Web Search

Use web search with haimaker to get real-time information from the internet.

Feature	Details
Supported Endpoints	- /chat/completions - /responses
Supported Providers	openai, xai, vertex_ai, anthropic, gemini, perplexity

Which Search Engine is Used?

Each provider uses their own search backend:

Provider	Search Engine	Notes
OpenAI (gpt-5-search-api, gpt-4o-search-preview, gpt-4o-mini-search-preview)	OpenAI's internal search	Real-time web data
xAI (grok-3)	xAI's search + X/Twitter	Real-time social media data
Google AI/Vertex (gemini-2.0-flash)	Google Search	Uses actual Google search results
Anthropic (claude-3-5-sonnet)	Anthropic's web search	Real-time web data
Perplexity	Perplexity's search engine	AI-powered search and reasoning

Important: Only Search Models Support web_search_options

For OpenAI, only dedicated search models support the web_search_options parameter:

• gpt-4o-search-preview
• gpt-4o-mini-search-preview
• gpt-5-search-api

Regular models like gpt-5, gpt-4.1, gpt-4o do not support web_search_options

The web_search_options parameter is optional

Search models (like gpt-4o-search-preview) automatically search the web even without the web_search_options parameter.

Use web_search_options when you need to:

• Adjust search_context_size ("low", "medium", "high")
• Specify user_location for localized results

info

Anthropic Web Search Models: Claude models that support web search: claude-3-5-sonnet-latest, claude-3-5-sonnet-20241022, claude-3-5-haiku-latest, claude-3-5-haiku-20241022, claude-3-7-sonnet-20250219

OpenAI Web Search: Two Approaches

OpenAI offers two distinct ways to use web search depending on the endpoint and model:

Approach	Endpoint	Models	How to enable
Search Models	/chat/completions	gpt-5-search-api, gpt-4o-search-preview, gpt-4o-mini-search-preview	Pass web_search_options parameter
Web Search Tool	/responses	gpt-5, gpt-4.1, gpt-4o, and other regular models	Pass web_search_preview tool

Search models search automatically

Search models like gpt-5-search-api automatically search the web even without the web_search_options parameter. Use web_search_options to set search_context_size ("low", "medium", "high") or specify user_location for localized results.

/chat/completions

Quick Start

Python

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.haimaker.ai/v1"
)

response = client.chat.completions.create(
    model="gpt-5-search-api",
    messages=[
        {
            "role": "user",
            "content": "What was a positive news story from today?"
        }
    ],
    extra_body={
        "web_search_options": {
            "search_context_size": "medium"  # Options: "low", "medium", "high"
        }
    }
)

print(response.choices[0].message.content)

cURL

curl https://api.haimaker.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "gpt-5-search-api",
    "messages": [
      {
        "role": "user",
        "content": "What was a positive news story from today?"
      }
    ],
    "web_search_options": {
      "search_context_size": "medium"
    }
  }'

Search Context Size

The search_context_size parameter controls how much search context is provided to the model:

Value	Description
"low"	Minimal search context, faster responses
"medium"	Balanced search context (default)
"high"	Maximum search context, more comprehensive

response = client.chat.completions.create(
    model="gpt-5-search-api",
    messages=[{"role": "user", "content": "What's happening in tech today?"}],
    extra_body={
        "web_search_options": {
            "search_context_size": "high"
        }
    }
)

Using Different Providers

xAI Grok

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.haimaker.ai/v1"
)

response = client.chat.completions.create(
    model="xai/grok-3",
    messages=[
        {
            "role": "user",
            "content": "What are people saying about AI on Twitter today?"
        }
    ],
    extra_body={
        "web_search_options": {
            "search_context_size": "high"
        }
    }
)

print(response.choices[0].message.content)

Anthropic Claude

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.haimaker.ai/v1"
)

response = client.chat.completions.create(
    model="anthropic/claude-3-5-sonnet-latest",
    messages=[
        {
            "role": "user",
            "content": "What are the latest developments in AI?"
        }
    ],
    extra_body={
        "web_search_options": {
            "search_context_size": "medium",
            "user_location": {
                "type": "approximate",
                "approximate": {
                    "city": "San Francisco"
                }
            }
        }
    }
)

print(response.choices[0].message.content)

Google Gemini

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.haimaker.ai/v1"
)

response = client.chat.completions.create(
    model="gemini/gemini-2.0-flash",
    messages=[
        {
            "role": "user",
            "content": "What are the top news stories today?"
        }
    ],
    extra_body={
        "web_search_options": {
            "search_context_size": "low"
        }
    }
)

print(response.choices[0].message.content)

/responses

Use the web_search_preview tool with models like gpt-5, gpt-4.1, gpt-4o, etc.

info

Search-dedicated models like gpt-5-search-api and gpt-4o-search-preview do not support the /responses endpoint. Use them with /chat/completions + web_search_options instead (see above).

Quick Start

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.haimaker.ai/v1"
)

response = client.responses.create(
    model="gpt-5",
    input="What is the capital of France?",
    tools=[{
        "type": "web_search_preview"  # enables web search with default medium context size
    }]
)

print(response.output_text)

Search Context Size

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.haimaker.ai/v1"
)

# Customize search context size
response = client.responses.create(
    model="gpt-5",
    input="What is the capital of France?",
    tools=[{
        "type": "web_search_preview",
        "search_context_size": "low"  # Options: "low", "medium" (default), "high"
    }]
)

print(response.output_text)

Checking if a Model Supports Web Search

Call the /v1/model_group/info endpoint to check if a model supports web search:

curl https://api.haimaker.ai/v1/model_group/info \
  -H "Authorization: Bearer YOUR_API_KEY"

The response includes a supports_web_search field for each model:

{
  "data": [
    {
      "model_group": "gpt-5-search-api",
      "providers": ["openai"],
      "max_tokens": 128000,
      "supports_web_search": true
    },
    {
      "model_group": "gpt-4o-search-preview",
      "providers": ["openai"],
      "max_tokens": 128000,
      "supports_web_search": true
    },
    {
      "model_group": "grok-3",
      "providers": ["xai"],
      "max_tokens": 131072,
      "supports_web_search": true
    },
    {
      "model_group": "gemini-2-flash",
      "providers": ["vertex_ai"],
      "max_tokens": 8192,
      "supports_web_search": true
    }
  ]
}

You can also check the full list of available models at haimaker.ai/models or call /v1/models for models available to your API key.