Claude Fable 5$22.000/MClaude Opus 4.8$11.000/MClaude Opus 4.7$11.000/MClaude Opus 4.6$11.000/MClaude Opus 4.5$33.000/MClaude Sonnet 3.7$6.600/MClaude Opus 3$33.000/MClaude 2.1$12.800/MClaude 2$12.800/MGPT-5.5$12.500/MGPT-5.2$5.425/MGPT-5.2-Codex$5.425/MGPT-5$3.875/MGPT-4.5$97.500/MGPT-4 Turbo Preview$16.000/MGPT-4$39.000/MGPT-4-32k$78.000/Mo3$19.000/Mo3-mini$2.090/Mo4-mini$2.090/Mo1$28.500/Mo1-mini$5.700/Mo1-preview$28.500/MGemini 3.5 Pro$5.000/MGemini 3.1 Pro$5.000/MGemini 3 Pro$5.000/MGemini 2.5 Pro$3.875/MGemini 1.5 Pro$2.375/MGemini 1.0 Ultra$12.000/MGemini 1.0 Pro$0.800/MClaude Fable 5$22.000/MClaude Opus 4.8$11.000/MClaude Opus 4.7$11.000/MClaude Opus 4.6$11.000/MClaude Opus 4.5$33.000/MClaude Sonnet 3.7$6.600/MClaude Opus 3$33.000/MClaude 2.1$12.800/MClaude 2$12.800/MGPT-5.5$12.500/MGPT-5.2$5.425/MGPT-5.2-Codex$5.425/MGPT-5$3.875/MGPT-4.5$97.500/MGPT-4 Turbo Preview$16.000/MGPT-4$39.000/MGPT-4-32k$78.000/Mo3$19.000/Mo3-mini$2.090/Mo4-mini$2.090/Mo1$28.500/Mo1-mini$5.700/Mo1-preview$28.500/MGemini 3.5 Pro$5.000/MGemini 3.1 Pro$5.000/MGemini 3 Pro$5.000/MGemini 2.5 Pro$3.875/MGemini 1.5 Pro$2.375/MGemini 1.0 Ultra$12.000/MGemini 1.0 Pro$0.800/M
BETA
Subscribe
← Back to Index·All Databricks models
Databricks
DatabricksEfficient

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 128K-token context window.

Modalities textOfficial model page ↗Provider pricing ↗API docs ↗Compare with another model →Estimate monthly cost →
INPUT
$1.000/M
per million input tokens
OUTPUT
$3.000/M
per million output tokens
BLENDED 70/30
$1.600/M
default reference rate · how it's calculated →
CONTEXT
128K
128,000 tokens
What it's 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.
GPQA Diamond47%
Graduate-level science questions, "Google-proof".
MATH68%
High-school competition math problems.
HumanEval80%
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 →
DBRX Instruct
Open · 32K ctx
in $0.750/Mout $2.250/M
DBRX Base
Base · 32K ctx
in $0.750/Mout $2.250/M
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 128K tokens of context (128,000 tokens).

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.