GPT-5 Search API
OpenAI's search model for building search-based text answers into applications through an OpenAI-compatible API.
Channel
Each channel is compared at its lowest input-price tier; output breaks ties. A dash means /api/pricing does not provide that rate. Selecting a channel updates the endpoints and call example below.
openai/gpt-5-search-apiEndpoints
/v1/chat/completionsChat CompletionsCall it
Using openai/gpt-5-search-api
1from openai import OpenAI23client = OpenAI(4 base_url="https://www.realrelay.ai/v1",5 api_key="sk-***",6)78response = client.chat.completions.create(9 model="openai/gpt-5-search-api",10 messages=[{"role": "user", "content": "Hello"}],11)1213print(response.choices[0].message.content)1import OpenAI from "openai";23const client = new OpenAI({4 baseURL: "https://www.realrelay.ai/v1",5 apiKey: process.env.REALRELAY_API_KEY,6});78const response = await client.chat.completions.create({9 model: "openai/gpt-5-search-api",10 messages: [{ role: "user", content: "Hello" }],11});1213console.log(response.choices[0].message.content);1curl https://www.realrelay.ai/v1/chat/completions \2 -H "Authorization: Bearer $REALRELAY_API_KEY" \3 -H "Content-Type: application/json" \4 -d '{5 "model": "openai/gpt-5-search-api",6 "messages": [{ "role": "user", "content": "Hello" }]7 }'Prices and availability as published on Oct 12, 2026.
Capabilities
GPT-5 Search API returns text output and is listed in the Search category of OpenAI's pricing.
Overview
GPT-5 Search API is a model from OpenAI that sits in the Search category of OpenAI's pricing. It returns text output, and input, cached input and output tokens are priced separately. You call it through RealRelay with the model ID openai/gpt-5-search-api, using standard OpenAI-style requests.
It returns text. Prices per 1M tokens are $1.25 for input, $0.125 for cached input and $10.00 for output.
Pricing
GPT-5 Search API costs $1.25 per 1M input tokens and $10.00 per 1M output tokens. Cached input reads cost $0.125 per 1M tokens. GPT-5 Search API is available through RealRelay's OpenAI-compatible API.
Use cases
Use GPT-5 Search API for applications built around search, such as question-answering assistants that return a written text answer to a user's query.
Its flat per-token pricing, with a lower rate for cached input, also suits assistants that reuse the same instructions across many requests. Because the model returns text, its answers can be shown directly in a chat interface or passed to other services.
Frequently asked questions
- What is GPT-5 Search API?
- GPT-5 Search API is a model from OpenAI that sits in the Search category of OpenAI's pricing.
- How much does GPT-5 Search API cost?
- GPT-5 Search API costs $1.25 per 1M input tokens and $10.00 per 1M output tokens. Cached input reads cost $0.125 per 1M tokens.
- What outputs does GPT-5 Search API return?
- GPT-5 Search API returns text.
- Does GPT-5 Search API have cached input pricing?
- Yes. Cached input for GPT-5 Search API costs $0.125 per 1M tokens, compared with $1.25 per 1M tokens for standard input.
- What is GPT-5 Search API used for?
- Use GPT-5 Search API for applications built around search, such as question-answering assistants that return a written text answer to a user's query.
- How do I call GPT-5 Search API via the API?
- Call GPT-5 Search API through RealRelay's OpenAI-compatible API by setting the model name to openai/gpt-5-search-api.
