Snowflake Gen AI Governance · Topic 10 of 15

Cortex Analyst Costs and Cortex AI Function Token Costs

Cortex Analyst bills per message and AI functions per token; see which functions bill input and output, how to minimize tokens and use AI_COUNT_TOKENS.

  • 4 min
In a nutshell
  • Analyst: per message, HTTP 200 only; warehouse separate; view CORTEX_ANALYST_USAGE_HISTORY.
  • AI functions: per token; embeddings and Cortex Guard bill input only.
  • AI_EXTRACT counts a page as 970 tokens; audio is 50 tokens per second.

What it is

Two Cortex features sit at opposite ends of the billing spectrum. Cortex Analyst bills per message. Cortex AI functions (AI_COMPLETE, AI_CLASSIFY, AI_EXTRACT and the rest) bill per token processed. The exam tests whether you can say which unit applies and which habits lower the bill.

Analyst questionone messagebilled perMessageHTTP 200 onlyAI function calltext and promptbilled perTokensinput and output

How it works

Cortex Analyst: per message

  • Credits are charged per message processed. Only successful responses (HTTP 200) count.
  • Token count does not change the price, except when Analyst is called through Cortex Agents, where it bills per token.
  • The warehouse that runs the generated SQL is billed separately.
  • Track it in SNOWFLAKE.ACCOUNT_USAGE.CORTEX_ANALYST_USAGE_HISTORY (columns include START_TIME, END_TIME, REQUEST_COUNT, CREDITS and USERNAME, aggregated hourly). Usage also appears in METERING_HISTORY under service type AI_SERVICES.
  • Cortex Analyst is not one of the per-user quota domains, so do not plan on quotas to cap it.

AI functions: per token

Snowflake Cortex AI functions incur compute cost based on tokens processed. A token is roughly four characters of text, varying by model. Rates are in credits per million tokens in the Snowflake Service Consumption Table.

Billing patternFunctions
Input and output tokensAI_COMPLETE, AI_CLASSIFY, AI_FILTER, AI_AGG, AI_SUMMARIZE, AI_TRANSLATE, AI_EXTRACT, AI_REDACT, and the older SUMMARIZE
Input tokens onlyAI_EMBED, AI_SIMILARITY, the EMBED_* functions, and Cortex Guard
Per pageAI_PARSE_DOCUMENT

Other billing facts:

  • Hidden prompt tokens. AI_CLASSIFY, AI_FILTER, AI_AGG, AI_SENTIMENT, AI_SUMMARIZE_AGG, TRANSLATE and similar functions add their own prompt, so billed tokens exceed your text.
  • AI_CLASSIFY labels, descriptions and examples are billed for every record, not once per call.
  • AI_EXTRACT counts each document page as 970 input tokens, and the responseFormat argument counts as input too.
  • Audio counts as 50 tokens per second.
  • Cortex Guard adds input token cost on top of AI_COMPLETE.
  • The legacy SNOWFLAKE.CORTEX versions bill the same way as their AI_* successors.

Minimizing tokens

HabitWhy it saves
Send only the needed textTokens in equal cost
Trim or chunk long documents and keep prompts shortInput is billed
Keep AI_CLASSIFY labels and descriptions shortThey repeat per row
Set max_tokens in AI_COMPLETE model_parametersCaps output (default is 4096)
Pick a smaller model for easy tasksSmaller models cost fewer credits per token
Use the purpose-built function (AI_CLASSIFY, AI_FILTER) instead of a free-form promptFewer tokens and tighter output
Filter rows in SQL before calling the functionFewer calls
Test on a sample with LIMITAvoid a full-table surprise

AI_COUNT_TOKENS

AI_COUNT_TOKENS is a helper function that counts the tokens a text would use before you run the real call. It incurs only the compute cost of running it, not the model cost. Use it on a sample to size a batch.

Warehouse note

A warehouse is still needed to run the query. Snowflake advises a warehouse no larger than MEDIUM, because a bigger one does not make the function faster and only adds cost.

Implications

Cost scales with rows times tokens per row. A table of 1 million rows with long text and a large model can cost far more than the same task done on a filtered sample with a small model. Long prompts repeat on every row, so shared instruction text is a fixed cost per row.

Exam tip

When a question asks how to reduce the cost of an AI function over a large table, the answer is almost always: shorten input and prompt, filter rows first, choose a smaller model, or cap output tokens.

Large tablefilter rowsFewer rowstrim textShorter inputsmall modelCheaper tokenscap outputmax_tokens

Common mistakes

Assuming message length changes Analyst price. It bills per message, except through agents.

Counting only your text. Added prompts and per-row labels add tokens.

Using a LARGE warehouse for AI queries. MEDIUM or smaller is advised.

Ignoring output tokens. Most generative functions bill output too.

Confusing AI_COUNT_TOKENS with a free model call. It only costs its own compute.

What to remember for the exam

  • Analyst: per message, HTTP 200 only; warehouse separate; view CORTEX_ANALYST_USAGE_HISTORY.
  • AI functions: per token; embeddings and Cortex Guard bill input only.
  • AI_EXTRACT counts a page as 970 tokens; audio is 50 tokens per second.
  • Lower cost by trimming input, filtering rows, small models and max_tokens.

Check yourself

  • How is Cortex Analyst billed?

    Per message processed, counting only successful HTTP 200 responses, with warehouse costs separate.

  • Which functions bill input tokens only?

    Embedding and similarity functions such as AI_EMBED and AI_SIMILARITY, plus Cortex Guard.

  • How do you estimate tokens before running a batch?

    Use AI_COUNT_TOKENS, which costs only its own compute.

Topic 10 of 15 in Snowflake Gen AI Governance

Test yourself on Snowflake Gen AI Governance

The full Snowflake GES-C02 question bank has 585 questions, with timed practice exams and an explanation for every answer.

This study guide is independent and is not affiliated with, endorsed by, or sponsored by Snowflake. Vendor names, certification names and exam codes are trademarks of their respective owners and are used for identification only.