Meta logo

Llama 3 8B Instruct

Pricing & Specs API
Free REST API for prices, specs and benchmarks
Llama 3 8B Instruct is Meta's language model with a 32K context window and up to 8K output tokens, available from 8 providers, starting at $0.03 / 1M input and $0.04 / 1M output. Meta's 8B instruction-tuned LLM from the Llama 3 generation, offering fast and cost-effective instruction-following across diverse tasks.
Specifications
Canonical IDmeta-llama-3-8b-instruct
TypeLanguage
StatusActive
CreatorMetaMeta
Providers
Context Window32K tokens
Max Output8K tokens
Input ModalitiesPDFText
Output ModalitiesText
Parameters8B
HuggingFace Likes4,486
HuggingFace Downloads (30d)1,342,402
HuggingFace Downloads (all-time)40,122,839
Release Date · 2 years ago
Knowledge Cutoff · 3 years ago
Deprecation Date
Benchmarks
Intelligence Index
#543
MMLU-Pro
#314
GPQA
#490
HLE
#354
LiveCodeBench
#312
AIME
#181
IFBench
#393
Time to First Token
#195
SciCode
#450
MATH-500
#166
LCR
#447
TerminalBench Hard
#400
TAU2
#409
Output TPS
#430

Capabilities

Input2/5
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

US Dollar ($)
Per 1M tokens
ProviderStandard
Input
$ / 1M
Output
$ / 1M
Amazon Bedrock logo
Amazon Bedrock
meta.llama3-8b-instruct-v1:0
$0.3$0.6
Anyscale logo
Anyscale
anyscale/meta-llama/Meta-Llama-3-8B-Instruct
$0.15$0.15
Cloudflare Workers AI logo
Cloudflare Workers AI
@cf/meta/llama-3-8b-instruct
$0.282$0.827
DeepInfra logo
DeepInfra
deepinfra/meta-llama/Meta-Llama-3-8B-Instruct
$0.03$0.06
Fireworks AI logo
Fireworks AI
fireworks_ai/accounts/fireworks/models/llama-v3-8b-instruct-hf
$0.2$0.2
Gradient AI logo
Gradient AI
gradient_ai/llama3-8b-instruct
$0.2$0.2
Novita logo
Novita
novita/meta-llama/llama-3-8b-instruct
$0.04$0.04
Replicate logo
Replicate
replicate/meta/llama-3-8b-instruct
$0.05$0.25

Cost Calculator

US Dollar ($)
Preset:

Cheapest Instances to Run It

Cloud GPU instances that can host Llama 3 8B Instruct, ranked by cheapest on-demand price. The model needs about 19 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
g2-standard-4GCPnvidia-l424 GB$0.705/hr
g6.xlargeAWSL422 GB$0.805/hr
g2-standard-8GCPnvidia-l424 GB$0.851/hr
7 more instances can run Llama 3 8B 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 8B Instruct32K$0.030$0.040Current
Llama 3 70B Instruct131K$0.120$0.300Deprecated

Model IDs

@cf/meta/llama-3-8b-instruct
accounts/fireworks/models/llama-v3-8b-instruct
accounts/fireworks/models/llama-v3-8b-instruct-hf
accounts/fireworks/models/llama-v3-8b-instruct-v0
anyscale/meta-llama/Meta-Llama-3-8B-Instruct
bedrock/ap-south-1/meta.llama3-8b-instruct-v1:0
bedrock/ca-central-1/meta.llama3-8b-instruct-v1:0
bedrock/eu-west-1/meta.llama3-8b-instruct-v1:0
bedrock/eu-west-2/meta.llama3-8b-instruct-v1:0
bedrock/sa-east-1/meta.llama3-8b-instruct-v1:0
bedrock/us-east-1/meta.llama3-8b-instruct-v1:0
bedrock/us-gov-east-1/meta.llama3-8b-instruct-v1:0
bedrock/us-gov-west-1/meta.llama3-8b-instruct-v1:0
bedrock/us-west-1/meta.llama3-8b-instruct-v1:0
deepinfra/meta-llama/Meta-Llama-3-8B-Instruct
fireworks_ai/accounts/fireworks/models/llama-v3-8b-instruct-hf
gradient_ai/llama3-8b-instruct
huggingface-llm-gradientai-llama-3-8B-instruct-262k
huggingface-llm-llama-3-8b-instruct-gradient
llama-3-instruct-8b
meta-llama-3-8b-instruct
meta-llama/llama-3-8b-instruct
meta-llama/Meta-Llama-3-8B-Instruct
meta-textgeneration-llama-3-8b-instruct
meta-textgenerationneuron-llama-3-8b-instruct
meta.llama3-8b-instruct-v1:0
novita/meta-llama/llama-3-8b-instruct
replicate/meta/llama-3-8b-instruct
vertex_ai/meta/llama3-8b-instruct-maas