llama-3_2-nemoretriever-300m-embed-v1 API
About
llama-3_2-nemoretriever-300m-embed-v1 is a high-performance LLM available via the Nvidia API, ideal for scalable text generation and natural language processing. This model delivers available completely free of charge, open weights architecture. Access llama-3_2-nemoretriever-300m-embed-v1 via the Nvidia API with up to 2K output tokens.
Capabilities
Input Modalities
text
Output Modalities
text
Reasoning
No
Structured Output
No
Tool Use
No
WeightsOpen
Limits
Context Window
33K
Tokens
Input Limit
33K
Tokens
Max Output
2K
Tokens
Pricing
Standard (per 1M tokens)
Input
Free
Output
Free
Frequently Asked Questions
llama-3_2-nemoretriever-300m-embed-v1 by Nvidia costs Free per 1M input tokens and Free per 1M output tokens.
Model Details
ID
nvidia/llama-3_2-nemoretriever-300m-embed-v1
Provider
NvidiaFamily
Release Date
Jul 24, 2025
Knowledge Cutoff
N/A
API Integration
NPM Package
@ai-sdk/openai-compatible
Environment Variables
NVIDIA_API_KEY
API Base URL
https://integrate.api.nvidia.com/v1