Llama 3.1 405B

Meta · Llama 3 · open · released Jul 23, 2024 · meta-llama/Meta-Llama-3.1-405B-Instruct

Llama 3 family:Llama 3.1 405B·Llama 3.1 8B·Llama 3.3 70B

Meta's largest open model — frontier-class capability with full open weights for sovereign deployment.

Pricing

InputOpen weights / ~$1 / 1M hosted
OutputOpen weights / ~$1 / 1M hosted
Cost bandFree/open
Free tierOpen weights (Meta Llama license).

Limits

Context window128k
Max outputRuntime-dependent
Knowledge cutoffDec 2023
DeploymentSelf-hosted (multi-GPU), Together, Fireworks, Bedrock
OpenAI-compatible APIYes
ModalitiesText

Where it fits

Best forHighest-quality open inference for teams with multi-GPU infrastructure.
Business fitSignificant hardware requirement; Llama 3.3 70B often gives 90% quality at a fraction of the cost.

Capabilities

Open weightsFunction calling128k context

Benchmark scores

Composite79 / 100
Coding78 / 100 (HumanEval)
Reasoning80 / 100 (MMLU-Pro)
Long context76 / 100 (RULER 128K)
Instruction following80 / 100 (IFEval)

Editorial aggregate of published benchmark results as of Sep 1, 2024. These are not independent measurements run by this site.

Change history

No recorded changes for this model yet. Pricing and context are checked daily; changes appear here with dates and sources.

Data

Last checkedJan 10, 2026

Verify with provider documentation before committing spend. Report an error and it gets fixed with a logged correction.

Open in the comparison table JSON API