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 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 4K-token context window.

Released Jul 2023Modalities textOfficial model page ↗API docs ↗Compare with another model →Estimate monthly cost →
INPUT
$0.900/M
per million input tokens
OUTPUT
$0.900/M
per million output tokens
BLENDED 70/30
$0.900/M
default reference rate · how it's calculated →
CONTEXT
4K
4,000 tokens
What it's 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.
GPQA Diamond24%
Graduate-level science questions, "Google-proof".
MATH14%
High-school competition math problems.
HumanEval30%
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 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 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 4K tokens of context (4,000 tokens).

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.