Databricks
Frontier

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 $0.7500 per million input tokens and $2.25 per million output tokens (blended $1.20/M), with a 32,000-token context window.

RatesUSD per million tokens. Blend is 70% input, 30% output, our calculation.

INPUT
$0.7500/M
per million input tokens
OUTPUT
$2.25/M
per million output tokens
BLENDED 70/30
$1.20/M
unchanged since 3 May
CONTEXT
32,000
tokens

Hand-maintained from Databricks's published pricing; no check date on record.

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

No published benchmark scores tracked for this model yet. Frontier and reasoning models from major providers have scores; smaller models and inference-host variants typically inherit the underlying open-weights score.

More from Databricks

See all 3 →

Frequently asked questions

How much does DBRX Base cost?

DBRX Base costs $0.7500 per million input tokens and $2.25 per million output tokens, for a blended reference rate of $1.20 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.

Terms used on this page