Using DeepSeek R1 on Databricks Foundation Model Serving

Implementation guide · DeepSeek R1 · DeepSeek

ServerlessOpen Source

Databricks Foundation Model Serving exposes DeepSeek R1 through model ID deepseek-r1. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.

Last refreshed 2026-04-19. Next refresh: weekly.

Quick Start

  1. 1
    Create an account at Databricks Foundation Model Serving and generate an API key.
  2. 2
    Use the Databricks Foundation Model Serving SDK or REST API to call deepseek-r1 — see the documentation for request format.
API PortalDocumentationPricing

Code Examples

See Databricks Foundation Model Serving documentation for integration details.

Pricing on Databricks Foundation Model Serving

Capabilities

ReasoningStructured OutputsCode Execution

About DeepSeek R1

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

Full model details →

Model Specs

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

Also available on(13)

Bitdeer AI$0.10/1MSiliconFlow$0.25/1MDeepSeek Platform$0.55/1M
Compare all providers →

Provider

Databricks Foundation Model Serving

Databricks

San Francisco, California, United States