LLM Reference
NVIDIA NIM

Llama 3.1 Swallow 70B Instruct on NVIDIA NIM

Swallow · Tokyo Institute of Technology

Serverless

Pricing

TypePrice (per 1M)
Input tokensFree
Output tokensFree

Capabilities

VisionMultimodalReasoningFunction CallingTool UseJSON ModeCode Execution

About Llama 3.1 Swallow 70B Instruct

Japanese bilingual model from Institute of Science Tokyo, fine-tuned from Llama 3.1.

Get Started

DocsPortalPricing

Model Specs

Released2025-01-01
Parameters70B
Context4K
ArchitectureDecoder Only

Related Models on NVIDIA NIM

Llama 3.1 Swallow 8B InstructLlama 3 Swallow 70B Instruct

Provider

NVIDIA NIM
NVIDIA NIM

NVIDIA

All models on NVIDIA NIM →