Video understanding

Console

1. In the Vertex AI section of the Google Cloud console, go to the Vertex AI Studio page.

   Go to Vertex AI Studio

2. Click Create prompt.

3. Optional: Configure the model and parameters:

   • Model: Select a model.

4. Optional: To configure advanced parameters, click Advanced and configure as follows:

   Click to expand advanced configurations

   • Top-K: Use the slider or textbox to enter a value for top-K.

     Top-K changes how the model selects tokens for output. A top-K of 1 means the next selected token is the most probable among all tokens in the model's vocabulary (also called greedy decoding), while a top-K of 3 means that the next token is selected from among the three most probable tokens by using temperature.

     For each token selection step, the top-K tokens with the highest probabilities are sampled. Then tokens are further filtered based on top-P with the final token selected using temperature sampling.

     Specify a lower value for less random responses and a higher value for more random responses.

   • Top-P: Use the slider or textbox to enter a value for top-P. Tokens are selected from most probable to the least until the sum of their probabilities equals the value of top-P. For the least variable results, set top-P to 0.
   • Max responses: Use the slider or textbox to enter a value for the number of responses to generate.
   • Streaming responses: Enable to print responses as they're generated.
   • Safety filter threshold: Select the threshold of how likely you are to see responses that could be harmful.
   • Enable Grounding: Grounding isn't supported for multimodal prompts.
   • Region: Select the region that you want to use.
   • Temperature: Use the slider or textbox to enter a value for temperature.

         
     The temperature is used for sampling during response generation, which occurs when topP
     and topK are applied. Temperature controls the degree of randomness in token selection.
     Lower temperatures are good for prompts that require a less open-ended or creative response, while
     higher temperatures can lead to more diverse or creative results. A temperature of 0
     means that the highest probability tokens are always selected. In this case, responses for a given
     prompt are mostly deterministic, but a small amount of variation is still possible.
     
     If the model returns a response that's too generic, too short, or the model gives a fallback
     response, try increasing the temperature.
     
       <li>**Output token limit**: Use the slider or textbox to enter a value for
         the max output limit.
     
         
     Maximum number of tokens that can be generated in the response. A token is
     approximately four characters. 100 tokens correspond to roughly 60-80 words.
     
     Specify a lower value for shorter responses and a higher value for potentially longer
     responses.
     
       <li>**Add stop sequence**: Optional. Enter a stop sequence, which is a
         series of characters that includes spaces. If the model encounters a
         stop sequence, the response generation stops. The stop sequence isn't
         included in the response, and you can add up to five stop sequences.
     </ul>
     

5. Click Insert Media, and select a source for your file.

   Upload

   Select the file that you want to upload and click Open.

   By URL

   Enter the URL of the file that you want to use and click Insert.

   YouTube

   Enter the URL of the YouTube video that you want to use and click Insert.

   You can use any public video or a video that's owned by the account that you used to sign in to the Google Cloud console.

   Cloud Storage

   Select the bucket and then the file from the bucket that you want to import and click Select.

   Google Drive

   1. Choose an account and give consent to Vertex AI Studio to access your account the first time you select this option. You can upload multiple files that have a total size of up to 10 MB. A single file can't exceed 7 MB.
   2. Click the file that you want to add.

   3. Click Select.

      The file thumbnail displays in the Prompt pane. The total number of tokens also displays. If your prompt data exceeds the token limit, the tokens are truncated and aren't included in processing your data.

6. Enter your text prompt in the Prompt pane.

7. Optional: To view the Token ID to text and Token IDs, click the tokens count in the Prompt pane.

8. Click Submit.

9. Optional: To save your prompt to My prompts, click save_alt Save.

10. Optional: To get the Python code or a curl command for your prompt, click code Build with code > Get code.

Python

Install

pip install --upgrade google-genai

To learn more, see the SDK reference documentation.

Set environment variables to use the Gen AI SDK with Vertex AI:

# Replace the `GOOGLE_CLOUD_PROJECT` and `GOOGLE_CLOUD_LOCATION` values
# with appropriate values for your project.
export GOOGLE_CLOUD_PROJECT=GOOGLE_CLOUD_PROJECT
export GOOGLE_CLOUD_LOCATION=global
export GOOGLE_GENAI_USE_VERTEXAI=True

from google import genai
from google.genai.types import HttpOptions, Part

client = genai.Client(http_options=HttpOptions(api_version="v1"))
response = client.models.generate_content(
    model="gemini-2.5-flash",
    contents=[
        Part.from_uri(
            file_uri="gs://cloud-samples-data/generative-ai/video/ad_copy_from_video.mp4",
            mime_type="video/mp4",
        ),
        "What is in the video?",
    ],
)
print(response.text)
# Example response:
# The video shows several people surfing in an ocean with a coastline in the background. The camera ...

Go

Learn how to install or update the Go.

To learn more, see the SDK reference documentation.

Set environment variables to use the Gen AI SDK with Vertex AI:

# Replace the `GOOGLE_CLOUD_PROJECT` and `GOOGLE_CLOUD_LOCATION` values
# with appropriate values for your project.
export GOOGLE_CLOUD_PROJECT=GOOGLE_CLOUD_PROJECT
export GOOGLE_CLOUD_LOCATION=global
export GOOGLE_GENAI_USE_VERTEXAI=True

import (
	"context"
	"fmt"
	"io"

	genai "google.golang.org/genai"
)

// generateWithMuteVideo shows how to generate text using a video with no sound as the input.
func generateWithMuteVideo(w io.Writer) error {
	ctx := context.Background()

	client, err := genai.NewClient(ctx, &genai.ClientConfig{
		HTTPOptions: genai.HTTPOptions{APIVersion: "v1"},
	})
	if err != nil {
		return fmt.Errorf("failed to create genai client: %w", err)
	}

	modelName := "gemini-2.5-flash"
	contents := []*genai.Content{
		{Parts: []*genai.Part{
			{Text: "What is in the video?"},
			{FileData: &genai.FileData{
				FileURI:  "gs://cloud-samples-data/generative-ai/video/ad_copy_from_video.mp4",
				MIMEType: "video/mp4",
			}},
		},
			Role: "user"},
	}

	resp, err := client.Models.GenerateContent(ctx, modelName, contents, nil)
	if err != nil {
		return fmt.Errorf("failed to generate content: %w", err)
	}

	respText := resp.Text()

	fmt.Fprintln(w, respText)

	// Example response:
	// The video shows several surfers riding waves in an ocean setting. The waves are ...

	return nil
}

REST

After you set up your environment, you can use REST to test a text prompt. The following sample sends a request to the publisher model endpoint.

Before using any of the request data, make the following replacements:

• PROJECT_ID: Your project ID.
• FILE_URI: The URI or URL of the file to include in the prompt. Acceptable values include the following:
  • Cloud Storage bucket URI: The object must either be publicly readable or reside in the same Google Cloud project that's sending the request. For gemini-2.0-flash and gemini-2.0-flash-lite, the size limit is 2 GB.
  • HTTP URL: The file URL must be publicly readable. You can specify one video file, one audio file, and up to 10 image files per request. Audio files, video files, and documents can't exceed 15 MB.
  • YouTube video URL:The YouTube video must be either owned by the account that you used to sign in to the Google Cloud console or is public. Only one YouTube video URL is supported per request.

  When specifying a fileURI, you must also specify the media type (mimeType) of the file. If VPC Service Controls is enabled, specifying a media file URL for fileURI is not supported.

  If you don't have a video file in Cloud Storage, then you can use the following publicly available file: gs://cloud-samples-data/video/animals.mp4 with a mime type of video/mp4. To view this video, open the sample MP4 file.

• MIME_TYPE: The media type of the file specified in the data or fileUri fields. Acceptable values include the following:

  Click to expand MIME types

  • application/pdf
  • audio/mpeg
  • audio/mp3
  • audio/wav
  • image/png
  • image/jpeg
  • image/webp
  • text/plain
  • video/mov
  • video/mpeg
  • video/mp4
  • video/mpg
  • video/avi
  • video/wmv
  • video/mpegps
  • video/flv
• TEXT: The text instructions to include in the prompt. For example, What is in the video?

To send your request, choose one of these options:

cat > request.json << 'EOF'
{
  "contents": {
    "role": "USER",
    "parts": [
      {
        "fileData": {
          "fileUri": "FILE_URI",
          "mimeType": "MIME_TYPE"
        }
      },
      {
        "text": "TEXT"
      }
    ]
  }
}
EOF

curl -X POST \
     -H "Authorization: Bearer $(gcloud auth print-access-token)" \
     -H "Content-Type: application/json; charset=utf-8" \
     -d @request.json \
     "https://aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/global/publishers/google/models/gemini-2.5-flash:generateContent"

@'
{
  "contents": {
    "role": "USER",
    "parts": [
      {
        "fileData": {
          "fileUri": "FILE_URI",
          "mimeType": "MIME_TYPE"
        }
      },
      {
        "text": "TEXT"
      }
    ]
  }
}
'@  | Out-File -FilePath request.json -Encoding utf8

$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://aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/global/publishers/google/models/gemini-2.5-flash:generateContent" | Select-Object -Expand Content

You should receive a JSON response similar to the following.

{
  "candidates": [
    {
      "content": {
        "role": "model",
        "parts": [
          {
            "text": "This video is a commercial for Google Photos, featuring animals taking selfies
              with the Google Photos app. The commercial plays on the popularity of media in which
              animals act like humans, especially their use of technology. The commercial also
              highlights the app's ability to automatically back up photos."
          }
        ]
      },
      "finishReason": "STOP",
      "safetyRatings": [
        {
          "category": "HARM_CATEGORY_HATE_SPEECH",
          "probability": "NEGLIGIBLE",
          "probabilityScore": 0.053601142,
          "severity": "HARM_SEVERITY_NEGLIGIBLE",
          "severityScore": 0.053799648
        },
        {
          "category": "HARM_CATEGORY_DANGEROUS_CONTENT",
          "probability": "NEGLIGIBLE",
          "probabilityScore": 0.06278921,
          "severity": "HARM_SEVERITY_NEGLIGIBLE",
          "severityScore": 0.07850098
        },
        {
          "category": "HARM_CATEGORY_HARASSMENT",
          "probability": "NEGLIGIBLE",
          "probabilityScore": 0.090253234,
          "severity": "HARM_SEVERITY_NEGLIGIBLE",
          "severityScore": 0.058453236
        },
        {
          "category": "HARM_CATEGORY_SEXUALLY_EXPLICIT",
          "probability": "NEGLIGIBLE",
          "probabilityScore": 0.1647851,
          "severity": "HARM_SEVERITY_NEGLIGIBLE",
          "severityScore": 0.09285216
        }
      ]
    }
  ],
  "usageMetadata": {
    "promptTokenCount": 28916,
    "candidatesTokenCount": 61,
    "totalTokenCount": 28977
  }
}

• Use the generateContent method to request that the response is returned after it's fully generated. To reduce the perception of latency to a human audience, stream the response as it's being generated by using the streamGenerateContent method.
• The multimodal model ID is located at the end of the URL before the method (for example, gemini-2.0-flash). This sample might support other models as well.

Python

Install

pip install --upgrade google-genai

To learn more, see the SDK reference documentation.

Set environment variables to use the Gen AI SDK with Vertex AI:

# Replace the `GOOGLE_CLOUD_PROJECT` and `GOOGLE_CLOUD_LOCATION` values
# with appropriate values for your project.
export GOOGLE_CLOUD_PROJECT=GOOGLE_CLOUD_PROJECT
export GOOGLE_CLOUD_LOCATION=global
export GOOGLE_GENAI_USE_VERTEXAI=True

from google import genai
from google.genai.types import HttpOptions, Part

client = genai.Client(http_options=HttpOptions(api_version="v1"))
response = client.models.generate_content(
    model="gemini-2.5-flash",
    contents=[
        Part.from_uri(
            file_uri="gs://cloud-samples-data/generative-ai/video/ad_copy_from_video.mp4",
            mime_type="video/mp4",
        ),
        "What is in the video?",
    ],
)
print(response.text)
# Example response:
# The video shows several people surfing in an ocean with a coastline in the background. The camera ...

REST

After you set up your environment, you can use REST to test a text prompt. The following sample sends a request to the publisher model endpoint.

Before using any of the request data, make the following replacements:

• PROJECT_ID: .
• FILE_URI: The URI or URL of the file to include in the prompt. Acceptable values include the following:
  • Cloud Storage bucket URI: The object must either be publicly readable or reside in the same Google Cloud project that's sending the request. For gemini-2.0-flash and gemini-2.0-flash-lite, the size limit is 2 GB.
  • HTTP URL: The file URL must be publicly readable. You can specify one video file, one audio file, and up to 10 image files per request. Audio files, video files, and documents can't exceed 15 MB.
  • YouTube video URL:The YouTube video must be either owned by the account that you used to sign in to the Google Cloud console or is public. Only one YouTube video URL is supported per request.

  When specifying a fileURI, you must also specify the media type (mimeType) of the file. If VPC Service Controls is enabled, specifying a media file URL for fileURI is not supported.

  If you don't have a video file in Cloud Storage, then you can use the following publicly available file: gs://cloud-samples-data/generative-ai/video/pixel8.mp4 with a mime type of video/mp4. To view this video, open the sample MP4 file.

• MIME_TYPE: The media type of the file specified in the data or fileUri fields. Acceptable values include the following:

  Click to expand MIME types

  • application/pdf
  • audio/mpeg
  • audio/mp3
  • audio/wav
  • image/png
  • image/jpeg
  • image/webp
  • text/plain
  • video/mov
  • video/mpeg
  • video/mp4
  • video/mpg
  • video/avi
  • video/wmv
  • video/mpegps
  • video/flv
• TEXT

  The text instructions to include in the prompt. For example, Provide a description of the video. The description should also contain anything important which people say in the video.

To send your request, choose one of these options:

cat > request.json << 'EOF'
{
  "contents": {
    "role": "USER",
    "parts": [
      {
        "fileData": {
          "fileUri": "FILE_URI",
          "mimeType": "MIME_TYPE"
        }
      },
      {
        "text": "TEXT"
      }
    ]
  }
}
EOF

curl -X POST \
     -H "Authorization: Bearer $(gcloud auth print-access-token)" \
     -H "Content-Type: application/json; charset=utf-8" \
     -d @request.json \
     "https://aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/global/publishers/google/models/gemini-2.5-flash:generateContent"

@'
{
  "contents": {
    "role": "USER",
    "parts": [
      {
        "fileData": {
          "fileUri": "FILE_URI",
          "mimeType": "MIME_TYPE"
        }
      },
      {
        "text": "TEXT"
      }
    ]
  }
}
'@  | Out-File -FilePath request.json -Encoding utf8

$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://aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/global/publishers/google/models/gemini-2.5-flash:generateContent" | Select-Object -Expand Content

You should receive a JSON response similar to the following.

{
  "candidates": [
    {
      "content": {
        "role": "model",
        "parts": [
          {
            "text": "The video opens with a shot of a train traveling over a bridge in the night. \n
              \nThe scene changes to a woman walking in the streets of Tokyo. She says "My name is
              Saeko. I am a photographer in Tokyo. Tokyo has many faces. The city at night
              is totally different from what you see during the day. The new Pixel has a feature
              called "Video Boost". In low light, it activates "Night Sight" to make the quality
              even better." \n\nShe then uses her phone to take several photos of different parts of
              the city including a street with a lot of shops, a small alleyway, and a small
              restaurant. She says "Sancha is where I used to live when I first moved to Tokyo. I
              have a lot of great memories here. Oh, I like this." \n\nShe smiles and says
              "Beautiful".\n\nThe video ends with the woman standing in a different part of the
              city. She says "Next, I came to Shibuya." The scene shows the famous Shibuya crossing
              in the night. \n\nThe video features a woman showcasing the camera features of the
              Google Pixel phone while walking around the streets of Tokyo. She mentions "Night
              Sight" and "Video Boost" features. \n"
          }
        ]
      },
      "finishReason": "STOP",
      "safetyRatings": [
        {
          "category": "HARM_CATEGORY_HATE_SPEECH",
          "probability": "NEGLIGIBLE",
          "probabilityScore": 0.053601142,
          "severity": "HARM_SEVERITY_NEGLIGIBLE",
          "severityScore": 0.053799648
        },
        {
          "category": "HARM_CATEGORY_DANGEROUS_CONTENT",
          "probability": "NEGLIGIBLE",
          "probabilityScore": 0.06278921,
          "severity": "HARM_SEVERITY_NEGLIGIBLE",
          "severityScore": 0.07850098
        },
        {
          "category": "HARM_CATEGORY_HARASSMENT",
          "probability": "NEGLIGIBLE",
          "probabilityScore": 0.090253234,
          "severity": "HARM_SEVERITY_NEGLIGIBLE",
          "severityScore": 0.058453236
        },
        {
          "category": "HARM_CATEGORY_SEXUALLY_EXPLICIT",
          "probability": "NEGLIGIBLE",
          "probabilityScore": 0.1647851,
          "severity": "HARM_SEVERITY_NEGLIGIBLE",
          "severityScore": 0.09285216
        }
      ]
    }
  ],
  "usageMetadata": {
    "promptTokenCount": 28916,
    "candidatesTokenCount": 61,
    "totalTokenCount": 28977
  }
}

• Use the generateContent method to request that the response is returned after it's fully generated. To reduce the perception of latency to a human audience, stream the response as it's being generated by using the streamGenerateContent method.
• The multimodal model ID is located at the end of the URL before the method (for example, gemini-2.0-flash). This sample might support other models as well.

Console

1. In the Vertex AI section of the Google Cloud console, go to the Vertex AI Studio page.

   Go to Vertex AI Studio

2. Click Create prompt.

3. Optional: Configure the model and parameters:

   • Model: Select a model.

4. Optional: To configure advanced parameters, click Advanced and configure as follows:

   Click to expand advanced configurations

   • Top-K: Use the slider or textbox to enter a value for top-K.

     Top-K changes how the model selects tokens for output. A top-K of 1 means the next selected token is the most probable among all tokens in the model's vocabulary (also called greedy decoding), while a top-K of 3 means that the next token is selected from among the three most probable tokens by using temperature.

     For each token selection step, the top-K tokens with the highest probabilities are sampled. Then tokens are further filtered based on top-P with the final token selected using temperature sampling.

     Specify a lower value for less random responses and a higher value for more random responses.

   • Top-P: Use the slider or textbox to enter a value for top-P. Tokens are selected from most probable to the least until the sum of their probabilities equals the value of top-P. For the least variable results, set top-P to 0.
   • Max responses: Use the slider or textbox to enter a value for the number of responses to generate.
   • Streaming responses: Enable to print responses as they're generated.
   • Safety filter threshold: Select the threshold of how likely you are to see responses that could be harmful.
   • Enable Grounding: Grounding isn't supported for multimodal prompts.
   • Region: Select the region that you want to use.
   • Temperature: Use the slider or textbox to enter a value for temperature.

         
     The temperature is used for sampling during response generation, which occurs when topP
     and topK are applied. Temperature controls the degree of randomness in token selection.
     Lower temperatures are good for prompts that require a less open-ended or creative response, while
     higher temperatures can lead to more diverse or creative results. A temperature of 0
     means that the highest probability tokens are always selected. In this case, responses for a given
     prompt are mostly deterministic, but a small amount of variation is still possible.
     
     If the model returns a response that's too generic, too short, or the model gives a fallback
     response, try increasing the temperature.
     
       <li>**Output token limit**: Use the slider or textbox to enter a value for
         the max output limit.
     
         
     Maximum number of tokens that can be generated in the response. A token is
     approximately four characters. 100 tokens correspond to roughly 60-80 words.
     
     Specify a lower value for shorter responses and a higher value for potentially longer
     responses.
     
       <li>**Add stop sequence**: Optional. Enter a stop sequence, which is a
         series of characters that includes spaces. If the model encounters a
         stop sequence, the response generation stops. The stop sequence isn't
         included in the response, and you can add up to five stop sequences.
     </ul>
     

5. Click Insert Media, and select a source for your file.

   Upload

   Select the file that you want to upload and click Open.

   By URL

   Enter the URL of the file that you want to use and click Insert.

   YouTube

   Enter the URL of the YouTube video that you want to use and click Insert.

   You can use any public video or a video that's owned by the account that you used to sign in to the Google Cloud console.

   Cloud Storage

   Select the bucket and then the file from the bucket that you want to import and click Select.

   Google Drive

   1. Choose an account and give consent to Vertex AI Studio to access your account the first time you select this option. You can upload multiple files that have a total size of up to 10 MB. A single file can't exceed 7 MB.
   2. Click the file that you want to add.

   3. Click Select.

      The file thumbnail displays in the Prompt pane. The total number of tokens also displays. If your prompt data exceeds the token limit, the tokens are truncated and aren't included in processing your data.

6. Enter your text prompt in the Prompt pane.

7. Optional: To view the Token ID to text and Token IDs, click the tokens count in the Prompt pane.

8. Click Submit.

9. Optional: To save your prompt to My prompts, click save_alt Save.

10. Optional: To get the Python code or a curl command for your prompt, click code Build with code > Get code.