GPT-4o Search Preview

openai/gpt-4o-search-preview
JSON
by OpenAI · 2025-03-12

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

ctx128K tokens
Max output16.4K
Inputtext
Outputtext
INPUT$2.50/ 1M tokens
OUTPUT$10.00/ 1M tokens
p50 TTFTCollecting…
p95 TTFTCollecting…
TRAFFICCollecting…

GPT-4o Search Preview is a text-only model from OpenAI, offered as part of the GPT-4o family. It is accessible via OrcaRouter's API at the base URL https://api.orcarouter.ai/v1 under the model…

What is GPT-4o Search Preview?

Who should use this model?

What are its key specifications?

How does it relate to the broader GPT-4o family?

Code samples

Call from any SDK

OpenAI-compatible — keep the SDK you already use

  • OpenAI SDKhttps://api.orcarouter.ai/v1
from openai import OpenAI

client = OpenAI(
    base_url="https://api.orcarouter.ai/v1",
    api_key="$ORCAROUTER_API_KEY",
)

response = client.chat.completions.create(
    model="openai/gpt-4o-search-preview",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Supported parameters

  • max_tokens
  • response_format
  • stream
  • structured_outputs
  • web_search_options

Pricing

Input / 1M tokens$2.50
Output / 1M tokens$10.00
CurrencyUSD

Cost calculator

Tokens / month10MM
Input share70%%
Estimated / month $47.50

Estimate based on list price

Token & cost estimator

Input tokens: 20Cost per request: $0.005050

Estimate only — actual token counts depend on the provider's tokenizer.

Performance

p50 TTFT
Collecting…
Output speed
Collecting…
p95 TTFT
Collecting…
Error rate
Collecting…

Public benchmarks

Source: Design Arena

How it compares

GPT-4o Search PreviewGPT-5.2 ProGPT-5.4 ProGPT-5.5
Input $/M$2.50$21.00$60.00$5.00
Output $/M$10.00$168.00$270.00$30.00
Context128K400K1.1M
Quality3/1010/1010/1010/10
Compare side-by-sideCompare side-by-sideCompare side-by-sideCompare side-by-side

FAQ

What is the cost per token for GPT-4o Search Preview on OrcaRouter?
Input tokens are billed at $2.50 per 1 million tokens, and output tokens at $10.00 per 1 million tokens. There is no markup – you pay exactly the provider rate.
What is the context window size?
The model supports a 128,000-token context window and can generate up to 16,384 tokens per response.
What are the main strengths of GPT-4o Search Preview?
It offers a very large context window and is optimized for text-only search-related tasks. It is priced at the same per-token rate as standard GPT-4o, with zero markup on OrcaRouter.
How does it compare to the standard GPT-4o model?
The standard GPT-4o supports multimodal inputs (text, images, audio), while Search Preview is text-only. Both have identical context windows and pricing. Search Preview may be better for search-centric text tasks, but no benchmarks confirm this.
Does OrcaRouter store or use my data for training?
Data handling policies depend on OrcaRouter's terms. The model itself is provided by OpenAI. OrcaRouter does not add any markup, but you should review OrcaRouter's privacy policy for data usage details.
How do I call GPT-4o Search Preview using an OpenAI-compatible API?
Set the base URL to https://api.orcarouter.ai/v1 and use the model ID "openai/gpt-4o-search-preview". Include your OrcaRouter API key in the Authorization header. Standard OpenAI client libraries work without modification.
Can this model process images or audio?
No. GPT-4o Search Preview accepts only text inputs. For multimodal tasks, use the standard GPT-4o model.
Are there any published benchmark scores for this model?
OpenAI has not released benchmark scores specifically for the Search Preview variant. It is part of the GPT-4o family, but no official performance numbers are available.

Embed this badge

OpenAI: GPT-4o Search Preview$2.50/M invia OrcaRouter
HTML <a href="https://www.orcarouter.ai/models/openai/gpt-4o-search-preview" target="_blank"> <img src="https://www.orcarouter.ai/embed/openai/gpt-4o-search-preview.svg" alt="OpenAI: GPT-4o Search Preview on OrcaRouter" /> </a>
Markdown [![OpenAI: GPT-4o Search Preview](https://www.orcarouter.ai/embed/openai/gpt-4o-search-preview.svg)](https://www.orcarouter.ai/models/openai/gpt-4o-search-preview)

Model card as data

GET /api/public/models/openai/gpt-4o-search-previewOpen
Machine-readable:/llms.txt/llms-full.txt