GPT-4o-mini Search Preview

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

GPT-4o mini Search Preview is 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$0.15/ 1M tokens
OUTPUT$0.60/ 1M tokens
p50 TTFTCollecting…
p95 TTFTCollecting…
TRAFFICCollecting…

GPT-4o-mini Search Preview is a variant of OpenAI's GPT-4o-mini model that includes built-in web search capabilities. It is designed to provide answers that incorporate real-time information from the…

What is GPT-4o-mini Search Preview?

Who should use this model?

Key specifications

How does the search preview work?

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-mini-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$0.150
Output / 1M tokens$0.600
CurrencyUSD

Cost calculator

Tokens / month10MM
Input share70%%
Estimated / month $2.85

Estimate based on list price

Token & cost estimator

Input tokens: 20Cost per request: $0.000303

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-mini Search PreviewGPT-5.2 ProGPT-5.4 ProGPT-5.5
Input $/M$0.15$21.00$60.00$5.00
Output $/M$0.60$168.00$270.00$30.00
Context128K400K1.1M
Quality2/1010/1010/1010/10
Compare side-by-sideCompare side-by-sideCompare side-by-sideCompare side-by-side

FAQ

What is the cost to use GPT-4o-mini Search Preview on OrcaRouter?
Pricing is $0.15 per million input tokens and $0.60 per million output tokens, billed at the provider rate with zero markup. You pay exactly what OpenAI charges, with no additional fees.
What is the context window and max output length?
The context window is 128,000 tokens. Maximum output length is 16,384 tokens. The model accepts text inputs only.
What are the main strengths of GPT-4o-mini Search Preview?
Its strengths include built-in web search for up-to-date information, large context window, fast inference compared to GPT-4o, and low cost. It is ideal for applications needing current data without separate search APIs.
How does it compare to the base GPT-4o-mini?
Both have identical pricing and specifications except that the Search Preview variant can perform web searches. The base model relies only on its training data. Choose Search Preview if you need live information; otherwise the base model offers similar performance at the same price.
Does OrcaRouter train on my data?
OrcaRouter does not use customer data for training. Data handling follows OpenAI's and OrcaRouter's policies. Typically, data is not used to improve models unless explicitly opted in. Refer to OrcaRouter's privacy policy for specifics.
How do I call the model via OrcaRouter's API?
Use the base URL https://api.orcarouter.ai/v1 with an OpenAI-compatible client. Set the model parameter to "openai/gpt-4o-mini-search-preview". Include your OrcaRouter API key in the Authorization header. All standard chat completion parameters are supported.
What types of queries trigger the search preview?
The model automatically decides when to search the web, typically for questions about recent events, current data, or information likely to have changed since its training cutoff. You can also prompt it explicitly to search for specific topics.
Is there any additional latency for search preview?
Yes, the web retrieval adds some latency compared to the base GPT-4o-mini. Typical response times are a few seconds. You can use streaming to show partial responses.

Embed this badge

OpenAI: GPT-4o-mini Search Preview$0.15/M invia OrcaRouter
HTML <a href="https://www.orcarouter.ai/models/openai/gpt-4o-mini-search-preview" target="_blank"> <img src="https://www.orcarouter.ai/embed/openai/gpt-4o-mini-search-preview.svg" alt="OpenAI: GPT-4o-mini Search Preview on OrcaRouter" /> </a>
Markdown [![OpenAI: GPT-4o-mini Search Preview](https://www.orcarouter.ai/embed/openai/gpt-4o-mini-search-preview.svg)](https://www.orcarouter.ai/models/openai/gpt-4o-mini-search-preview)

Model card as data

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