sao10k

EfficientLIVE INDEX

Llama 3 8B Lunaris

Name: Llama 3 8B Lunaris
Brand: sao10k
Price: 0.040000 USD

text->text

Original 8B Llama 3. Used widely as a fine-tune base before 3.1/3.2 arrived.

Llama 3 8B Lunaris is a efficient AI model from sao10k. It costs $0.040 per million input tokens and $0.050 per million output tokens (blended $0.043/M), with a 8,192-token context window.

Profile inherited from upstream Llama 3 8B ↗ — this is a hosted variant of the same open-weights model.

Released Apr 2024Modalities textOfficial model page ↗Pricing source ↗Compare with another model →Estimate monthly cost →

INPUT

$0.040/M

per million input tokens

OUTPUT

$0.050/M

per million output tokens

BLENDED 70/30

$0.043/M

unchanged since 3 May

default reference rate · how it is calculated →

CONTEXT

8,192

tokens

What it is good at

Open weights
Single-GPU friendly
Fine-tune ecosystem

Typical use cases

Fine-tune base
Legacy Llama 3 deployments

Benchmarks

vs. best public score

Scores inherited from Llama 3 8B — this is a hosted variant of the same open-weights model, so the underlying benchmark scores are identical.

MMLU68%

Multitask academic knowledge across 57 subjects.

GPQA Diamond28%

Graduate-level science questions, "Google-proof".

MATH30%

High-school competition math problems.

HumanEval62%

Python function synthesis from docstrings.

LMArena Elo1152 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 sao10k

See all 2 →

Llama 3.3 Euryale 70B

text->text · 131,072 ctx

in $0.650/Mout $0.750/M

Llama 3.1 Euryale 70B v2.2

text->text · 131,072 ctx

in $0.850/Mout $0.850/M

Frequently asked questions

How much does Llama 3 8B Lunaris cost?

Llama 3 8B Lunaris costs $0.040 per million input tokens and $0.050 per million output tokens, for a blended reference rate of $0.043 per million tokens.

What is Llama 3 8B Lunaris's context window?

Llama 3 8B Lunaris supports up to 8,192 tokens of context in a single request.

What is Llama 3 8B Lunaris best for?

Llama 3 8B Lunaris is well suited to Open weights, Single-GPU friendly and Fine-tune ecosystem.

Who makes Llama 3 8B Lunaris?

Llama 3 8B Lunaris is developed and served by sao10k. It was released in Apr 2024.

Terms used on this page

Full glossary →

Token Input tokens Output tokens Price per million tokens Context window Prompt caching Batch API Blended cost