DBRX Base
Base
Base (non-instruction-tuned) DBRX. Designed for downstream fine-tuning on top of the MoE backbone.
DBRX Base is a frontier AI model from Databricks. It costs $0.750 per million input tokens and $2.250 per million output tokens (blended $1.200/M), with a 32,000-token context window.
INPUT
$0.750/M
per million input tokens
OUTPUT
$2.250/M
per million output tokens
CONTEXT
32,000
tokens
What it is good at
- Open-weights MoE base
- Fine-tune target
- Databricks-native deployment
Typical use cases
- Fine-tune base on Databricks
- MoE research
Benchmarks
vs. best public score
Hand-curated from each provider's published reports and public leaderboards. Methodology varies across sources, treat as directional rather than authoritative.
More from Databricks
See all 3 →Frequently asked questions
How much does DBRX Base cost?
DBRX Base costs $0.750 per million input tokens and $2.250 per million output tokens, for a blended reference rate of $1.200 per million tokens.
What is DBRX Base's context window?
DBRX Base supports up to 32,000 tokens of context in a single request.
What is DBRX Base best for?
DBRX Base is well suited to Open-weights MoE base, Fine-tune target and Databricks-native deployment.
Who makes DBRX Base?
DBRX Base is developed and served by Databricks. It was released in Mar 2024.