API pricing

Snowflake Pricing

Snowflake charges between $0.240 and $25.00 per 1 million output tokens, depending on the model. Llama3.1 8B is the cheapest at $0.240/1M output and $0.240/1M input; Claude 4 Opus is the most expensive at $25.00/1M output. The largest context window is 5.0M tokens (OpenAI GPT 5 Nano). Prices are USD, current as of July 20, 2026.

Last updated · synced weekly from the upstream model catalog

Cheapest input

$0.150/1M

OpenAI GPT 5 Nano

Cheapest output

$0.240/1M

Llama3.1 8B

Longest context

5.0M

OpenAI GPT 5 Nano

Models priced

19

Avg $7.41/1M output

Pricing by model

All prices in USD per 1 million tokens. All 19 priced models, cheapest first.

ModelInput / 1MOutput / 1MContext
Llama3.1 8B$0.240$0.240128K
OpenAI GPT 5 Nano$0.150$0.6005.0M
Llama3.1 70B$0.720$0.720128K
Llama3.3 70B$0.720$0.720128K
Snowflake Llama 3.3 70B$0.720$0.720128K
Llama4 Maverick$0.240$0.970128K
Llama3.1 405B$1.20$1.20128K
OpenAI GPT 5 Mini$0.300$1.201.0M
Claude Haiku 4.5$1.00$5.00200K
DeepSeek R1$1.35$5.40128K
Mistral Large2$2.00$6.00128K
OpenAI GPT 4.1$2.00$8.00300K
OpenAI GPT 5$1.25$10.00300K
Claude 3.5 Sonnet$3.00$15.00200K
Claude 3.7 Sonnet$3.00$15.00200K
Claude 4 Sonnet$3.00$15.00200K
Claude Sonnet 4.5$3.00$15.00200K
Claude Sonnet 4.6$3.00$15.00200K
Claude 4 Opus$5.00$25.00200K

Frequently asked questions

How much does Snowflake cost per 1M tokens?

Snowflake pricing ranges from $0.240 to $25.00 per 1 million output tokens across 19 models. Input tokens are cheaper than output on every model. Rates current as of July 20, 2026.

What is the cheapest Snowflake model?

Llama3.1 8B is the cheapest Snowflake model on output tokens at $0.240 per 1M, while OpenAI GPT 5 Nano is cheapest on input at $0.150 per 1M. Which wins for you depends on your input-to-output ratio.

What is the largest Snowflake context window?

OpenAI GPT 5 Nano has the largest context window in the Snowflake catalog at 5.0M input tokens, with up to 16K output tokens per response.

How do I calculate my actual Snowflake bill?

Multiply your input tokens by the input rate and your output tokens by the output rate, both per million, then add retries and any conversation history resent on each turn. Calcaas does this against your real usage pattern and shows the margin left at your price point.

Other providers

What will this actually cost you?

Per-token rates only tell you half the story. Calcaas multiplies them by your real usage — prompt size, response length, retries and conversation history — then shows the margin left at your price point.

Open the free cost calculator