modelgrep
O

OpenAI: GPT-4o Search Preview

openai/gpt-4o-search-preview

JSON
Use via OpenRouter ↗
Intelligence
Design Elo
Speed
76
114th fastest
Latency
2.2s
first token
Input price
$2.50
257th cheapest
Context
128K
16K max out

How it compares

Faster than63%
of all ranked models
Cheaper than14%
of all ranked models

Overview

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

Providers & pricing (1)

ProviderIn $/MOut $/MUptime
OpenAI$2.50$10.00

Specifications

Context window128K
Max output16K
Knowledge cutoffOct 2023
Input modalitiestext
Output modalitiestext
Prompt caching
Cache read price
ModeratedYes

GPT-4o Search Preview FAQ

How much does GPT-4o Search Preview cost?

GPT-4o Search Preview costs $2.50 per million input tokens and $10.00 per million output tokens via OpenRouter, making it 257th cheapest of 298 paid models.

How fast is GPT-4o Search Preview?

GPT-4o Search Preview generates around 76 tokens per second with 2.2s time-to-first-token (p50), the 114th fastest tracked model.

What is GPT-4o Search Preview's context window?

GPT-4o Search Preview supports a 128K-token context window and can output up to 16K tokens. It accepts text input.

Compare head-to-head