Meta
Efficient

Llama 3 70B

Previous Gen

Original Llama 3 70B from April 2024. Largely superseded by Llama 3.1/3.3, but still common in fine-tuned variants.

Llama 3 70B is a efficient AI model from Meta. It costs $0.5900 per million input tokens and $0.7900 per million output tokens (blended $0.6500/M), with a 8,000-token context window.

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

INPUT
$0.5900/M
per million input tokens
OUTPUT
$0.7900/M
per million output tokens
BLENDED 70/30
$0.6500/M
unchanged since 3 May
CONTEXT
8,000
tokens

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

What it is good at
  • Open weights
  • 8K base context (extended via fine-tunes)
  • Fine-tune base
Typical use cases
  • Existing Llama 3 fine-tunes
  • Migration to 3.1/3.3

Benchmarks

vs. best public score
MMLU80%
Multitask academic knowledge across 57 subjects. No source recorded yet.
MATH50%
High-school competition math problems. No source recorded yet.
Python function synthesis from docstrings. No source recorded yet.
LMArena Elo1276 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.

Also reported by the provider

Results on benchmarks outside the set we compare across models. They are listed for completeness and are deliberately excluded from the bars above and from every ranking on this site, because a score is only comparable against the same benchmark variant. Why benchmark scores do not compare →

  • GPQA Main (0-shot)39.5%self-reported by Meta · no date on the source · Maker evaluation details identify this as the GPQA main set, not Diamond, 0-shot. Not comparable with the GPQA Diamond column, so shown here and never ranked.

More from Meta

See all 20 →

Frequently asked questions

How much does Llama 3 70B cost?

Llama 3 70B costs $0.5900 per million input tokens and $0.7900 per million output tokens, for a blended reference rate of $0.6500 per million tokens.

What is Llama 3 70B's context window?

Llama 3 70B supports up to 8,000 tokens of context in a single request.

What is Llama 3 70B best for?

Llama 3 70B is well suited to Open weights, 8K base context (extended via fine-tunes) and Fine-tune base.

Who makes Llama 3 70B?

Llama 3 70B is developed and served by Meta. It was released in Apr 2024.

Terms used on this page