Llama 3.2 1B Instruct is Meta's language model with a 131K context window and up to 60K output tokens, available from 5 providers, starting at $0.027 / 1M input and $0.080 / 1M output. Meta's 1B instruction-tuned LLM from Llama 3.2, optimized for lightweight on-device deployment with efficient instruction-following in multiple regions.
Specifications
Canonical IDmeta-llama-3-2-1b-instruct
TypeLanguage
StatusDeprecated
CreatorMetaMeta
Providers
Context Window131K tokens
Max Output60K tokens
Input ModalitiesText
Output ModalitiesText
Parameters1B
HuggingFace Likes1,372
HuggingFace Downloads (30d)4,623,641
HuggingFace Downloads (all-time)59,725,960
Release Date · 2 years ago
Knowledge Cutoff
Deprecation Date
Benchmarks
Intelligence Index
6.3
#466
Coding Index
0.6
#389
Math Index
0.0
#260
MMLU-Pro
0.2
#319
GPQA
0.2
#450
HLE
0.1
#249
LiveCodeBench
0.0
#320
AIME
0.0
#169
IFBench
0.2
#371
Time to First Token
0.58s
#273
SciCode
0.0
#441
MATH-500
0.1
#181
AIME 2025
0.0
#260
LCR
0.1
#318
TerminalBench Hard
0.0
#368
TAU2
0.0
#376
Output TPS
96.5
#129

Capabilities

Input1/5
Text
Image·
Audio·
Video·
PDF·
Output1/5
Text
Image·
Audio·
Video·
Embedding·
Capabilities3/13
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·

Pricing by Provider

View Amazon Bedrock

Cost Calculator

Preset:

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
Llama 3.3 70B Instruct131K$0.100$0.200Available
Llama 3.2 1B Instruct131K$0.027$0.080Current
Llama 3.2 3B Instruct131K$0.015$0.020Deprecated
Llama 3.1 405B Instruct131K$0.120$0.300Deprecating
Llama 3.1 70B Instruct131K$0.100$0.100Available
Llama 3.1 8B Instruct200K$0.020$0.030Available
Llama 3.1 70B128K$0.360$0.360Available
Llama 3.1 8B131K$0.030$0.050Available
Llama 3 70B Instruct131K$0.120$0.300Available
Llama 3 8B Instruct32K$0.030$0.040Available
Llama 3.1 Tulu3 405BAvailable

Model IDs