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 3.1 8B

Compact

Small, fast Llama 3.1. The default cheap open-weights model in 2024–25 across Groq, Cerebras and Together.

Llama 3.1 8B is a efficient AI model from Meta. It costs $0.100 per million input tokens and $0.100 per million output tokens (blended $0.100/M), with a 128K-token context window.

Released Jul 2024Modalities textOfficial model page ↗API docs ↗Compare with another model →Estimate monthly cost →
INPUT
$0.100/M
per million input tokens
OUTPUT
$0.100/M
per million output tokens
BLENDED 70/30
$0.100/M
default reference rate · how it's calculated →
CONTEXT
128K
128,000 tokens
What it's good at
  • Cheap
  • Fast on LPU/Cerebras
  • Open weights
  • 128K context
Typical use cases
  • Bulk classification
  • Cheap chat
  • Edge inference
Benchmarks
vs. best public score
MMLU73%
Multitask academic knowledge across 57 subjects.
GPQA Diamond31%
Graduate-level science questions, "Google-proof".
MATH51%
High-school competition math problems.
HumanEval73%
Python function synthesis from docstrings.
LMArena Elo1180 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 3.2 90B Vision
Vision · 128K ctx
in $0.880/Mout $0.880/M
Frequently asked questions

How much does Llama 3.1 8B cost?

Llama 3.1 8B costs $0.100 per million input tokens and $0.100 per million output tokens, for a blended reference rate of $0.100 per million tokens.

What is Llama 3.1 8B's context window?

Llama 3.1 8B supports up to 128K tokens of context (128,000 tokens).

What is Llama 3.1 8B best for?

Llama 3.1 8B is well suited to Cheap, Fast on LPU/Cerebras and Open weights.

Who makes Llama 3.1 8B?

Llama 3.1 8B is developed and served by Meta. It was released in Jul 2024.