Skip to main content
DatabricksReleased March 27, 2024

DBRX

Open Source#20 Arena Rank132B (36B active) parameters

DBRX holds a solid spot in the Arena rankings at #20. Context window: 0.032K tokens.

Context

32K

Input

Free (open)

Key Specifications

🏆

Arena Rank

#20

📐

Context Window

32K

📥

Input Price

per 1M tokens

Free (open)

📤

Output Price

per 1M tokens

Free (open)

🧠

Parameters

132B (36B active)

🔓

Open Source

Yes

Best For

Enterprise AIdata analysiscoding

About DBRX

DBRX, developed by Databricks, is an open-source Mixture-of-Experts model with 132 billion total parameters (36 billion active per token) and a 32K token context window. The model uses a fine-grained MoE architecture with 16 experts, activating 4 per token for efficient inference on enterprise data workloads. DBRX excels at SQL generation, data analysis, code debugging, and analytical reasoning tasks. Designed to integrate with Databricks' lakehouse platform, it demonstrates particular strength in structured data understanding and data science workflows. Free and fully open-source, it can be deployed on enterprise GPU infrastructure for data-sensitive environments. DBRX ranks #20 on the Chatbot Arena leaderboard, reflecting competitive performance for its specialized design. The model represents Databricks' strategy of building AI models optimized for the data engineering and analytics use cases central to its enterprise customer base.

Pricing per 1M tokens

Input Tokens

Free (open)

Output Tokens

Free (open)

Frequently Asked Questions

What is DBRX?
DBRX, developed by Databricks, is an open-source Mixture-of-Experts model with 132 billion total parameters (36 billion active per token) and a 32K token context window. The model uses a fine-grained MoE architecture with 16 experts, activating 4 per token for efficient inference on enterprise data workloads. DBRX excels at SQL generation, data analysis, code debugging, and analytical reasoning tasks. Designed to integrate with Databricks' lakehouse platform, it demonstrates particular strength in structured data understanding and data science workflows. Free and fully open-source, it can be deployed on enterprise GPU infrastructure for data-sensitive environments. DBRX ranks #20 on the Chatbot Arena leaderboard, reflecting competitive performance for its specialized design. The model represents Databricks' strategy of building AI models optimized for the data engineering and analytics use cases central to its enterprise customer base.
How much does DBRX cost?
Input pricing for DBRX is Free (open) per million tokens; output runs Free (open). Token-based pricing means you can scale up or down without a fixed commitment.
What is DBRX's context window?
The context window for DBRX is 32K tokens. That's the maximum amount of text you can feed into a single prompt, including system instructions, conversation history, and the actual query.
Is DBRX open source?
DBRX is fully open source. You can grab the weights, run it on your own hardware, and fine-tune it for specific tasks. That flexibility is a big deal for teams with strict data requirements.
What is DBRX best for?
The sweet spot for DBRX is: Enterprise AI, data analysis, coding. If your workload fits one of these categories, it's worth benchmarking against alternatives.