Run Llama 3.1 8B on your data

Llama 3.1 8B is an LLM designed for multilingual dialogue use cases and optimized for tool use. It excels in tasks requiring strong reasoning and integration with external tools, making it a valuable choice for applications involving function calling, API interactions, or structured data manipulation. The model leverages supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to enhance safety and helpfulness.

Metric	Value
Parameter Count	8 billion
Mixture of Experts	No
Context Length	128,000 tokens
Multilingual	Yes
Quantized*	Unknown

*Quantization is specific to the inference provider and may vary.

	Modality	Price (1M tokens)
Llama 3.1 405B Instruct	text	text	$3.00	$3.00
Llama 3.1 70B Instruct	text	text	$0.90	$0.90
Llama 3.1 8B	text	text	$0.05	$0.08
Llama 3.3 70B Instruct	text	text	$0.90	$0.90
Llama 3.3 70B Speculative Decoding	text	text	$0.59	$0.59
Llama 3.3 70B Versatile 128k	text	text	$0.59	$0.79
Llama 4 Maverick	text, image	text	$0.22	$0.88
meta-llama/Llama-3.1-8B-Instruct	text	text	$0.20	$0.20
meta-llama/Llama-4-Scout-17B-16E-Instruct	text	text	$0.08	$0.30

Modality

Price (1M tokens)

Model

Input

Output

Input

Output

Llama 3.1 405B Instruct

text

$3.00

Llama 3.1 70B Instruct

text