Llama 3.3 70B Instruct is Meta's language model with a 131K context window and up to 120K output tokens, available from 21 providers, starting at $0.1 / 1M input and $0.2 / 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 · 2 years ago
Knowledge Cutoff · 3 years ago
Benchmarks
Intelligence Index
8.6
#317
Math Index
7.7
#228
MMLU-Pro
0.7
#196
GPQA
0.5
#325
HLE
0.0
#399
LiveCodeBench
0.3
#217
AIME
0.3
#75
IFBench
0.5
#169
Time to First Token
0.61s
#288
SciCode
0.3
#291
MATH-500
0.8
#103
AIME 2025
0.1
#228
LCR
0.1
#280
TerminalBench Hard
0.0
#291
TAU2
0.3
#255
Output TPS
94.7
#138

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

US Dollar ($)
Per 1M tokens
ProviderStandardBatch
Input
$ / 1M
Output
$ / 1M
Input
$ / 1M
Output
$ / 1M
Amazon Bedrock logo
Amazon Bedrock
meta.llama3-3-70b-instruct-v1:0
$0.72$0.72$0.36$0.36
Azure AI Foundry logo
Azure AI Foundry
azure_ai/Llama-3.3-70B-Instruct
$0.71$0.71
Crusoe
crusoe/meta-llama/Llama-3.3-70B-Instruct
$0.2$0.2
Databricks logo
Databricks
databricks/databricks-meta-llama-3-3-70b-instruct
$0.5$1.50
DeepInfra logo
DeepInfra
deepinfra/meta-llama/Llama-3.3-70B-Instruct
$0.23$0.4
Fireworks AI logo
Fireworks AI
fireworks_ai/accounts/fireworks/models/llama-v3p3-70b-instruct
$0.9$0.9
Gradient AI logo
Gradient AI
gradient_ai/llama3.3-70b-instruct
$0.65$0.65
Groq logo
Groq
groq/llama-3.3-70b-versatile
$0.59$0.79
Hugging Face logo
Hugging Face
hyperbolic:meta-llama/Llama-3.3-70B-Instruct
$0.4N/A
Hugging Face logo
Hugging Face
novita:meta-llama/llama-3.3-70b-instruct
$0.135$0.4
Hugging Face logo
Hugging Face
ovhcloud:Meta-Llama-3_3-70B-Instruct
$0.74$0.74
Hyperbolic logo
Hyperbolic
hyperbolic/meta-llama/Llama-3.3-70B-Instruct
$0.12$0.3
IBM watsonx logo
IBM watsonx
watsonx/meta-llama/llama-3-3-70b-instruct
$0.71$0.71
Lambda logo
Lambda
lambda_ai/llama3.3-70b-instruct-fp8
$0.12$0.3
Nebius logo
Nebius
nebius/meta-llama/Llama-3.3-70B-Instruct
$0.13$0.4
Novita logo
Novita
novita/meta-llama/llama-3.3-70b-instruct
$0.135$0.4
Nscale logo
Nscale
nscale/meta-llama/Llama-3.3-70B-Instruct
$0.2$0.2
OpenRouter logo
OpenRouter
meta-llama/llama-3.3-70b-instruct
$0.1$0.32
Oracle Cloud (OCI) logo
Oracle Cloud (OCI)
oci/meta.llama-3.3-70b-instruct
$0.72$0.72
OVHcloud logo
OVHcloud
ovhcloud/Meta-Llama-3_3-70B-Instruct
$0.67$0.67
SambaNova logo
SambaNova
sambanova/Meta-Llama-3.3-70B-Instruct
$0.6$1.20
Scaleway logo
Scaleway
scaleway/meta/llama-3.3-70b-instruct
$0.9$0.9
Weights & Biases logo
Weights & Biases
wandb/meta-llama/Llama-3.3-70B-Instruct
$71.00$71.00

Cost Calculator

US Dollar ($)
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 3.2 11B128K$0.160$0.160Available
Llama 3.1 405B Instruct131K$0.120$0.300Deprecating
Llama 3.1 70B Instruct131K$0.120$0.300Available
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$0.300Deprecated
Llama 3 8B Instruct32K$0.030$0.040Available

Model IDs

accounts/fireworks/models/llama-v3p3-70b-instruct
azure_ai/Llama-3.3-70B-Instruct
crusoe/meta-llama/Llama-3.3-70B-Instruct
databricks/databricks-meta-llama-3-3-70b-instruct
deepinfra/meta-llama/Llama-3.3-70B-Instruct
fireworks_ai/accounts/fireworks/models/llama-v3p3-70b-instruct
gradient_ai/llama3.3-70b-instruct
groq/llama-3.3-70b-versatile
hyperbolic/meta-llama/Llama-3.3-70B-Instruct
lambda_ai/llama3.3-70b-instruct-fp8
llama-3-3-instruct-70b
llama-3.3-70b-instruct-maas
meta_llama/Llama-3.3-70B-Instruct
meta-llama-3-3-70b-instruct
meta-llama/llama-3.3-70b-instruct
meta-llama/llama-3.3-70b-instruct:free
meta-textgeneration-llama-3-3-70b-instruct
meta.llama3-3-70b-instruct-v1:0
meta.llama3-3-70b-instruct-v1:0:128k
nebius/meta-llama/Llama-3.3-70B-Instruct
novita/meta-llama/llama-3.3-70b-instruct
nscale/meta-llama/Llama-3.3-70B-Instruct
oci/meta.llama-3.3-70b-instruct
oci/meta.llama-3.3-70b-instruct-fp8-dynamic
ovhcloud/Meta-Llama-3_3-70B-Instruct
publishers/google/models/llama-3.3-70b-instruct-maas
publishers/meta/models/llama-3.3-70b-instruct-maas
sambanova/Meta-Llama-3.3-70B-Instruct
scaleway/meta/llama-3.3-70b-instruct
together_ai/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free
us.meta.llama3-3-70b-instruct-v1:0
wandb/meta-llama/Llama-3.3-70B-Instruct
watsonx/meta-llama/llama-3-3-70b-instruct