OpenAI: GPT-4o Search Preview
GPT-4o Search Preview adds web-search capability to OpenAI's GPT-4o base, but without benchmark data of its own it cannot be scored above the conservative range. Businesses should treat this as a specialised search-augmented variant rather than a general-purpose reasoning model.
Assessment date: March 14, 2026
Our methodology takes into account a range of factors including pricing, functionality, capabilities, benchmark performance, and real-world applicability. Rankings are reviewed and updated regularly as new models are released. Issues with our rankings? Contact us
GPT-4o Search Previewis a specialized model for web search in Chat Completions. It is trained to understand and execute web search queries.
Architecture
| Modality | Text → Text |
| Tokenizer | GPT |
Model Information
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $2.50 | $0.002500 |
| Output | $10.00 | $0.010000 |
External Resources
Data sourced from OpenRouter API, Artificial Analysis and Hugging Face Open LLM Leaderboard. Scores are editorially curated by our team.
Last updated: March 15, 2026 7:52 pm