Models and Pricing

Avian API Models

Models

Model	Description	Context Length	Speed
Meta-Llama-3.1-405B-Instruct	High-intelligence model for complex, multi-step tasks	131,072 tokens	~ 130 t/s
Meta-Llama-3.3-70B-Instruct	High intelligence at a cheaper price than Llama 405B	131,072 tokens	~ 250 t/s
Meta-Llama-3.1-70B-Instruct	Fast and versatile model for general usage	131,072 tokens	~ 250 t/s
Meta-Llama-3.1-8B-Instruct	Extremely quick model for high throughput tasks	131,072 tokens	~ 500 t/s

Avian API Pricing

Model	Input Price (per 1M tokens)	Output Price (per 1M tokens)
Meta-Llama-3.1-405B-Instruct	$1.50 USD	$1.50 USD
Meta-Llama-3.3-70B-Instruct	$0.45 USD	$0.45 USD
Meta-Llama-3.1-70B-Instruct	$0.45 USD	$0.45 USD
Meta-Llama-3.1-8B-Instruct	$0.10 USD	$0.10 USD

Avian Dedicated Deployments Pricing

GPU	Price (billed per second)	Memory
H200 SXM	From $0.00208	141GB HBM3
H100 SXM	From $0.00139	80GB HBM3