MetaReleased on Jul 23, 2024

Llama 3.1 8B Instruct: Benchmarks, Pricing & Size

Llama 3.1 8B Instruct is a language model from Meta, released in July 2024.

Llama 3.1 8B Instruct is a multilingual large language model optimized for dialogue use cases. It features a 128K context length, state-of-the-art tool use, and strong reasoning capabilities.

Input
Text
Output
Text
Speed
Latency p95200ms
Throughput P952047char/s
Cost
$0.03/ 1M · 8:1 in:out
$0.03 in · $0.03 out

Llama 3.1 8B Instruct pricing

Providers

Llama 3.1 8B Instruct starts at $0.0300 per million input tokens and $0.0300 per million output tokens via Lambda. See all 9 providers below with their per-token pricing, latency, throughput, and modality support.

ProviderInput $/MOutput $/MMax InputMax OutputLatency p95 sThroughput P95QuantInputOutput
Lambda logoLambda
$0.0300$0.0300131.1K131.1K
0.50
42 c/s
—
DeepInfra logoDeepInfra
$0.0500$0.0500131.1K131.1K
0.50
118 c/s
—
Groq logoGroq
$0.0500$0.0800131.1K131.1K
0.50
750 c/s
—
Sambanova logoSambanova
$0.100$0.200131.1K131.1K
0.50
1050 c/s
—
Cerebras logoCerebras
$0.100$0.100131.1K131.1K
0.20
2047 c/s
—
Hyperbolic logoHyperbolic
$0.100$0.100131.1K131.1K
0.50
200 c/s
—
Together logoTogether
$0.200$0.200131.1K131.1K
0.50
194 c/s
—
Fireworks logoFireworks
$0.200$0.200131.1K131.1K
0.50
292 c/s
—
Bedrock logoBedrock
$0.220$0.220131.1K131.1K
0.50
100 c/s
—
Loading chart...
Loading chart...
Loading chart...

Llama 3.1 8B Instruct model size

Llama 3.1 8B Instruct has 8 billion parameters and was trained on 15 trillion tokens. See how it compares to other models in the same parameter range.

ParametersTraining tokens
8B
15Ttokens
1875× tokens-to-params ratio
Small (3–10B)
8B
1B7B70B405B

Llama 3.1 8B Instruct API

API access coming soon

Llama 3.1 8B Instruct will be available through our gateway shortly.

Llama 3.1 8B Instruct examples

Recent arena outputs from Llama 3.1 8B Instruct, picked from the highest-ranked matchups.

Llama 3.1 8B Instruct license

Llama 3.1 8B Instruct is released under the Llama 3.1 Community License license, which restricts commercial use, has 8.0B parameters, has a knowledge cutoff of December 2023.

License
Llama 3.1 Community License
Non-commercial
Parameters
8.0B
Knowledge cutoff
December 2023

FAQ

Common questions about Llama 3.1 8B Instruct.

When was Llama 3.1 8B Instruct released?

Llama 3.1 8B Instruct was released on July 23, 2024 by Meta. This is the official Llama 3.1 8B Instruct release date tracked on LLM Stats.

Is Llama 3.1 8B Instruct available via API?

Yes, Llama 3.1 8B Instruct is available via API. See the official documentation for authentication and endpoint details. It is served by 9 providers tracked on LLM Stats.

How big is Llama 3.1 8B Instruct?

Llama 3.1 8B Instruct has 8 billion parameters. It was trained on 15.0 trillion tokens. It ships as an open-weight model, so you can download and run it on your own hardware.

Who created Llama 3.1 8B Instruct?

Llama 3.1 8B Instruct was created by Meta.

What is the license for Llama 3.1 8B Instruct?

Llama 3.1 8B Instruct is released under the Llama 3.1 Community License license. This is an open-source / open-weight license that permits self-hosting.

What is the knowledge cutoff date for Llama 3.1 8B Instruct?

Llama 3.1 8B Instruct has a knowledge cutoff of December 2023, meaning it was trained on data up to that point and may not know about events after it.

Where can I use Llama 3.1 8B Instruct?

Llama 3.1 8B Instruct is available through 9 providers including Lambda, DeepInfra, Groq, and 6 more.

Where is the Llama 3.1 8B Instruct paper or technical report?

Llama 3.1 8B Instruct has a paper or technical report available at https://ai.meta.com/blog/meta-llama-3-1/. Use that source for architecture, training, release and evaluation details.