Meta logo

Llama 3 70B Instruct

Deprecated
Pricing & Specs API
Free REST API for prices, specs and benchmarks
Llama 3 70B Instruct is Meta's language model with a 131K context window and up to 8K output tokens, available from 8 providers, starting at $0.12 / 1M input and $0.3 / 1M output. Meta's 70B instruction-tuned LLM from the Llama 3 generation, widely used for enterprise conversational AI and complex instruction-following tasks.
Specifications
Canonical IDmeta-llama-3-70b-instruct
TypeLanguage
StatusDeprecated
CreatorMetaMeta
Providers
Context Window131K tokens
Max Output8K tokens
Input ModalitiesPDFText
Output ModalitiesText
Parameters70B
HuggingFace Likes1,510
HuggingFace Downloads (30d)44,220
HuggingFace Downloads (all-time)5,966,217
Release Date · 2 years ago
Knowledge Cutoff · 3 years ago
Deprecation Date
Benchmarks
Intelligence Index
#485
MMLU-Pro
#273
GPQA
#447
HLE
#407
LiveCodeBench
#265
AIME
#180
IFBench
#290
Time to First Token
#194
SciCode
#413
MATH-500
#169
LCR
#446
TerminalBench Hard
#361
TAU2
#408
Output TPS
#429

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

US Dollar ($)
Per 1M tokens
ProviderStandard
Input
$ / 1M
Output
$ / 1M
Cache Read
$ / 1M
Cache Write 5m
$ / 1M
Amazon Bedrock logo
Amazon Bedrock
meta.llama3-70b-instruct-v1:0
$2.65$3.50N/AN/A
Anyscale logo
Anyscale
anyscale/meta-llama/Meta-Llama-3-70B-Instruct
$1.00$1.00N/AN/A
Databricks logo
Databricks
databricks/databricks-meta-llama-3-70b-instruct
$1.00$3.00$1.00$1.00
Fireworks AI logo
Fireworks AI
fireworks_ai/accounts/fireworks/models/llama-v3-70b-instruct
$0.9$0.9N/AN/A
Hyperbolic logo
Hyperbolic
hyperbolic/meta-llama/Meta-Llama-3-70B-Instruct
$0.12$0.3N/AN/A
Novita logo
Novita
novita/meta-llama/llama-3-70b-instruct
$0.51$0.74N/AN/A
OpenRouter logo
OpenRouter
openrouter/meta-llama/llama-3-70b-instruct
$0.59$0.79N/AN/A
Replicate logo
Replicate
replicate/meta/llama-3-70b-instruct
$0.65$2.75N/AN/A

Cost Calculator

US Dollar ($)
Preset:

Cheapest Instances to Run It

Cloud GPU instances that can host Llama 3 70B Instruct, ranked by cheapest on-demand price. The model needs about 168 GB of GPU memory at FP16 precision (estimated from its parameter count), so treat the fit as guidance rather than a guarantee.

All clouds
FP16 (full precision)
US Dollar ($)
Instance
Cloud
GPU
VRAM
Price
Cheapest region
Standard_NP40sAzure4× AMD Alveo U250 FPGA (64GB)256 GB$6.60/hr
g2-standard-96GCP8× nvidia-l4192 GB$7.98/hr
g7e.12xlargeAWS2× RTX PRO Server 6000192 GB$8.29/hr
7 more instances can run Llama 3 70B Instruct
Unlock the full ranked list and FP8 / INT4 quantization with a CloudPrice subscription.

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
Llama 3.3 70B Instruct131K$0.120$0.200Deprecated
Llama 3.2 3B Instruct131K$0.015$0.020Deprecated
Llama 3.2 1B Instruct131K$0.020$0.020Deprecated
Llama 3.2 11B128K$0.160$0.160Available
Llama 3.1 405B Instruct131K$0.120$0.300Deprecated
Llama 3.1 8B Instruct200K$0.020$0.030Deprecated
Llama 3.1 70B Instruct131K$0.100$0.100Deprecated
Llama 3.1 70B128K$0.360$0.360Available
Llama 3.1 8B131K$0.030$0.050Available
Llama 3 70B Instruct131K$0.120$0.300Current
Llama 3 8B Instruct32K$0.030$0.040Available

Model IDs

accounts/fireworks/models/llama-v3-70b-instruct
accounts/fireworks/models/llama-v3-70b-instruct-hf
accounts/fireworks/models/llama-v3-70b-instruct-v2
anyscale/meta-llama/Meta-Llama-3-70B-Instruct
azure_ai/Meta-Llama-3-70B-Instruct
bedrock/ap-south-1/meta.llama3-70b-instruct-v1:0
bedrock/ca-central-1/meta.llama3-70b-instruct-v1:0
bedrock/eu-west-1/meta.llama3-70b-instruct-v1:0
bedrock/eu-west-2/meta.llama3-70b-instruct-v1:0
bedrock/sa-east-1/meta.llama3-70b-instruct-v1:0
bedrock/us-east-1/meta.llama3-70b-instruct-v1:0
bedrock/us-gov-east-1/meta.llama3-70b-instruct-v1:0
bedrock/us-gov-west-1/meta.llama3-70b-instruct-v1:0
bedrock/us-west-1/meta.llama3-70b-instruct-v1:0
databricks/databricks-meta-llama-3-70b-instruct
fireworks_ai/accounts/fireworks/models/llama-v3-70b-instruct
fireworks_ai/accounts/fireworks/models/llama-v3-70b-instruct-hf
hyperbolic/meta-llama/Meta-Llama-3-70B-Instruct
llama-3-instruct-70b
meta-llama-3-70b-instruct
meta-llama/llama-3-70b-instruct
meta-textgeneration-llama-3-70b-instruct
meta-textgenerationneuron-llama-3-70b-instruct
meta.llama3-70b-instruct-v1:0
novita/meta-llama/llama-3-70b-instruct
openrouter/meta-llama/llama-3-70b-instruct
replicate/meta/llama-3-70b-instruct
vertex_ai/meta/llama3-70b-instruct-maas