Use Anthropic's Claude models

You can stream your Claude responses to reduce the end-user latency perception. A streamed response uses server-sent events (SSE) to incrementally stream the response.

You pay for Claude models as you use them (pay as you go), or you pay a fixed fee when using provision throughput. For pay-as-you-go pricing, see Anthropic Claude models on the Vertex AI pricing page.

Available Claude models

The following models are available from Anthropic to use in Vertex AI. To access a Claude model, go to its Model Garden model card.

Claude 3.5 Sonnet v2

Claude 3.5 Sonnet v2 is a state-of-the-art model for real-world software engineering tasks and agentic capabilities. Claude 3.5 Sonnet v2 delivers these advancements at the same price and speed as Claude 3.5 Sonnet.

The upgraded Claude 3.5 Sonnet model is capable of interacting with tools that can manipulate a computer desktop environment. For more information, see the Anthropic documentation.

Claude 3.5 Sonnet is optimized for the following use cases:

• Agentic tasks and tool use - Claude 3.5 Sonnet offers superior instruction following, tool selection, error correction, and advanced reasoning for agentic workflows that require tool use.
• Coding - For software development tasks ranging from code migrations, code fixes, and translations, Claude 3.5 Sonnet offers strong performance in both planning and solving for complex coding tasks.
• Document Q&A - Claude 3.5 Sonnet combines strong context comprehension, advanced reasoning, and synthesis to deliver accurate and human-like responses.
• Visual data extraction - With Claude 3.5 Sonnet leading vision skills, Claude 3.5 Sonnet can extract raw data from visuals like charts or graphs as part of AI workflows.
• Content generation and analysis - Claude 3.5 Sonnet can understand nuance and tone in content, generating more compelling content and analyzing content on a deeper level.

Go to the Claude 3.5 Sonnet v2 model card

Claude 3.5 Haiku

Claude 3.5 Haiku, the next generation of Anthropic's fastest and most cost-effective model, is optimal for use cases where speed and affordability matter. It improves on its predecessor across every skill set. Claude 3.5 Haiku is optimized for the following use cases:

• Code completions - With its rapid response time and understanding of programming patterns, Claude 3.5 Haiku excels at providing quick, accurate code suggestions and completions in real-time development workflows.
• Interactive chat bots - Claude 3.5 Haiku's improved reasoning and natural conversation abilities make it ideal for creating responsive, engaging chatbots that can handle high volumes of user interactions efficiently.
• Data extraction and labeling - Leveraging its improved analysis skills, Claude 3.5 Haiku efficiently processes and categorizes data, making it useful for rapid data extraction and automated labeling tasks.
• Real-time content moderation - With strong reasoning skills and content understanding, Claude 3.5 Haiku provides fast, reliable content moderation for platforms that require immediate response times at scale.

Go to the Claude 3.5 Haiku model card

Claude 3 Opus

Anthropic's Claude 3 Opus is a powerful AI model with top-level performance on highly complex tasks. It can navigate open-ended prompts and sight-unseen scenarios with remarkable fluency and human-like understanding. Claude 3 Opus is optimized for the following use cases:

• Task automation, such as interactive coding and planning, or running complex actions across APIs and databases.

• Research and development tasks, such as research review, brainstorming and hypothesis generation, and product testing.

• Strategy tasks, such as advanced analysis of charts and graphs, financials and market trends, and forecasting.

• Vision tasks, such as processing images to return text output. Also, analysis of charts, graphs, technical diagrams, reports, and other visual content.

Go to the Claude 3 Opus model card

Claude 3 Haiku

Anthropic's Claude 3 Haiku is Anthropic's fastest vision and text model for near-instant responses to basic queries, meant for seamless AI experiences mimicking human interactions.

• Live customer interactions and translations.

• Content moderation to catch suspicious behavior or customer requests.

• Cost-saving tasks, such as inventory management and knowledge extraction from unstructured data.

• Vision tasks, such as processing images to return text output, analysis of charts, graphs, technical diagrams, reports, and other visual content.

Go to the Claude 3 Haiku model card

Claude 3.5 Sonnet

Anthropic's Claude 3.5 Sonnet outperforms Claude 3 Opus on a wide range of Anthropic's evaluations, with the speed and cost of Anthropic's mid-tier Claude 3 Sonnet. Claude 3.5 Sonnet is optimized for the following use cases:

• Coding, such as writing, editing, and running code with sophisticated reasoning and troubleshooting capabilities.

• Handle complex queries from customer support by understanding user context and orchestrating multi-step workflows.

• Data science and analysis by navigating unstructured data and leveraging multiple tools to generate insights.

• Visual processing, such as interpreting charts and graphs that require visual understanding.

• Writing content with a more natural, human-like tone.

Go to the Claude 3.5 Sonnet model card

Claude 3 Sonnet

Anthropic's Claude 3 Sonnet is Anthropic's dependable combination of skills and speed. It is engineered to be dependable for scaled AI deployments across a variety of use cases. Claude 3 Sonnet is optimized for the following use cases:

• Data processing, including retrieval-augmented generation (RAG) and search retrieval.

• Sales tasks, such as product recommendations, forecasting, and targeted marketing.

• Time-saving tasks, such as code generation, quality control, and optical character recognition (OCR) in images.

• Vision tasks, such as processing images to return text output. Also, analysis of charts, graphs, technical diagrams, reports, and other visual content.

Go to the Claude 3 Sonnet model card

Use Claude models

You can use Anthropic's SDK or curl commands to send requests to the Vertex AI endpoint using the following model names:

• For Claude 3.5 Sonnet v2, use claude-3-5-sonnet-v2@20241022.
• For Claude 3.5 Haiku, use claude-3-5-haiku@20241022.
• For Claude 3 Opus, use claude-3-opus@20240229.
• For Claude 3.5 Sonnet, use claude-3-5-sonnet@20240620.
• For Claude 3 Haiku, use claude-3-haiku@20240307.
• For Claude 3 Sonnet, use claude-3-sonnet@20240229.

Anthropic Claude model versions must be used with a suffix that starts with an @ symbol (such as claude-3-5-sonnet-v2@20241022 or claude-3-5-haiku@20241022) to guarantee consistent behavior.

Before you begin

To use the Anthropic Claude models with Vertex AI, you must perform the following steps. The Vertex AI API (aiplatform.googleapis.com) must be enabled to use Vertex AI. If you already have an existing project with the Vertex AI API enabled, you can use that project instead of creating a new project.

Make sure you have the required permissions to enable and use partner models. For more information, see Grant the required permissions.

1. Sign in to your Google Cloud account. If you're new to Google Cloud, create an account to evaluate how our products perform in real-world scenarios. New customers also get $300 in free credits to run, test, and deploy workloads.

2. In the Google Cloud console, on the project selector page, select or create a Google Cloud project.

   Go to project selector

3. Make sure that billing is enabled for your Google Cloud project.

4. Enable the Vertex AI API.

   Enable the API

5. In the Google Cloud console, on the project selector page, select or create a Google Cloud project.

   Go to project selector

6. Make sure that billing is enabled for your Google Cloud project.

7. Enable the Vertex AI API.

   Enable the API

8. Go to one of the following Model Garden model cards, then click Enable:
   • Go to the Claude 3.5 Sonnet v2 model card
   • Go to the Claude 3.5 Haiku model card
   • Go to the Claude 3 Opus model card
   • Go to the Claude 3.5 Sonnet model card
   • Go to the Claude 3 Haiku model card
   • Go to the Claude 3 Sonnet model card

Use the Anthropic SDK

You can make API requests to the Anthropic Claude models using the Anthropic Claude SDK. To learn more, see the following:

• Claude messages API reference
• Anthropic Python API library
• Anthropic Vertex AI TypeScript API Library

Make a streaming call to a Claude model using the Anthropic Vertex SDK

The following code sample uses the Anthropic Vertex SDK to perform a streaming call to a Claude model.

# TODO(developer): Vertex AI SDK - uncomment below & run
# pip3 install --upgrade --user google-cloud-aiplatform
# gcloud auth application-default login
# pip3 install -U 'anthropic[vertex]'

# TODO(developer): Update and un-comment below line
# PROJECT_ID = "your-project-id"

from anthropic import AnthropicVertex

client = AnthropicVertex(project_id=PROJECT_ID, region="us-east5")
result = []

with client.messages.stream(
    model="claude-3-5-sonnet-v2@20241022",
    max_tokens=1024,
    messages=[
        {
            "role": "user",
            "content": "Send me a recipe for banana bread.",
        }
    ],
) as stream:
    for text in stream.text_stream:
        print(text, end="", flush=True)
        result.append(text)

# Example response:
# Here's a simple recipe for delicious banana bread:
# Ingredients:
# - 2-3 ripe bananas, mashed
# - 1/3 cup melted butter
# ...
# ...
# 8. Bake for 50-60 minutes, or until a toothpick inserted into the center comes out clean.
# 9. Let cool in the pan for a few minutes, then remove and cool completely on a wire rack.

Make a unary call to a Claude model using the Anthropic Vertex SDK

The following code sample uses the Anthropic Vertex SDK to perform a unary call to a Claude model.

# TODO(developer): Vertex AI SDK - uncomment below & run
# pip3 install --upgrade --user google-cloud-aiplatform
# gcloud auth application-default login
# pip3 install -U 'anthropic[vertex]'

# TODO(developer): Update and un-comment below line
# PROJECT_ID = "your-project-id"

from anthropic import AnthropicVertex

client = AnthropicVertex(project_id=PROJECT_ID, region="us-east5")
message = client.messages.create(
    model="claude-3-5-sonnet-v2@20241022",
    max_tokens=1024,
    messages=[
        {
            "role": "user",
            "content": "Send me a recipe for banana bread.",
        }
    ],
)
print(message.model_dump_json(indent=2))
# Example response:
# {
#   "id": "msg_vrtx_0162rhgehxa9rvJM5BSVLZ9j",
#   "content": [
#     {
#       "text": "Here's a simple recipe for delicious banana bread:\n\nIngredients:\n- 2-3 ripe bananas...
#   ...

Use a curl command

You can use a curl command to make a request to the Vertex AI endpoint. The curl command specifies which supported Claude model you want to use.

Anthropic Claude model versions must be used with a suffix that starts with an @ symbol (such as claude-3-5-sonnet-v2@20241022 or claude-3-5-haiku@20241022) to guarantee consistent behavior.

The following topic shows you how to create a curl command and includes a sample curl command.

POST https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/publishers/anthropic/models/MODEL:streamRawPredict

{
  "anthropic_version": "vertex-2023-10-16",
  "messages": [
   {
    "role": "ROLE",
    "content": "CONTENT"
   }],
  "max_tokens": MAX_TOKENS,
  "stream": STREAM
}

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/anthropic/models/MODEL:streamRawPredict"

$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/anthropic/models/MODEL:streamRawPredict" | Select-Object -Expand Content

{
  "id":"msg_012NDLxqh6LsztWCU7zTb14C",
  "type":"message",
  "role":"assistant",
  "content":[{
    "type":"text",
    "text":"Hello! Nice to meet you."
  }],
  "model":"claude-2.1",
  "stop_reason":"end_turn",
  "stop_sequence":null,
  "usage":{
    "input_tokens":11,
    "output_tokens":11
  }
}

MODEL_ID="MODEL"
LOCATION="us-central1"
PROJECT_ID="PROJECT_ID"

curl \
-X POST \
-H "Authorization: Bearer $(gcloud auth print-access-token)" \
-H "Content-Type: application/json" \
https://${LOCATION}-aiplatform.googleapis.com/v1/projects/${PROJECT_ID}/locations/${LOCATION}/publishers/anthropic/models/${MODEL_ID}:streamRawPredict -d \
'{
  "anthropic_version": "vertex-2023-10-16",
  "messages": [{
    "role": "user",
    "content": "Hello!"
  }],
  "max_tokens": 50,
  "stream": true}'

Tool use (function calling)

The Anthropic Claude models support tools and function calling to enhance a model's capabilities. For more information, see the Tool use overview in the Anthropic documentation.

The following samples demonstrate how to use tools by using an SDK or curl command. The samples search for nearby restaurants in San Francisco that are open.

# TODO(developer): Vertex AI SDK - uncomment below & run
# pip3 install --upgrade --user google-cloud-aiplatform
# gcloud auth application-default login
# pip3 install -U 'anthropic[vertex]'
from anthropic import AnthropicVertex

# TODO(developer): Update and un-comment below line
# PROJECT_ID = "your-project-id"

client = AnthropicVertex(project_id=PROJECT_ID, region="us-east5")
message = client.messages.create(
    model="claude-3-5-sonnet-v2@20241022",
    max_tokens=1024,
    tools=[
        {
            "name": "text_search_places_api",
            "description": "returns information about a set of places based on a string",
            "input_schema": {
                "type": "object",
                "properties": {
                    "textQuery": {
                        "type": "string",
                        "description": "The text string on which to search",
                    },
                    "priceLevels": {
                        "type": "array",
                        "description": "Price levels to query places, value can be one of [PRICE_LEVEL_INEXPENSIVE, PRICE_LEVEL_MODERATE, PRICE_LEVEL_EXPENSIVE, PRICE_LEVEL_VERY_EXPENSIVE]",
                    },
                    "openNow": {
                        "type": "boolean",
                        "description": "whether those places are open for business.",
                    },
                },
                "required": ["textQuery"],
            },
        }
    ],
    messages=[
        {
            "role": "user",
            "content": "What are some affordable and good Italian restaurants open now in San Francisco??",
        }
    ],
)
print(message.model_dump_json(indent=2))
# Example response:
# {
#   "id": "msg_vrtx_018pk1ykbbxAYhyWUdP1bJoQ",
#   "content": [
#     {
#       "text": "To answer your question about affordable and good Italian restaurants
#       that are currently open in San Francisco....
# ...

POST https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/publishers/anthropic/models/MODEL:rawPredict

{
  "anthropic_version": "vertex-2023-10-16",
  "max_tokens": MAX_TOKENS,
  "stream": STREAM,
  "tools": [
    {
      "name": "text_search_places_api",
      "description": "Returns information about a set of places based on a string",
      "input_schema": {
        "type": "object",
        "properties": {
          "textQuery": {
            "type": "string",
            "description": "The text string on which to search"
          },
          "priceLevels": {
            "type": "array",
            "description": "Price levels to query places, value can be one of [PRICE_LEVEL_INEXPENSIVE, PRICE_LEVEL_MODERATE, PRICE_LEVEL_EXPENSIVE, PRICE_LEVEL_VERY_EXPENSIVE]",
          },
          "openNow": {
            "type": "boolean",
            "description": "Describes whether a place is open for business at
            the time of the query."
          },
        },
        "required": ["textQuery"]
      }
    }
  ],
  "messages": [
    {
      "role": "user",
      "content": "What are some affordable and good Italian restaurants that are open now in San Francisco??"
    }
  ]
}

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/anthropic/models/MODEL:rawPredict"

$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/anthropic/models/MODEL:rawPredict" | Select-Object -Expand Content

{
  "id": "msg_vrtx_01ErR7VMNQdnvDt3n7Nmc4ER",
  "type": "message",
  "role": "assistant",
  "model": "claude-3-opus-20240229",
  "content": [
    {
      "type": "text",
      "text": "\nTo find affordable and good Italian restaurants that are currently open in San Francisco, the text_search_places_api tool seems most relevant. \n\nThe required textQuery parameter can be inferred as \"Italian restaurants in San Francisco\", since the user specified Italian restaurants and the location of San Francisco.\n\nTwo optional parameters are also relevant:\nopenNow - this should be set to true, since the user specified they want restaurants open now\npriceLevels - to find affordable restaurants, this can be set to [PRICE_LEVEL_INEXPENSIVE, PRICE_LEVEL_MODERATE]\n\nWith the textQuery provided and the two optional parameters that can help narrow the results to match the user's criteria, we have enough information to make a good call to the text_search_places_api tool to try to answer the user's request.\n"
    },
    {
      "type": "tool_use",
      "id": "toolu_vrtx_01TAJCTkxe8HhRoaQ69N4ouP",
      "name": "text_search_places_api",
      "input": {
        "textQuery": "Italian restaurants in San Francisco",
        "openNow": true,
        "priceLevels": [
          "PRICE_LEVEL_INEXPENSIVE",
          "PRICE_LEVEL_MODERATE"
        ]
      }
    }
  ],
  "stop_reason": "tool_use",
  "stop_sequence": null,
  "usage": {
    "input_tokens": 727,
    "output_tokens": 308
  }
}

Use Vertex AI Studio

For some of the Anthropic Claude models, you can use Vertex AI Studio to quickly prototype and test generative AI models in the Google Cloud console. As an example, you can use Vertex AI Studio to compare Claude model responses with other supported models such as Google Gemini.

For more information, see Quickstart: Send text prompts to Gemini using Vertex AI Studio.

Anthropic Claude region availability

• us-east5 (Ohio)
• europe-west1 (Belgium)

• us-east5 (Ohio)

• us-east5 (Ohio)

• us-east5 (Ohio)
• asia-southeast1 (Singapore)
• europe-west1 (Belgium)

• us-east5 (Ohio)
• asia-southeast1 (Singapore)
• europe-west1 (Belgium)

• us-east5 (Ohio)

Anthropic Claude quotas and supported context length

For Claude models, a quota applies for each region where the model is available. The quota is specified in queries per minute (QPM) and tokens per minute (TPM). TPM includes both input and output tokens.

To maintain overall service performance and acceptable use, the maximum quotas might vary by account and, in some cases, access might be restricted. View your project's quotas on the Quotas & Systems Limits page in the Google Cloud console. You must also have the following quotas available:

• Online prediction requests per base model per minute per region per base_model
• Online prediction tokens per minute per base model per minute per region per base_model

Claude 3.5 Sonnet v2

The following table shows the maximum quotas and supported context length for Claude 3.5 Sonnet v2.

Claude 3.5 Haiku

The following table shows the maximum quotas and supported context length for Claude 3.5 Haiku.

Claude 3 Opus

The following table shows the maximum quotas and supported context length for Claude 3 Opus.

Claude 3 Haiku

The following table shows the maximum quotas and supported context length for Claude 3 Haiku.

Claude 3.5 Sonnet

The following table shows the maximum quotas and supported context length for Claude 3.5 Sonnet.

Claude 3 Sonnet

The following table shows the maximum quotas and supported context length for Claude 3 Sonnet.

If you want to increase any of your quotas for Generative AI on Vertex AI, you can use the Google Cloud console to request a quota increase. To learn more about quotas, see Work with quotas.