Meta logo

Llama 3.1


Llama 3.1 is Meta's language model with a 8K context window and up to 8K output tokens. Meta's Llama 3.1 open-weight LLM series with extended 128K context window and improved multilingual and tool-use capabilities.
Specifications
Canonical IDmeta-llama-3-1
TypeLanguage
StatusActive
CreatorMetaMeta
Context Window8K tokens
Max Output8K tokens
Input ModalitiesText
Output ModalitiesText

Capabilities

Input1/5
Text
Image·
Audio·
Video·
PDF·
Output1/5
Text
Image·
Audio·
Video·
Embedding·
Capabilities1/13
Reasoning·
Adaptive Reasoning·
Function Calling
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
Llama 3.2 11B128K$0.160$0.160Available
Llama 3.2 11B Instruct128K$0.350$0.350Deprecated
Llama 3.2 1B Instruct128K$0.027$0.080Deprecated
Llama 3.2 3B Instruct131K$0.015$0.020Deprecated
Llama 3.2 90B128K$0.720$0.720Available
Llama 3.2 90B Instruct128K$2.00$2.00Deprecated
Llama 3.2 1B131K$0.100$0.100Available
Llama 3.2 3B131K$0.040$0.080Available
Llama 3.1 405B Instruct131K$0.120$0.300Deprecating
Llama 3.1 70B128K$0.600$0.600Available
Llama 3.18KCurrent

Model IDs