Cerebras
Efficient

Llama-3.1-8B (Cerebras)

Ultra-Fast Nano

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

Llama-3.1-8B (Cerebras) is a efficient AI model from Cerebras. It costs $0.1000 per million input tokens and $0.1000 per million output tokens (blended $0.1000/M), with a 128,000-token context window.

Profile inherited from upstream Llama 3.1 8B ↗ — this is a hosted variant of the same open-weights model.

RatesUSD per million tokens. Blend is 70% input, 30% output, our calculation.

INPUT
$0.1000/M
per million input tokens
OUTPUT
$0.1000/M
per million output tokens
BLENDED 70/30
$0.1000/M
unchanged since 3 May
CONTEXT
128,000
tokens

Hand-maintained from Cerebras's published pricing; no check date on record.

What it is 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
Scores inherited from Llama 3.1 8B — this is a hosted variant of the same open-weights model, so the underlying benchmark scores are identical.
MMLU73%
Multitask academic knowledge across 57 subjects. Source: Meta (self-reported), MMLU (CoT), 0-shot, read 2026-11-10.
Graduate-level science questions, "Google-proof". Source: Meta (self-reported), GPQA Diamond (CoT), 0-shot, read 2026-11-10.
MATH51.9%
High-school competition math problems. Source: Meta (self-reported), MATH (CoT), 0-shot, read 2026-11-10.
HumanEval72.6%
Python function synthesis from docstrings. Source: Meta (self-reported), HumanEval, 0-shot pass@1, read 2026-11-10.
LMArena Elo1211 Elo
Crowd-sourced head-to-head preference Elo rating. Source: LMArena (independent), LMArena Text Arena score, read 2026-11-10.
Hand-curated from each provider's published reports and public leaderboards. Methodology varies across sources, treat as directional rather than authoritative.

More from Cerebras

See all 4 →

Frequently asked questions

How much does Llama-3.1-8B (Cerebras) cost?

Llama-3.1-8B (Cerebras) costs $0.1000 per million input tokens and $0.1000 per million output tokens, for a blended reference rate of $0.1000 per million tokens.

What is Llama-3.1-8B (Cerebras)'s context window?

Llama-3.1-8B (Cerebras) supports up to 128,000 tokens of context in a single request.

What is Llama-3.1-8B (Cerebras) best for?

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

Who makes Llama-3.1-8B (Cerebras)?

Llama-3.1-8B (Cerebras) is developed and served by Cerebras. It was released in Jul 2024.

Terms used on this page