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 Meta models
Meta
MetaEfficient

Llama 3 8B

Previous Gen

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

Llama 3 8B is a efficient AI model from Meta. It costs $0.200 per million input tokens and $0.200 per million output tokens (blended $0.200/M), with a 8K-token context window.

Released Apr 2024Modalities textOfficial model page ↗API docs ↗Compare with another model →Estimate monthly cost →
INPUT
$0.200/M
per million input tokens
OUTPUT
$0.200/M
per million output tokens
BLENDED 70/30
$0.200/M
default reference rate · how it's calculated →
CONTEXT
8K
8,000 tokens
What it's 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
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 Meta
See all 19 →
Llama 4 Maverick
Frontier · 128K ctx
in $0.200/Mout $0.600/M
Llama 4 Scout
Efficient · 512K ctx
in $0.100/Mout $0.350/M
Llama 3.3 70B
Open · 128K ctx
in $0.230/Mout $0.400/M
Llama 3.1 405B
Large · 128K ctx
in $0.800/Mout $0.800/M
Llama 3.1 70B
Balanced · 128K ctx
in $0.350/Mout $0.400/M
Llama 3.1 8B
Compact · 128K ctx
in $0.100/Mout $0.100/M
Frequently asked questions

How much does Llama 3 8B cost?

Llama 3 8B costs $0.200 per million input tokens and $0.200 per million output tokens, for a blended reference rate of $0.200 per million tokens.

What is Llama 3 8B's context window?

Llama 3 8B supports up to 8K tokens of context (8,000 tokens).

What is Llama 3 8B best for?

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

Who makes Llama 3 8B?

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