Claude Fable 5$22.000/MClaude Opus 5$11.000/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-5.6 Sol$12.500/MGPT-5.6 Terra$5.000/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/MClaude Fable 5$22.000/MClaude Opus 5$11.000/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-5.6 Sol$12.500/MGPT-5.6 Terra$5.000/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/M
Meta
Meta
Efficient

Llama 2 70B Chat

Legacy

Llama 2 70B chat, the model that opened the open-weights frontier in 2023. Now mainly historical, but still hosted for legacy fine-tunes.

Llama 2 70B Chat is a efficient AI model from Meta. It costs $0.900 per million input tokens and $0.900 per million output tokens (blended $0.900/M), with a 4,000-token context window.

INPUT
$0.900/M
per million input tokens
OUTPUT
$0.900/M
per million output tokens
BLENDED 70/30
$0.900/M
unchanged since 3 May
CONTEXT
4,000
tokens
What it is good at
  • Historic open-weights flagship
  • 4K context
Typical use cases
  • Legacy Llama 2 deployments
  • Migrations to Llama 3+

Benchmarks

vs. best public score
MMLU69%
Multitask academic knowledge across 57 subjects.
Graduate-level science questions, "Google-proof".
MATH14%
High-school competition math problems.
Python function synthesis from docstrings.
LMArena Elo1093 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 20

Frequently asked questions

How much does Llama 2 70B Chat cost?

Llama 2 70B Chat costs $0.900 per million input tokens and $0.900 per million output tokens, for a blended reference rate of $0.900 per million tokens.

What is Llama 2 70B Chat's context window?

Llama 2 70B Chat supports up to 4,000 tokens of context in a single request.

What is Llama 2 70B Chat best for?

Llama 2 70B Chat is well suited to Historic open-weights flagship, 4K context and Legacy Llama 2 deployments.

Who makes Llama 2 70B Chat?

Llama 2 70B Chat is developed and served by Meta. It was released in Jul 2023.

Terms used on this page