Snowflake Cortex models in preview¶

This page is an index of models in private preview for Cortex AI Functions and REST API requests. Contact your Snowflake representative for access to a listed model in an available region.

AI Functions¶

The following models are in private preview to use with their designated AISQL functions:

Cross-region¶


Function (Model)	Cross Cloud (Any Region)	AWS US (Cross-Region)	AWS US Commercial Gov (Cross-Region)	Google Cloud US (Cross-Region)
AI_COMPLETE `claude-4-opus`	*	*	*
AI_COMPLETE `gemini-2.5-flash`				*
AI_COMPLETE `gemini-2.5-flash-lite`				*

North America¶


Function (Model)	Azure East US 2 (Virginia)
AI_COMPLETE `openai-o4-mini`	*

REST API endpoints¶

The following models are in private preview for REST API endpoints:


(Model)	Cross Cloud (Any Region)
`openai-o4-mini`	*

Model restrictions¶

Models used by Snowflake Cortex have limitations on size as described in the following table. Sizes are stated in tokens. Tokens generally represent about four characters of text, so the number of words corresponding to a limit is less than the number of tokens. Inputs that exceed the limit result in an error.

The maximum size of the output that a model can produce is limited by the following factors:

The model's output token limit
The space available in the context window after the model consumes the input tokens


Function	Model	Context window (tokens)	Max output (tokens)
COMPLETE	`gemini-2.5-flash`	1,048,576	64,000
	`gemini-2.5-flash-lite`	1,048,576	64,000
	`claude-4-opus`	200,000	8,192