GPT-5 Search API API Pricing
As of October 10, 2026, GPT-5 Search API costs $1.25 per 1M input tokens and $10.00 per 1M output tokens on OpenAI, with cache reads at $0.125 per 1M tokens. It has a 272,000-token context window and returns up to 128,000 tokens per response.
- Input
- $1.25 / 1M tokens
- Output
- $10.00 / 1M tokens
- Cache read
- $0.125 / 1M tokens
- Context window
- 272,000 tokens
- Max output
- 128,000 tokens
- Providers
- 1
- Added to LiteLLM
- February 2026
GPT-5 Search API pricing by provider
2 listings across 1 provider. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.
Other GPT-5 Search API prices on OpenAI
| Web search | $10.00 per 1K searches |
What GPT-5 Search API costs in practice
1,000 requests with 2,000 input and 500 output tokens each
| OpenAI | $7.50 |
100 long-document requests with 100,000 input and 2,000 output tokens each
| OpenAI | $14.50 |
GPT-5 Search API features
- Function calling
- Parallel tool calls
- Structured output
- Image input
- PDF input
- Prompt caching
- Web search
Use GPT-5 Search API with LiteLLM
Call GPT-5 Search API through the LiteLLM Python SDK, or put it behind the LiteLLM proxy and send OpenAI-format requests to /v1/chat/completions. LiteLLM tracks the cost of every request at these prices.
from litellm import completion
response = completion(
model="gpt-5-search-api",
messages=[{"role": "user", "content": "Hello!"}],
)model_list:
- model_name: gpt-5-search-api
litellm_params:
model: gpt-5-search-api
api_key: os.environ/OPENAI_API_KEYcurl http://0.0.0.0:4000/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer sk-1234" \
-d '{
"model": "gpt-5-search-api",
"messages": [{"role": "user", "content": "Hello!"}]
}'GPT-5 Search API FAQ
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 on OpenAI, with cache reads at $0.125 per 1M tokens.
What is the context window of GPT-5 Search API?
GPT-5 Search API has a 272,000-token context window and returns up to 128,000 tokens per response.
Which providers offer GPT-5 Search API?
GPT-5 Search API is available from OpenAI through LiteLLM, using the model name gpt-5-search-api.
How do I call GPT-5 Search API with an OpenAI-compatible API?
Use the LiteLLM Python SDK with model="gpt-5-search-api", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/chat/completions from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.
What features does GPT-5 Search API support?
GPT-5 Search API supports function calling, parallel tool calls, structured output, image input, PDF input, prompt caching and web search.
When did LiteLLM add GPT-5 Search API?
GPT-5 Search API was added to LiteLLM's model price file in February 2026.
Sources
Prices come from LiteLLM's open-source model_prices_and_context_window.json, which LiteLLM uses to calculate the cost of every request. Provider pricing pages:
LiteLLM docs: OpenAI.
Provider pages: OpenAI.
