Snowflake Cortex models & pricing

Snowflake Cortex hosts 24 models covering 1 modalities. In-warehouse LLM functions — Arctic, Llama, Mistral, with data residency in Snowflake. Cheapest input starts at free tier; the most premium goes up to enterprise tier. Use Future AGI's Agent Command Center to route any Snowflake Cortex model with cost-optimized fallback and unified observability.

Homepage ↗ Docs ↗
24

chat 24

Model Input / 1M Output / 1M Context Caps
Claude 3.5 Sonnet 18,000
DeepSeek R1 32,768 reasoning
Gemma 7B 8,000
Jamba 1.5 Large 256,000
Jamba 1.5 mini 256,000
Jamba Instruct 256,000
Llama2.70b Chat 4,096
Llama3.1 405B 128,000
Llama3.1 70B 128,000
Llama3.1 8B 128,000
Llama3.2 1B 128,000
Llama3.2 3B 128,000
Llama3.3 70B 128,000
Llama3.70b 8,000
Llama3.8b 8,000
Mistral 7B 32,000
Mistral Large 32,000
Mistral Large2 128,000
Mixtral 8×7B 32,000
Reka Core 32,000
Reka Flash 100,000
Snowflake Arctic 4,096
Snowflake Llama 3.1 405B 8,000
Snowflake Llama 3.3 70B 8,000

FAQ

How many Snowflake Cortex models are there?

24 Snowflake Cortex models are listed across 1 modality on this page. 0 have public per-token pricing.

How is Snowflake Cortex pricing verified?

Pricing is aggregated from BerriAI/litellm, models.dev, and OpenRouter and refreshed weekly. Each row shows a per-model "verified" date. If a price is wrong, click the row to open the model page and use the inline "suggest edit" link — submissions go into a public review queue.

Which Snowflake Cortex model is cheapest?

Several Snowflake Cortex models are free or have public-pricing pending. Browse the rows above and submit a source if you spot one we're missing.

Can I route to Snowflake Cortex via an OpenAI-compatible API?

Yes — point your OpenAI client at Future AGI's Agent Command Center, configure a Snowflake Cortex target, and call Snowflake Cortex models with the standard /v1/chat/completions surface. The same gateway can route to other providers as fallback. Free for the first 100K requests/month.

Route any Snowflake Cortex model via Agent Command Center →
OpenAI-compatible endpoint. Caching, fallback, guardrails, observability. Free for 100K requests/month.