LLM Reference
GCP Vertex AI

DeepSeek R1 on GCP Vertex AI

DeepSeek R1 · DeepSeek

ServerlessOpen Source

Last refreshed 2026-06-15. Next refresh: weekly.

Why use DeepSeek R1 on GCP Vertex AI?

GCP Vertex AI offers DeepSeek R1 with pay-as-you-go pricing at $1.35/1M input tokens. Vertex AI is Google Cloud's managed AI platform, offering access to Gemini models and hundreds of partner models alongside tools for fine-tuning, grounding, vector search, and end-to-end MLOps pipelines.

Compare DeepSeek R1 across 14 providers to find the best fit for your use case
Input / 1M
$1.35
Output / 1M
$5.40
Cache
Not sourced
Batch
Not sourced

Setup recipe

Python + curl
Install
pip install google-cloud-aiplatform
Auth
export GOOGLE_CLOUD_PROJECT=...
Call
import os
import vertexai
from vertexai.generative_models import GenerativeModel
vertexai.init(project=os.environ["GOOGLE_CLOUD_PROJECT"], location="us-central1")
Model ID
deepseek-r1

Request example

import os
import vertexai
from vertexai.generative_models import GenerativeModel

# Reads GOOGLE_CLOUD_PROJECT from env; authenticates via Application Default Credentials
vertexai.init(project=os.environ["GOOGLE_CLOUD_PROJECT"], location="us-central1")
model = GenerativeModel("deepseek-r1")
response = model.generate_content("Hello")
print(response.text)

Gotchas

  • For Google-published models use the model name directly, e.g. "gemini-2.0-flash-001". For third-party publishers (Anthropic, Meta, etc.) use the full publisher path, e.g. "publishers/anthropic/models/claude-3-5-sonnet-v2@20241022".
  • The examples expect GOOGLE_CLOUD_PROJECT; rename it only if your application config maps the new variable.

Compare DeepSeek R1 Across Providers

ProviderInput (per 1M)Output (per 1M)
DeepSeek Platform$0.55$2.19
OpenRouter$0.70$2.50
Together AI$3.00$7.00
Fireworks AI$0.56$1.68
NVIDIA NIM
View all 14 providers →

Pricing

TypePrice (per 1M)
Input tokens$1.35
Output tokens$5.40

Capabilities

ReasoningStructured OutputsCode Execution

About DeepSeek R1

DeepSeek R1: Reasoning-optimized model with extended thinking capabilities. 128K context.

Get Started

Model Specs

Released2025-01-20
Parameters671B, 37B Active
Context128k
ArchitectureDecoder Only
Knowledge cutoff2023-12

Related Models on GCP Vertex AI