Llama 3.3 70B Instruct is Meta's language model with a 131K context window and up to 120K output tokens, available from 20 providers, starting at $0.100 / 1M input and $0.200 / 1M output. Meta's 70B instruction-tuned LLM from Llama 3.3, optimized for complex instruction-following and deployed across multiple cloud regions.
Specifications
Canonical IDmeta-llama-3-3-70b-instruct
TypeLanguage
StatusActive
CreatorMetaMeta
Providers
Context Window131K tokens
Max Output120K tokens
Input ModalitiesText
Output ModalitiesText
Parameters70B
HuggingFace Likes2,731
HuggingFace Downloads (30d)496,024
HuggingFace Downloads (all-time)10,779,619
Release Date · 1 year ago
Knowledge Cutoff
Benchmarks
Intelligence Index
14.5
#308
Coding Index
10.7
#290
Math Index
7.7
#228
MMLU-Pro
0.7
#196
GPQA
0.5
#317
HLE
0.0
#390
LiveCodeBench
0.3
#217
AIME
0.3
#75
IFBench
0.5
#160
Time to First Token
0.60s
#276
SciCode
0.3
#284
MATH-500
0.8
#103
AIME 2025
0.1
#228
LCR
0.1
#273
TerminalBench Hard
0.0
#283
TAU2
0.3
#247
Output TPS
93.8
#132

Capabilities

Input1/5
Text
Image·
Audio·
Video·
PDF·
Output1/5
Text
Image·
Audio·
Video·
Embedding·
Capabilities4/13
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

Cost Calculator

Preset:

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
Llama 3.3 70B Instruct131K$0.100$0.200Current
Llama 3.2 3B Instruct131K$0.015$0.020Deprecated
Llama 3.2 1B Instruct131K$0.027$0.080Deprecated
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