Grounding with Exa Web Search

Exa provides a search API that gives access to publicly available web data optimized for grounding large language model responses. This page explains how to ground Gemini responses by using Exa.

Grounding with Exa Web Search on Vertex AI is a Separate Offering (as defined in your Google Cloud Agreement) that connects Gemini models to public web data provided by Exa's search API .

Grounding with Exa Web Search is available as a Restricted Preview . To access this feature for your project, contact your Google Cloud account team to request addition to the allowlist.

Use cases

Grounding with Exa improves accuracy and reduces hallucinations by giving models access to fresh, relevant web data. Common use cases include:

• General agents and chatbots: Retrieve up-to-date information to produce more reliable answers.
• Research agents: Conduct deep web research across multiple sources.
• Coding agents: Pull the latest code snippets, documents, and technical references.
• Voice agents: Web retrieval to support real-time, low-latency voice interactions.
• Vertical-specific agents: Fetch up-to-date, domain-specific information tailored to a particular industry or knowledge vertical.
• Data enrichment: Augment internal datasets with current web context and metadata.
• Automated workflows: Periodically gather news, people, company, or other frequently updated data for internal or production workflows.

Example

Who won Superbowl 2026?

Supported models

This section lists the models that support Grounding with Exa Web Search.

Before you begin

To use Grounding with Exa, you need to get an API key from Exa's web site . This API key is used in your request to Gemini.

Ground Gemini responses with Exa

Request grounded responses from Gemini by using the REST API as follows. For best performance, we recommend using default settings for optional parameters unless you strictly require non-default values.

POST https:// LOCATION 
-aiplatform.googleapis.com/v1/projects/ PROJECT_ID 
/locations/ LOCATION 
/publishers/google/models/ MODEL_ID 
:generateContent

{
  "contents": [{
    "role": "user",
    "parts": [{
      "text": " TEXT 
"
    }]
  }],
  "tools": [{
    "exaAiSearch": {
        "api_key": " API_KEY 
",
        "customConfigs": {
            "excludeDomains": [" EXCLUDE_DOMAINS 
"],
            "includeDomains": [" INCLUDE_DOMAINS 
"],
            "contents": {
                "highlights": {
                    "maxCharacters": MAX_CHARACTERS 
}
            },
            "numResults": NUM_RESULTS 
}
    }
}],
  "model": "projects/ PROJECT_ID 
/locations/ LOCATION 
/publishers/google/models/ MODEL_ID 
"
}

curl -X POST \
-H "Authorization: Bearer $(gcloud auth print-access-token)" \
-H "Content-Type: application/json; charset=utf-8" \
-d @request.json \
"https:// LOCATION 
-aiplatform.googleapis.com/v1/projects/ PROJECT_ID 
/locations/ LOCATION 
/publishers/google/models/ MODEL_ID 
:generateContent"

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
-Method POST `
-Headers $headers `
-ContentType: "application/json; charset=utf-8" `
-InFile request.json `
-Uri "https:// LOCATION 
-aiplatform.googleapis.com/v1/projects/ PROJECT_ID 
/locations/ LOCATION 
/publishers/google/models/ MODEL_ID 
:generateContent" | Select-Object -Expand Content

{
  "candidates": [
    {
      "content": {
        "role": "model",
        "parts": [
          {
            "text": "The Seattle Seahawks won Super Bowl LX on February 8, 2026, defeating the New England Patriots with a final score of 29-13."
          }
        ]
      },
      "finishReason": "STOP",
      "groundingMetadata": {
        "webSearchQueries": [
          "who won the last super bowl"
        ],
        "groundingChunks": [
          {
            "web": {
              "uri": "https://...",
              "title": "Super Bowl LX",
              "domain": "domain.com"
            }
          },
          {
            "web": {
              "uri": "https://...",
              "title": "Super Bowl LX Results",
              "domain": "domain.com"
            }
          }
        ],
        "groundingSupports": [
          {
            "segment": {
              "endIndex": 125,
              "text": "The Seattle Seahawks won Super Bowl LX on February 8, 2026, defeating the New England Patriots with a final score of 29-13."
            },
            "groundingChunkIndices": [
              0,
              1
            ]
          }
        ]
      }
    }
  ],
  "usageMetadata": {
    "promptTokenCount": 33,
    "candidatesTokenCount": 106,
    "totalTokenCount": 284,
    "billablePromptUsage": {
      "textCount": 142
    },
    "trafficType": "ON_DEMAND",
    "promptTokensDetails": [
      {
        "modality": "TEXT",
        "tokenCount": 33
      }
    ],
    "candidatesTokensDetails": [
      {
        "modality": "TEXT",
        "tokenCount": 106
      }
    ],
    "toolUsePromptTokensDetails": [
      {
        "modality": "TEXT",
        "tokenCount": 39
      }
    ],
    "toolUsePromptTokenCount": 39,
    "thoughtsTokenCount": 106
  },
  "modelVersion": " MODEL_VERSION 
",
  "createTime": " CREATE_TIME 
",
  "responseId": " RESPONSE_ID 
"
}

Quota

The default quota is 200 prompts per minute. If you need to increase your rate limits, contact support@exa.ai and your Google account team with your use case and requirements.

Billing

The use of Grounding with Exa incurs the following charges:

• Gemini token consumption: Prompt tokens, thinking tokens, output tokens. For more information, see Pricing .
• Gemini's Grounding with your data: For more information, see Pricing .
• Pricing for the use of Exa's search API: For more information, see Exa's pricing page .