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

CodeLlama 7B Instruct

Code

Smallest CodeLlama. Cheap on-prem code completion baseline; better modern options exist.

CodeLlama 7B Instruct is a efficient AI model from Meta. It costs $0.180 per million input tokens and $0.180 per million output tokens (blended $0.180/M), with a 16K-token context window.

Released Aug 2023Modalities textOfficial model page ↗API docs ↗Compare with another model →Estimate monthly cost →
INPUT
$0.180/M
per million input tokens
OUTPUT
$0.180/M
per million output tokens
BLENDED 70/30
$0.180/M
default reference rate · how it's calculated →
CONTEXT
16K
16,000 tokens
What it's good at
  • Open weights
  • Cheap
Typical use cases
  • Legacy CodeLlama 7B fine-tunes
Benchmarks
vs. best public score
HumanEval35%
Python function synthesis from docstrings.
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 CodeLlama 7B Instruct cost?

CodeLlama 7B Instruct costs $0.180 per million input tokens and $0.180 per million output tokens, for a blended reference rate of $0.180 per million tokens.

What is CodeLlama 7B Instruct's context window?

CodeLlama 7B Instruct supports up to 16K tokens of context (16,000 tokens).

What is CodeLlama 7B Instruct best for?

CodeLlama 7B Instruct is well suited to Open weights, Cheap and Legacy CodeLlama 7B fine-tunes.

Who makes CodeLlama 7B Instruct?

CodeLlama 7B Instruct is developed and served by Meta. It was released in Aug 2023.