Snowflake Arctic Embed L v2.0

Embedding

Snowflake Arctic Embed L v2.0 is a 568M-parameter multilingual embedding model optimized for semantic retrieval and RAG pipelines. Apache 2.0, 1024-dimensional vectors, 8192-token context window.

Available on

Snowflake Cortex AI

Technical specification

Context window

Parameters

License

Apache 2.0

Tools

Fine-tuning

Yes

Weights access

Open weights

Last updated: Apr 28, 2026

Modalities

Input

Text

Output

Structured data

Capabilities

Multilingual★

Language

Long context★

Reasoning

Pricing

Apr 28, 2026Source

PublicUSDper 1M tokens

Dostępny w Snowflake Cortex AI w modelu usage-based (Snowflake Credits). Na Hugging Face i do lokalnego wdrożenia bezpłatnie.

📋

Public pricing is marked but no items (e.g. price per 1M tokens) have been added yet.

Security and enterprise

Modele hostowane w Snowflake Cortex AI korzystają z pełnej infrastruktury bezpieczeństwa Snowflake. Dane nie opuszczają granicy bezpieczeństwa platformy.

Official Privacy CenterUpdated: April 28, 2026

Sources

Repository1Research paper1Documentation1

Arctic Embed L v2.0 – Hugging Face

huggingface.coRepository

Arctic-Embed 2.0: Multilingual Retrieval Without Compromise (arXiv 2412.04506)

arxiv.orgResearch paper

Snowflake Cortex AI – LLM Functions (dostępność modeli)

docs.snowflake.comDocumentation

Snowflake Arctic Embed L v2.0Snowflake Arctic Embed L v2.0Snowflake Arctic Embed L v2.0