GPT-4o Search Previewis a specialized model for web search in Chat Completions. It is trained to understand and execute web search queries.
Modalities
Input Price
$2.50per 1M
Output Price
$10per 1M
Context
128K
Weekly Tokens
19.7M
Released
Mar 12, 2025
Create an API key from your OpenRouter dashboard and set it as an environment variable:
Use openai/gpt-4o-search-preview with the OpenRouter API:
OpenRouter provides an OpenAI-compatible completion API to 400+ models & providers that you can call directly, or using the OpenAI SDK. Additionally, some third-party SDKs are available.
In the examples below, the OpenRouter-specific headers are optional. Setting them allows your app to appear on the OpenRouter leaderboards.
For information about using third-party SDKs and frameworks with OpenRouter, please see our frameworks documentation.
Add "stream": true to your request body to receive responses as server-sent events:
Sends a request for a model response for the given chat conversation. Supports both streaming and non-streaming modes.
https://openrouter.ai/api/v1/chat/completionsBearer $OPENROUTER_API_KEYapplication/jsonoptional — your site URL, for rankingsoptional — your site name, for rankingsopenai/gpt-4o-search-previewCreates a streaming or non-streaming response using the OpenAI Responses API format.
Docshttps://openrouter.ai/api/v1/responsesBearer $OPENROUTER_API_KEYapplication/jsonoptional — your site URL, for rankingsoptional — your site name, for rankingsopenai/gpt-4o-search-previewCreates a message using the Anthropic Messages API format. Supports text, images, PDFs, tools, and extended thinking.
Docshttps://openrouter.ai/api/v1/messagesBearer $OPENROUTER_API_KEYapplication/jsonoptional — your site URL, for rankingsoptional — your site name, for rankingsopenai/gpt-4o-search-preview| Name | Type | Default | Description |
|---|---|---|---|
web_search_options | map | — | Configures native web search options for models and providers that support web-connected answers. |
max_tokens | integer | — | This sets the upper limit for the number of tokens the model can generate in response. |
response_format | map | — | Forces the model to produce specific output format. |