

$10.00/1M

Sample API Code

from openai import OpenAI
client = OpenAI()
response = client.chat.completions.create(
    model="gpt-4o-search-preview",
    messages=[
        {"role": "user", "content": "What is the capital of France?"}
    ]
)
print(response.choices[0].message.content)

Required Libraries

openai
openai

Benchmarks

BenchmarkScoreSourceNotes
1000
LM ArenaScore for 'api-gpt-4o-search' model on LM Arena Search leaderboard.

Notes

GPT-4o Search Preview is a specialized model trained to understand and execute web search queries with the Chat Completions API. In addition to token fees, web search queries have a fee per tool call. It has a 128,000 context window and 16,384 max output tokens. Its knowledge cutoff is Oct 01, 2023. It supports snapshots for consistent performance.

Supported Data Types

Input Types

text

Output Types

text

Strengths & Weaknesses

Exceptional at

web search
information retrieval

Good at

grounded responses

Poor at

image understanding
audio processing
general reasoning
code generation

Additional Information

Latest Update

Mar 11, 2025

Knowledge Cutoff

Oct 1, 2023