Snowflake Cortex models & pricing
Snowflake Cortex hosts 37 models (21 with public pricing) covering 2 modalities. In-warehouse LLM functions — Arctic, Llama, Mistral, with data residency in Snowflake. Cheapest input starts at $0.0700/M tokens; the most premium goes up to $5.00/M. Use Future AGI's Agent Command Center to route any Snowflake Cortex model with cost-optimized fallback and unified observability.
chat 35
| Model ↕ | Input / 1M ↕ | Output / 1M ↕ | Blended ↕ | Context ↕ | Caps |
|---|---|---|---|---|---|
| OpenAI GPT 5 nano | $0.150/M | $0.600/M | $0.262/M | 5,000,000 | tools |
| Llama3.1 8B | $0.240/M | $0.240/M | $0.240/M | 128,000 | |
| Llama4 Maverick | $0.240/M | $0.970/M | $0.423/M | 128,000 | tools |
| OpenAI GPT 5 mini | $0.300/M | $1.20/M | $0.525/M | 1,000,000 | tools |
| Llama3.1 70B | $0.720/M | $0.720/M | $0.720/M | 128,000 | tools |
| Llama3.3 70B | $0.720/M | $0.720/M | $0.720/M | 128,000 | tools |
| Snowflake Llama 3.3 70B | $0.720/M | $0.720/M | $0.720/M | 128,000 | tools |
| Claude Haiku 4.5 | $1.00/M | $5.00/M | $2.00/M | 200,000 | tools · vision · cache |
| Llama3.1 405B | $1.20/M | $1.20/M | $1.20/M | 128,000 | tools |
| OpenAI GPT 5 | $1.25/M | $10.00/M | $3.44/M | 300,000 | tools · vision · reasoning · cache |
| DeepSeek R1 | $1.35/M | $5.40/M | $2.36/M | 128,000 | reasoning |
| Mistral Large2 | $2.00/M | $6.00/M | $3.00/M | 128,000 | tools |
| OpenAI GPT 4.1 | $2.00/M | $8.00/M | $3.50/M | 300,000 | tools · vision · cache |
| Claude 3.5 Sonnet | $3.00/M | $15.00/M | $6.00/M | 200,000 | tools · vision · cache |
| Claude 3.7 Sonnet | $3.00/M | $15.00/M | $6.00/M | 200,000 | tools · vision · reasoning · cache |
| Claude 4 Sonnet | $3.00/M | $15.00/M | $6.00/M | 200,000 | tools · vision · cache |
| Claude Sonnet 4.5 | $3.00/M | $15.00/M | $6.00/M | 200,000 | tools · vision · cache |
| Claude Sonnet 4.6 | $3.00/M | $15.00/M | $6.00/M | 200,000 | tools · vision · cache |
| Claude 4 Opus | $5.00/M | $25.00/M | $10.00/M | 200,000 | tools · vision · reasoning · cache |
| 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 | |
| Llama3.2 1B | — | — | — | 128,000 | |
| Llama3.2 3B | — | — | — | 128,000 | |
| Llama3.70b | — | — | — | 8,000 | |
| Llama3.8b | — | — | — | 8,000 | |
| Mistral 7B | — | — | — | 32,000 | |
| Mistral Large | — | — | — | 32,000 | |
| Mixtral 8×7B | — | — | — | 32,000 | |
| Reka Core | — | — | — | 32,000 | |
| Reka Flash | — | — | — | 100,000 | |
| Snowflake Arctic | — | — | — | 4,096 | |
| Snowflake Llama 3.1 405B | — | — | — | 8,000 |
embedding 2
| Model ↕ | Input / 1M ↕ | Output / 1M ↕ | Blended ↕ | Context ↕ | Caps |
|---|---|---|---|---|---|
| Snowflake Arctic Embed L v2.0 | $0.0700/M | — | — | 8,192 | |
| Snowflake Arctic Embed M v2.0 | $0.0700/M | — | — | 8,192 |
FAQ
How many Snowflake Cortex models are there?
37 Snowflake Cortex models are listed across 2 modalities on this page. 21 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?
Input pricing on Snowflake Cortex starts at $0.0700 per 1M tokens. Sort the table by price (or use the in-page filter at the top) to find the cheapest model that matches your capability requirements.
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.