DeepSeek models

DeepSeek models on Vertex AI offer fully managed and serverless models as APIs. To use a DeepSeek model on Vertex AI, send a request directly to the Vertex AI API endpoint. Because DeepSeek models use a managed API, there's no need to provision or manage infrastructure.

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

Available DeepSeek models

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

DeepSeek-R1-0528

DeepSeek-R1-0528 is the latest version of the DeepSeek R1 model. Compared to DeepSeek-R1, it has significantly improved depth of reasoning and inference capabilities. DeepSeek-R1-0528 excels in wide range tasks, such as creative writing, general question answering, editing, and summarization.

Considerations

• For production-ready safety, integrate DeepSeek-R1-0528 with Model Armor, which screens LLM prompts and responses for various security and safety risks.

Go to the DeepSeek-R1-0528 model card

Use DeepSeek models

You can use curl commands to send requests to the Vertex AI endpoint using the following model names:

• For DeepSeek-R1-0528, use deepseek-r1-0528-maas

Before you begin

To use DeepSeek 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.

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.

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

Go to project selector

Verify that billing is enabled for your Google Cloud project.

Enable the Vertex AI API.

Enable the API

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

Go to project selector

Verify that billing is enabled for your Google Cloud project.

Enable the Vertex AI API.

Enable the API

1. Go to one of the following Model Garden model cards, then click Enable:
   • Go to the DeepSeek-R1-0528 model card

Make a streaming call to a DeepSeek model

The following sample makes a streaming call to a DeepSeek model:

POST https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/endpoints/openapi/chat/completions

{
  "model": "deepseek-ai/MODEL",
  "messages": [
    {
      "role": "ROLE",
      "content": "CONTENT"
    }
  ],
  "max_tokens": MAX_OUTPUT_TOKENS,
  "stream": true
}

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/endpoints/openapi/chat/completions"

$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/endpoints/openapi/chat/completions" | Select-Object -Expand Content

data: {
  "choices": [
    {
      "delta": {
        "content": "CONTENT",
        "role": "assistant"
      },
      "index": 0,
      "logprobs": null
    }
  ],
  "created": 1234567890,
  "id": "2025-06-11|10:00:00.292195-07|9.7.144.202|-123456789",
  "model": "deepseek-ai/MODEL",
  "object": "chat.completion.chunk"
  "system_fingerprint": "",
}

data: {
  "choices": [
    {
      "delta": {
        "content": "CONTENT",
        "role": "assistant"
      },
      "finish_reason": "stop",
      "index": 0,
      "logprobs": null
    }
  ],
  "created": 1234567890,
  "id": "2025-06-11|10:00:00.292195-07|9.7.144.202|-123456789",
  "model": "deepseek-ai/MODEL",
  "object": "chat.completion.chunk"
  "system_fingerprint": "",
  "usage": {
    "completion_tokens": 131,
    "prompt_tokens": 14,
    "total_tokens": 145
  }
}

data: [DONE]

Make a non-streaming call to a DeepSeek model

The following sample makes a non-streaming call to a DeepSeek model:

POST https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/endpoints/openapi/chat/completions

{
  "model": "deepseek-ai/MODEL",
  "messages": [
    {
      "role": "ROLE",
      "content": "CONTENT"
    }
  ],
  "max_tokens": MAX_OUTPUT_TOKENS,
  "stream": false
}

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/endpoints/openapi/chat/completions"

$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/endpoints/openapi/chat/completions" | Select-Object -Expand Content

{
  "choices": [
    {
      "finish_reason": "stop",
      "index": 0,
      "logprobs": null,
      "message": {
        "content": "CONTENT",
        "role": "assistant"
      }
    }
  ],
  "created": 1234567890,
  "id": "2025-06-11|10:00:00.292195-07|9.7.144.202|-123456789",
  "model": "deepseek-ai/MODEL",
  "object": "chat.completion",
  "system_fingerprint": "",
  "usage": {
    "completion_tokens": 367,
    "prompt_tokens": 14,
    "total_tokens": 381
  }
}

DeepSeek model region availability and quotas

For DeepSeek models, a quota applies for each region where the model is available. The quota is specified in queries per minute (QPM).

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.