MetaReleased on Jul 23, 2024

Llama 3.1 70B Instruct: Benchmarks, Pricing & Context Window

Llama 3.1 70B Instruct is a language model from Meta, released in July 2024.

Llama 3.1 70B Instruct is a large language model optimized for multilingual dialogue use cases. It outperforms many available open source and closed chat models on common industry benchmarks.

Input
Text
Output
Text
Speed
TTFT200ms
Throughput1204char/s
Cost
$0.20/ 1M · 8:1 in:out
$0.20 in · $0.20 out

Llama 3.1 70B Instruct pricing

Providers

Llama 3.1 70B Instruct starts at $0.200 per million input tokens and $0.200 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 sThroughputQuantInputOutput
Lambda logoLambda
$0.200$0.200128.0K128.0K
0.50
42 c/s
—
DeepInfra logoDeepInfra
$0.350$0.400128.0K128.0K
0.50
25 c/s
—
Hyperbolic logoHyperbolic
$0.400$0.400128.0K128.0K
0.50
100 c/s
—
Groq logoGroq
$0.590$0.780128.0K128.0K
0.50
250 c/s
—
Cerebras logoCerebras
$0.600$0.600128.0K128.0K
0.20
1204 c/s
—
Together logoTogether
$0.890$0.890128.0K128.0K
0.50
94 c/s
—
Fireworks logoFireworks
$0.890$0.890128.0K128.0K
0.50
32 c/s
—
Bedrock logoBedrock
$0.890$0.890128.0K128.0K
0.50
100 c/s
—
Sambanova logoSambanova
$5.00$10.00128.0K128.0K
0.50
74 c/s
—
Loading chart...
Loading chart...
Loading chart...

Llama 3.1 70B Instruct API

API access coming soon

Llama 3.1 70B Instruct will be available through our gateway shortly.

Llama 3.1 70B Instruct examples

Recent arena outputs from Llama 3.1 70B Instruct, picked from the highest-ranked matchups.

Llama 3.1 70B Instruct license

Llama 3.1 70B Instruct is released under the Llama 3.1 Community License license, which restricts commercial use, has 70.0B parameters.

License
Llama 3.1 Community License
Non-commercial
Parameters
70.0B

FAQ

Common questions about Llama 3.1 70B Instruct.

When was Llama 3.1 70B Instruct released?

Llama 3.1 70B Instruct was released on July 23, 2024 by Meta. This is the official Llama 3.1 70B Instruct release date tracked on LLM Stats.

Is Llama 3.1 70B Instruct available via API?

Yes, Llama 3.1 70B 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 many parameters does Llama 3.1 70B Instruct have?

Llama 3.1 70B Instruct has 70 billion parameters. It ships as an open-weight model, so you can download and run it on your own hardware.

Who created Llama 3.1 70B Instruct?

Llama 3.1 70B Instruct was created by Meta.

What is the license for Llama 3.1 70B Instruct?

Llama 3.1 70B Instruct is released under the Llama 3.1 Community License license. This is an open-source / open-weight license that permits self-hosting.

Where can I use Llama 3.1 70B Instruct?

Llama 3.1 70B Instruct is available through 9 providers including Lambda, DeepInfra, Hyperbolic, and 6 more.

Where is the Llama 3.1 70B Instruct paper or technical report?

Llama 3.1 70B Instruct has a paper or technical report available at https://ai.meta.com/research/publications/llama-3-open-foundation-and-fine-tuned-chat-models/. Use that source for architecture, training, release and evaluation details.