Databricks
Databricks
Efficient

Llama 3.1 70B (DB)

Managed

Llama 3.1 70B hosted on Databricks Mosaic AI. Behaves identically to upstream Llama; the value-add is integration with Databricks data + governance.

Llama 3.1 70B (DB) is a efficient AI model from Databricks. It costs $1.000 per million input tokens and $3.000 per million output tokens (blended $1.600/M), with a 128,000-token context window.

INPUT
$1.000/M
per million input tokens
OUTPUT
$3.000/M
per million output tokens
BLENDED 70/30
$1.600/M
unchanged since 3 May
CONTEXT
128,000
tokens
What it is good at
  • Llama 3.1 70B quality
  • Databricks data + governance
  • Unity Catalog integration
Typical use cases
  • Databricks-native RAG
  • Governed enterprise chat

Benchmarks

vs. best public score
Scores inherited from Llama 3.1 70B — this is a hosted variant of the same open-weights model, so the underlying benchmark scores are identical.
MMLU83%
Multitask academic knowledge across 57 subjects.
Graduate-level science questions, "Google-proof".
MATH68%
High-school competition math problems.
Python function synthesis from docstrings.
LMArena Elo1248 Elo
Crowd-sourced head-to-head preference Elo rating.
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 Llama 3.1 70B (DB) cost?

Llama 3.1 70B (DB) costs $1.000 per million input tokens and $3.000 per million output tokens, for a blended reference rate of $1.600 per million tokens.

What is Llama 3.1 70B (DB)'s context window?

Llama 3.1 70B (DB) supports up to 128,000 tokens of context in a single request.

What is Llama 3.1 70B (DB) best for?

Llama 3.1 70B (DB) is well suited to Llama 3.1 70B quality, Databricks data + governance and Unity Catalog integration.

Who makes Llama 3.1 70B (DB)?

Llama 3.1 70B (DB) is developed and served by Databricks.

Terms used on this page