Name: Llama 3.1 70B Instruct
Brand: Meta

Llama 3.1 70B Instruct is Meta's language model with a 131K context window and up to 16K output tokens, available from 13 providers, starting at $0.100 / 1M input and $0.100 / 1M output. Meta's 70B instruction-tuned LLM with strong tool-use and multilingual capabilities, widely deployed across cloud regions for enterprise workloads.

Specifications
Canonical ID	`meta-llama-3-1-70b-instruct`
Type	Language
Status	Active
Creator	Meta
Providers	Amazon Bedrock Microsoft Azure AI Foundry Deep Infra Fireworks AI FriendliAI Hyperbolic Lambda Labs Nebius OpenRouter Oracle Cloud Infrastructure (OCI)OVHcloud Perplexity Together AI
Context Window	131K tokens
Max Output	16K tokens
Input Modalities	ImageText
Output Modalities	Text
Parameters	70B
HuggingFace Likes	907
HuggingFace Downloads (30d)	737,459
HuggingFace Downloads (all-time)	20,735,812
Release Date	2024-07-23 · 2 years ago
Knowledge Cutoff	2023-12-31

Benchmarks
Intelligence Index	12.5 #344
Coding Index	10.9 #278
Math Index	4.0 #243
MMLU-Pro	0.7 #221
GPQA	0.4 #355
HLE	0.0 #318
LiveCodeBench	0.2 #243
AIME	0.2 #96
IFBench	0.3 #273
Time to First Token	0.58s #265
SciCode	0.3 #269
MATH-500	0.6 #138
AIME 2025	0.0 #243
LCR	0.1 #306
TerminalBench Hard	0.0 #276
TAU2	0.2 #322
Output TPS	31.8 #251

Capabilities

Input2/5

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

Provider	Standard		Batch
Provider	Input $ / 1M	Output $ / 1M	Input $ / 1M	Output $ / 1M
DeepInfra deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo	$0.100	$0.280	—	—
Fireworks AI fireworks_ai/accounts/fireworks/models/llama-v3p1-70b-instruct-1b	$0.100	$0.100	—	—
Hyperbolic hyperbolic/meta-llama/Meta-Llama-3.1-70B-Instruct	$0.120	$0.300	—	—
Lambda lambda_ai/llama3.1-70b-instruct-fp8	$0.120	$0.300	—	—
Nebius nebius/meta-llama/Meta-Llama-3.1-70B-Instruct	$0.130	$0.400	—	—
OpenRouter meta-llama/llama-3.1-70b-instruct	$0.400	$0.400	—	—
FriendliAI friendliai/meta-llama-3.1-70b-instruct	$0.600	$0.600	—	—
OVHcloud ovhcloud/Meta-Llama-3_1-70B-Instruct	$0.670	$0.670	—	—
Amazon Bedrock meta.llama3-1-70b-instruct-v1:0	$0.720	$0.720	$0.360	$0.360
Oracle Cloud (OCI) oci/meta.llama-3.1-70b-instruct	$0.720	$0.720	—	—
Together AI together_ai/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo	$0.880	$0.880	—	—
Perplexity perplexity/llama-3.1-70b-instruct	$1.00	$1.00	—	—
Azure AI Foundry azure_ai/Meta-Llama-3.1-70B-Instruct	$2.68	$3.54	—	—

Cost Calculator

Preset:

Input tokens

Output tokens

Number of calls

Versions

Version	Released	Context	Input / 1M	Output / 1M	Status
Llama 3.3 70B Instruct	2024-12-06	131K	$0.100	$0.200	Available
Llama 3.2 3B Instruct	2024-09-25	131K	$0.015	$0.020	Deprecated
Llama 3.2 1B Instruct	2024-09-25	131K	$0.027	$0.080	Deprecated
Llama 3.1 70B Instruct	2024-07-23	131K	$0.100	$0.100	Current
Llama 3.1 405B Instruct	2024-07-23	131K	$0.120	$0.300	Deprecating
Llama 3.1 8B Instruct	2024-07-23	200K	$0.020	$0.030	Available
Llama 3.1 70B	2024-07-23	128K	$0.600	$0.600	Available
Llama 3.1 8B	2024-07-23	131K	$0.030	$0.050	Available
Llama 3 70B Instruct	2024-04-18	131K	$0.120	$0.300	Available
Llama 3 8B Instruct	2024-04-18	32K	$0.030	$0.040	Available
Llama 3.1 Tulu3 405B	—	—	—	—	Available

Llama 3.1 70B Instruct

Capabilities

Pricing by Provider

Cost Calculator

Versions

Model IDs