This guide covers every governance surface of Snowflake Cortex AI: audit logging, inference region controls, RBAC, model-level access, EU data residency, Cortex Analyst fallback behavior, AI observability, REST API audit coverage, and the complete model catalog with hosting infrastructure.
Contents#
- Audit Logging & Usage Views
- Inference Region Tracking & Control
- RBAC & Access Governance for Cortex AI
- Model-Level RBAC
- EU-Only Inference: Impact Across Cortex Services
- Cortex Analyst: Fallback Model Chain & RBAC Interaction
- AI Observability & Tracing
- REST API Audit Coverage
- Model Catalog: Hosting Infrastructure & Data Sovereignty
- Summary Matrix
1. Audit Logging & Usage Views#
Snowflake provides multiple ACCOUNT_USAGE views that cover every surface area of Cortex AI inference. All views are in the SNOWFLAKE.ACCOUNT_USAGE schema and require the SNOWFLAKE database role or ACCOUNTADMIN/SYSADMIN.
1.1 CORTEX_AISQL_USAGE_HISTORY (Primary – GA Dec 2025)#
The canonical replacement for the older CORTEX_FUNCTIONS_USAGE_HISTORY and CORTEX_FUNCTIONS_QUERY_USAGE_HISTORY views. Covers all Cortex AI SQL functions invoked in queries.
| Column | Type | Description |
|---|---|---|
USAGE_TIME | TIMESTAMP_LTZ | Hour the query completed (not started) |
MODEL_NAME | TEXT | Model used (e.g., llama3.1-70b, claude-3-5-sonnet) |
FUNCTION_NAME | TEXT | AI function called (e.g., AI_COMPLETE, AI_TRANSLATE) |
TOKEN_CREDITS | NUMBER | Credits billed for this function/model/query combo |
TOKENS | NUMBER | Total tokens processed |
TOKEN_CREDITS_GRANULAR | OBJECT | Per-type breakdown (input/output tokens) |
TOKENS_GRANULAR | OBJECT | Per-type token count breakdown |
QUERY_ID | TEXT | Query ID – join to QUERY_HISTORY for full context |
QUERY_TAG | TEXT | Session QUERY_TAG at invocation time |
USER_ID | TEXT | Internal user identifier |
WAREHOUSE_ID | TEXT | Virtual warehouse used |
Coverage starts: November 17, 2025. Data is retained for 365 days.
Example – usage by model and user over 30 days:
SELECT
DATE_TRUNC('day', h.USAGE_TIME) AS usage_date,
u.NAME AS user_name,
h.FUNCTION_NAME,
h.MODEL_NAME,
SUM(h.TOKEN_CREDITS) AS total_credits,
SUM(h.TOKENS) AS total_tokens
FROM SNOWFLAKE.ACCOUNT_USAGE.CORTEX_AISQL_USAGE_HISTORY h
JOIN SNOWFLAKE.ACCOUNT_USAGE.USERS u ON h.USER_ID = u.USER_ID
WHERE h.USAGE_TIME >= DATEADD('day', -30, CURRENT_TIMESTAMP())
GROUP BY 1, 2, 3, 4
ORDER BY usage_date DESC, total_credits DESC;1.2 CORTEX_AI_FUNCTIONS_USAGE_HISTORY (GA Jan 2026)#
A complementary view introduced January 5, 2026 that adds real-time in-flight query tracking and enriched role/tag attribution.
| Additional Column | Description |
|---|---|
START_TIME / END_TIME | Aggregation window (1-hour buckets) |
ROLE_NAMES | ARRAY – primary active role is index 0 |
IS_COMPLETED | BOOLEAN – tracks still-running queries |
CREDITS | Credits at the aggregation window level |
Key difference from CORTEX_AISQL_USAGE_HISTORY: Captures running queries updated every ~30 minutes (1-hour SLA). Useful for runaway query detection.
Notable columns for governance: ROLE_NAMES lets you attribute usage to specific roles – critical for chargeback and least-privilege audits.
Coverage starts: January 5, 2026. USER_ID, QUERY_TAG, and ROLE_NAMES available from February 16, 2026 onward.
1.3 CORTEX_ANALYST_USAGE_HISTORY#
Tracks usage for the Cortex Analyst REST API (text-to-SQL natural language interface).
| Column | Description |
|---|---|
START_TIME / END_TIME | Request received / response sent |
REQUEST_COUNT | Number of messages sent to Cortex Analyst |
CREDITS | Credits billed (per-message pricing, not per-token) |
USERNAME | Username from the authenticated session |
Note: Cortex Analyst billing is per-message (not per-token). Token count only affects cost when invoked via Cortex Agents. Data retained for 365 days.
1.4 METERING_HISTORY – AI_SERVICES Service Type#
All Cortex AI inference also appears in the standard SNOWFLAKE.ACCOUNT_USAGE.METERING_HISTORY view under SERVICE_TYPE = 'AI_SERVICES'. Useful for consolidated credit reporting alongside warehouse and storage costs.
SELECT SERVICE_TYPE, DATE_TRUNC('day', START_TIME) AS usage_date, SUM(CREDITS_USED)
FROM SNOWFLAKE.ACCOUNT_USAGE.METERING_HISTORY
WHERE SERVICE_TYPE = 'AI_SERVICES'
AND START_TIME >= DATEADD('month', -3, CURRENT_TIMESTAMP())
GROUP BY 1, 2
ORDER BY 2 DESC;1.5 QUERY_HISTORY – Full SQL Context#
All Cortex AI Function invocations inside SQL queries also appear in SNOWFLAKE.ACCOUNT_USAGE.QUERY_HISTORY. Join on QUERY_ID to get:
- Full SQL text (
QUERY_TEXT) - Session role and user
- Warehouse, database, schema context
- Execution status and duration
- Bytes scanned / rows produced
SELECT q.QUERY_TEXT, q.USER_NAME, q.ROLE_NAME, q.WAREHOUSE_NAME, q.EXECUTION_STATUS
FROM SNOWFLAKE.ACCOUNT_USAGE.QUERY_HISTORY q
JOIN SNOWFLAKE.ACCOUNT_USAGE.CORTEX_AISQL_USAGE_HISTORY c ON q.QUERY_ID = c.QUERY_ID
WHERE c.USAGE_TIME >= DATEADD('day', -7, CURRENT_TIMESTAMP());1.6 Cortex Agent Logs – SNOWFLAKE.LOCAL.AI_OBSERVABILITY_EVENTS#
Cortex Agents (including those powering Snowflake Intelligence) log detailed execution traces to the event table SNOWFLAKE.LOCAL.AI_OBSERVABILITY_EVENTS. Entries are immutable (cannot be modified; only AI_OBSERVABILITY_ADMIN can delete).
Logged information includes:
- Full conversation history per thread
- Execution spans: LLM planning, tool selection, tool execution, SQL execution, chart generation
- Inputs and outputs at each span
- User feedback (thumbs up/down per Agent response)
Access control for monitoring:
-- Grant monitoring access to a specific agent
GRANT MONITOR ON AGENT my_agent TO ROLE agent_monitoring_user_role;
GRANT DATABASE ROLE SNOWFLAKE.CORTEX_USER TO ROLE agent_monitoring_user_role;
-- Grant forward-looking access to all agents in a schema
GRANT MONITOR ON FUTURE AGENTS IN SCHEMA mydb.myschema TO ROLE agent_monitoring_user_role;2. Inference Region Tracking & Control#
2.1 The CORTEX_ENABLED_CROSS_REGION Parameter#
This account-level parameter governs where inference requests can be routed when the requested model is not available in the account’s native region.
| Value | Behavior |
|---|---|
DISABLED (default for most accounts) | Inference only in account’s native region |
ANY_REGION | Route to any supported Snowflake region (default for new accounts in new orgs, commercial, created after Mar 9 2026) |
AWS_US | Route to AWS US regions only |
AWS_EU | Route to AWS EU regions only |
AWS_US,AWS_EU | Comma-delimited list of allowed zone groups |
Only ACCOUNTADMIN can set this parameter. It cannot be set at user or session level.
-- Restrict to EU-only cross-region (data stays within AWS EU network)
ALTER ACCOUNT SET CORTEX_ENABLED_CROSS_REGION = 'AWS_EU';
-- Lock to home region only (strictest data residency)
ALTER ACCOUNT SET CORTEX_ENABLED_CROSS_REGION = 'DISABLED';
-- Check current setting
SHOW PARAMETERS LIKE 'CORTEX_ENABLED_CROSS_REGION' IN ACCOUNT;2.2 What Gets Audited for Cross-Region#
There is no dedicated ACCOUNT_USAGE view column that records which specific region processed a given inference request. Credits are always attributed to the requesting region regardless of where inference ran.
The available signals for inference region compliance are:
| Signal | Where | What It Provides |
|---|---|---|
CORTEX_ENABLED_CROSS_REGION setting changes | QUERY_HISTORY (ALTER ACCOUNT SET) | Audit trail for policy changes |
| Model name logged per query | CORTEX_AISQL_USAGE_HISTORY.MODEL_NAME | Cross-reference against regional model availability to infer if cross-region routing was required |
response_metadata.model_names in Cortex Analyst REST API responses | Application-level logging | Per-request ground truth of which model ran – key for detecting when a cross-region model was selected |
"model" field in Cortex LLM REST API completion response body | Application-level logging | Per-request model confirmation; shows actual resolved model if aliasing occurred |
CORTEX_AISQL_USAGE_HISTORY role attribution | ROLE_NAMES column (available from Feb 16, 2026) | Verify requests came from expected roles with expected model access |
The REST API response fields are the most granular per-request audit mechanism available. See Section 8.1 for full details.
2.3 Data Residency Guarantees During Cross-Region#
| Scenario | Data Path |
|---|---|
| Same cloud provider (AWS to AWS) | Stays on AWS global backbone plus snowflake uses mTLS for the inference calls |
| Same cloud provider (Azure to Azure) | Stays entirely on Azure global network |
| Cross-cloud provider | Traverses public internet using mTLS |
| SnowGov regions | Cross-region inference is not supported – requests stay in-region |
| US Commercial Gov | Stays within FIPS-validated infrastructure (AWS Bedrock FIPS endpoints) when AWS_US is set |
Prompt and output data is never stored or cached during cross-region inference.
3. RBAC & Access Governance for Cortex AI#
3.1 Database Roles – The Foundation#
Snowflake uses three built-in database roles in the SNOWFLAKE database to control Cortex AI access:
| Database Role | Access Granted |
|---|---|
SNOWFLAKE.CORTEX_USER | All Cortex AI features (LLM functions, Analyst, Search, Agents) |
SNOWFLAKE.CORTEX_ANALYST_USER | Cortex Analyst only (scoped access) |
SNOWFLAKE.CORTEX_ADMIN | Admin-level Cortex capabilities |
Critical default: SNOWFLAKE.CORTEX_USER is granted to the PUBLIC role by default, meaning all users can access all Cortex AI features unless explicitly revoked.
-- Check current grants on CORTEX_USER
SHOW GRANTS ON DATABASE ROLE SNOWFLAKE.CORTEX_USER;
-- Revoke from PUBLIC to enforce explicit access control
USE ROLE ACCOUNTADMIN;
REVOKE DATABASE ROLE SNOWFLAKE.CORTEX_USER FROM ROLE PUBLIC;
-- Grant only Cortex Analyst access to a specific role
GRANT DATABASE ROLE SNOWFLAKE.CORTEX_ANALYST_USER TO ROLE analyst_team_role;3.2 Scoping Access to Cortex Analyst Only#
If users should only be able to use Cortex Analyst (not arbitrary LLM functions), use CORTEX_ANALYST_USER instead of CORTEX_USER:
USE ROLE ACCOUNTADMIN;
-- Remove broad access first
REVOKE DATABASE ROLE SNOWFLAKE.CORTEX_USER FROM ROLE analyst;
-- Grant narrow Analyst-only access
GRANT DATABASE ROLE SNOWFLAKE.CORTEX_ANALYST_USER TO ROLE analyst;3.3 Per-User Spending Limits via RBAC#
Access to Cortex features can be revoked programmatically to enforce per-user monthly credit budgets using CORTEX_AI_FUNCTIONS_USAGE_HISTORY:
-- When a user exceeds their monthly limit, revoke their AI role
REVOKE ROLE AI_FUNCTIONS_USER_ROLE FROM USER exceeded_user;
-- Reinstate at the start of next month via a Snowflake Task4. Model-Level RBAC#
4.1 Overview (GA – April 2025)#
Beyond feature-level access, Snowflake supports model-level RBAC using application roles. Each supported LLM has a corresponding role in the SNOWFLAKE database:
SNOWFLAKE."CORTEX-MODEL-ROLE-<MODEL-SLUG>"Examples:
SNOWFLAKE."CORTEX-MODEL-ROLE-CLAUDE-SONNET"SNOWFLAKE."CORTEX-MODEL-ROLE-LLAMA3-1-70B"SNOWFLAKE."CORTEX-MODEL-ROLE-ARCTIC-TRANSLATE"SNOWFLAKE."CORTEX-MODEL-ROLE-MISTRAL-LARGE2"
4.2 CORTEX_MODELS_ALLOWLIST Parameter#
A complementary account-level parameter that provides allowlist/blocklist-style control:
| Setting | Behavior |
|---|---|
'All' (default) | All models are accessible to users with CORTEX_USER |
'None' | No models allowed via allowlist; RBAC roles are the only path |
'llama3.1-70b,mistral-large2' | Only listed models are accessible to all users |
-- Check current allowlist
SHOW PARAMETERS LIKE 'CORTEX_MODELS_ALLOWLIST' IN ACCOUNT;
-- Restrict to specific models (allowlist approach)
ALTER ACCOUNT SET CORTEX_MODELS_ALLOWLIST = 'llama3.1-70b,mistral-large2,arctic-translate';
-- Switch to pure RBAC mode (no allowlist)
ALTER ACCOUNT SET CORTEX_MODELS_ALLOWLIST = 'None';4.3 Enforcement Logic (BCR-2220 – 2026_02 Bundle)#
As of the 2026_02 behavior change bundle (BCR-2220), model RBAC and CORTEX_MODELS_ALLOWLIST are enforced across all Cortex AI Functions, not just AI_COMPLETE. The enforcement order is:
- Check model RBAC (application role) – if role grants access, ALLOW
- Check
CORTEX_MODELS_ALLOWLIST– if model is listed (or ='All'), ALLOW - Otherwise – FAIL with model-authorization error
Functions now fully enforcing model RBAC (newly added in BCR-2220): AI_TRANSCRIBE, AI_EXTRACT, AI_SENTIMENT, AI_TRANSLATE, CLASSIFY_TEXT, SUMMARIZE, EXTRACT_ANSWER, AI_PARSE_DOCUMENT, AI_REDACT
Functions that already enforced RBAC (pre-BCR-2220): AI_COMPLETE / COMPLETE, AI_CLASSIFY, AI_FILTER, AI_AGG, AI_SUMMARIZE_AGG
To prepare for or audit BCR-2220 exposure:
-- Check which affected functions are in use
SELECT DISTINCT FUNCTION_NAME
FROM SNOWFLAKE.ACCOUNT_USAGE.CORTEX_AISQL_USAGE_HISTORY
WHERE USAGE_TIME >= DATEADD('day', -90, CURRENT_TIMESTAMP())
AND FUNCTION_NAME IN (
'AI_TRANSCRIBE', 'TRANSCRIBE', 'AI_EXTRACT', 'AI_SENTIMENT',
'SENTIMENT', 'ENTITY_SENTIMENT', 'AI_TRANSLATE', 'TRANSLATE',
'CLASSIFY_TEXT', 'SUMMARIZE', 'EXTRACT_ANSWER',
'AI_PARSE_DOCUMENT', 'PARSE_DOCUMENT', 'AI_REDACT'
)
ORDER BY FUNCTION_NAME;4.4 Function-to-Model Alias Mapping#
Managed functions (non-AI_COMPLETE) use internal model aliases confirmed via BCR-2220 documentation. These must be explicitly permitted if CORTEX_MODELS_ALLOWLIST is not 'All':
| Function | Model Alias | Confirmed? |
|---|---|---|
AI_TRANSLATE / TRANSLATE | arctic-translate | Yes – BCR-2220 |
AI_TRANSCRIBE / TRANSCRIBE | arctic-transcribe | Yes – BCR-2220 |
AI_EXTRACT / EXTRACT_ANSWER | arctic-extract / arctic-extract-answer | Yes – BCR-2220 + docs |
AI_PARSE_DOCUMENT / PARSE_DOCUMENT | arctic-parse-document | Yes – BCR-2220 |
AI_SENTIMENT / SENTIMENT / ENTITY_SENTIMENT | arctic-sentiment | Yes – BCR-2220 |
CLASSIFY_TEXT, AI_REDACT | llama3.1-70b | Yes – BCR-2220 |
SUMMARIZE | mistral-7b | Yes – BCR-2220 |
AI_CLASSIFY, AI_FILTER, AI_AGG, AI_SUMMARIZE_AGG | Not disclosed – “Snowflake managed model” | Model identity not published |
Important:
AI_CLASSIFY,AI_FILTER,AI_AGG, andAI_SUMMARIZE_AGGalready enforced model RBAC before BCR-2220. Their underlying model is documented only as “Snowflake managed model” – Snowflake does not publish the specific model identifier. IfCORTEX_MODELS_ALLOWLISTis set to anything other than'All', these functions may fail unless the managed model is implicitly permitted. See Section 9.3 for detail.
5. EU-Only Inference: Impact Across Cortex Services#
5.1 Available EU Regions (Native)#
Snowflake Cortex AI is natively available in the following EU regions:
- AWS eu-central-1 (Frankfurt)
- AWS eu-west-1 (Ireland)
- Azure West Europe (Netherlands)
For accounts in other EU regions (e.g., AWS eu-west-3 Paris, Azure North Europe), cross-region inference must be enabled to access models not natively supported there.
5.2 Restricting to EU-Only Inference#
For strict EU data residency (e.g., GDPR compliance requirements where data must stay in the EU):
-- Allow cross-region only within AWS EU zones
ALTER ACCOUNT SET CORTEX_ENABLED_CROSS_REGION = 'AWS_EU';
-- OR lock entirely to home region (no cross-region at all)
ALTER ACCOUNT SET CORTEX_ENABLED_CROSS_REGION = 'DISABLED';5.3 Model Availability Impact by Service#
When CORTEX_ENABLED_CROSS_REGION = 'DISABLED' or = 'AWS_EU', only models natively available in the account’s region (or within the EU zone) can be used. Models hosted exclusively in US regions may not be accessible.
| Cortex Service | EU Restriction Impact |
|---|---|
Cortex AI Functions (AI_COMPLETE etc.) | Only EU-available models can be used; calls to US-only models fail with “model not available in region” error |
| Cortex Analyst | Model fallback chain may be reduced (see Section 6); requests fail if no accessible model remains |
| Cortex Agents | Agent orchestration that calls restricted models will fail; Snowflake Intelligence affected if default models are EU-unavailable |
| Cortex Search | Cross-region inference is not supported for Cortex Search – it is always in-region |
| AI Observability | LLM judges run via AI_COMPLETE – restricted model sets affect which judges can be used for evaluation |
6. Cortex Analyst: Fallback Model Chain & RBAC Interaction#
6.1 Model Selection Behavior#
Cortex Analyst automatically selects the best available model per request. Users cannot specify a model directly. Snowflake evaluates the following factors in combination:
- Models natively available in the account’s region
- The account’s
CORTEX_ENABLED_CROSS_REGIONsetting - Any model-level RBAC restrictions on the calling role
6.2 Cortex Analyst Model Fallback Priority (Current as of April 2026)#
Cortex Analyst selects the highest-ranked model the calling role has access to:
| Priority | Model |
|---|---|
| 1 | Anthropic Claude Sonnet 4 |
| 2 | Anthropic Claude Sonnet 3.7 |
| 3 | Anthropic Claude Sonnet 3.5 |
| 4 | OpenAI GPT 4.1 |
| 5 | Arctic Text2SQL R1.5 (with thinking) |
| 6 | Mistral Large 2 + Llama 3.1 70b (combination) |
Warning: Snowflake may update this model selection chain over time to take advantage of advances in model capability. This can cause result variance across time if model availability or RBAC changes.
6.3 RBAC + Region = Failure Risk#
The three controls multiply together. The following combinations can cause complete Cortex Analyst failures:
| Scenario | Effect |
|---|---|
EU account + DISABLED cross-region + Top models (Claude/GPT) not in EU | Falls back to Arctic R1.5 or Mistral/Llama combo |
EU account + All Anthropic/OpenAI models blocked by CORTEX_MODELS_ALLOWLIST | Falls back to Arctic R1.5 or Mistral/Llama |
| EU account + Model RBAC revokes all models the calling role can use | Request fails entirely with model-authorization error |
CORTEX_MODELS_ALLOWLIST = 'None' + No model application roles granted | Every Cortex Analyst request fails |
Recommended governance posture for EU deployments:
-- Ensure at minimum the Arctic and Mistral-family models are accessible for fallback
ALTER ACCOUNT SET CORTEX_MODELS_ALLOWLIST =
'llama3.1-70b,mistral-large2,arctic-text2sql-r1,arctic-translate,arctic-extract,arctic-sentiment';
-- OR grant model roles explicitly
GRANT APPLICATION ROLE SNOWFLAKE."CORTEX-MODEL-ROLE-MISTRAL-LARGE2" TO ROLE analyst_role;
GRANT APPLICATION ROLE SNOWFLAKE."CORTEX-MODEL-ROLE-LLAMA3-1-70B" TO ROLE analyst_role;Important: Model-level restrictions apply across all Cortex features – it is not possible to restrict a model only in Cortex Analyst while keeping it accessible in
AI_COMPLETE.
6.4 Controlling Consistency of Results#
Different models produce different SQL and natural language responses. For reproducible, consistent Cortex Analyst results in regulated environments:
- Pin
CORTEX_ENABLED_CROSS_REGIONto a fixed zone - Use
CORTEX_MODELS_ALLOWLISTor RBAC roles to maintain a fixed model set - Monitor
CORTEX_ANALYST_USAGE_HISTORYfor request counts and credit patterns
7. AI Observability & Tracing#
7.1 TruLens-Based Evaluation#
Snowflake AI Observability (GA) provides LLM-as-a-judge evaluation for generative AI applications, powered by TruLens. This enables:
- Systematic benchmarking (accuracy, latency, cost)
- Side-by-side comparison of models, prompts, inference configs
- Step-by-step tracing (prompt -> retrieval -> tool use -> response)
Required privileges:
CORTEX_USERdatabase roleCREATE EXTERNAL AGENTon the schemaCREATE TASKandEXECUTE TASKglobal privilege
Application representation: Each AI application is represented as an EXTERNAL AGENT object in Snowflake, which governs access to its traces and evaluation results.
7.2 Trace Storage#
Execution traces and evaluation results are stored in the Snowflake event table for the account. Evaluation runs themselves invoke SNOWFLAKE.CORTEX.COMPLETE – meaning evaluation costs appear in CORTEX_AISQL_USAGE_HISTORY and are subject to the same model RBAC constraints.
8. REST API Audit Coverage#
Cortex AI services expose REST APIs that can be called from outside Snowflake. Here is how each is covered in the audit layer:
| REST API | Audit Coverage |
|---|---|
Cortex Analyst API (/api/v2/cortex/analyst/message) | CORTEX_ANALYST_USAGE_HISTORY (per-message billing + username) |
Cortex Agent API (/api/v2/cortex/agents) | SNOWFLAKE.LOCAL.AI_OBSERVABILITY_EVENTS (full trace logging) |
Cortex LLM REST API (/api/v2/cortex/inference:complete, /api/v2/cortex/v1/chat/completions, /api/v2/cortex/v1/messages) | CORTEX_AISQL_USAGE_HISTORY / CORTEX_AI_FUNCTIONS_USAGE_HISTORY |
| Cortex Search (via REST) | CORTEX_SEARCH_SERVING_USAGE_HISTORY; SQL invocations also in QUERY_HISTORY |
Authentication: All REST API requests require an authorization token (OAuth, key-pair JWT, or PAT). The authenticated username/user ID flows through to all usage history views.
8.1 Per-Request Inference Model Signals in REST API Responses#
This is a critical capability for auditing which model actually ran for a given request – especially relevant when Cortex Analyst’s automatic fallback chain or cross-region inference is in play.
Cortex LLM REST API – "model" field in response body
Every completion response includes a "model" field that reflects the actual model that processed the request – not necessarily the one you requested, if aliasing or selection occurred:
{
"choices": [
{ "messages": "Your response here" }
],
"created": 1714497970,
"model": "claude-4-sonnet",
"usage": {
"completion_tokens": 65,
"prompt_tokens": 17,
"total_tokens": 82
}
}Use this field to verify:
- Which model in a multi-model setup was actually invoked
- Whether cross-region inference resulted in a different model being selected
- Compliance with RBAC restrictions (confirm a restricted model was not used)
Streaming responses deliver the same information via the response_metadata server-sent event emitted at the end of the stream.
Cortex Analyst REST API – response_metadata.model_names
The Cortex Analyst API response includes a response_metadata object that directly exposes which model(s) were selected for that request. This is the key audit field for verifying which step of the fallback chain fired:
{
"request_id": "75d343ee-699c-483f-83a1-e314609fb563",
"message": {
"role": "analyst",
"content": [
{ "type": "text", "text": "We interpreted your question as ..." },
{ "type": "sql", "statement": "SELECT * FROM table" }
]
},
"response_metadata": {
"model_names": ["claude-3-5-sonnet"],
"question_category": "CLEAR_SQL",
"cortex_search_retrieval": []
}
}response_metadata Field | What It Tells You |
|---|---|
model_names | Array of model IDs actually used. If Analyst used multiple models (e.g., one for planning, one for SQL), all appear here. |
question_category | How Analyst classified the question: CLEAR_SQL, AMBIGUOUS, etc. Useful for quality monitoring. |
cortex_search_retrieval | Details of any Cortex Search service calls made during the request. |
In streaming mode, response_metadata is delivered as a distinct server-sent event:
event: response_metadata
data: { "model_names": ["claude-4-sonnet"], "question_category": "CLEAR_SQL" }
event: doneGovernance use cases for response_metadata.model_names:
- EU compliance audit: Log every Analyst response and alert if
model_namescontainsclaude-*oropenai-*on an account configured to use only native models – this indicates cross-region inference fired or RBAC was misconfigured - Fallback chain monitoring: Track when Analyst degrades from Claude Sonnet 4 to lower-priority models – a signal of RBAC over-restriction or regional model unavailability
- Result reproducibility:
model_namesin the response is the ground truth for which model generated a given SQL – critical for debugging result variance
8.2 Capturing response_metadata for Audit Logging#
Since CORTEX_ANALYST_USAGE_HISTORY does not currently store the resolved model name (only request counts and credits), the only way to get per-request model attribution for Cortex Analyst is from the REST API response body itself. Applications calling the Analyst REST API should log response_metadata.model_names alongside the request_id:
import requests
import json
response = requests.post(
f"https://{account}.snowflakecomputing.com/api/v2/cortex/analyst/message",
headers={
"Authorization": f"Bearer {token}",
"Content-Type": "application/json",
},
json={
"messages": [
{"role": "user", "content": [{"type": "text", "text": question}]}
],
"semantic_model_file": "@db.schema.stage/model.yaml",
},
)
body = response.json()
request_id = body.get("request_id")
models_used = body.get("response_metadata", {}).get("model_names", [])
question_cat = body.get("response_metadata", {}).get("question_category")
# Log for audit trail
print(f"request_id={request_id} models={models_used} category={question_cat}")The request_id returned in the response is also the correlation key if Snowflake adds per-request model resolution to CORTEX_ANALYST_USAGE_HISTORY in future.
9. Model Catalog: Hosting Infrastructure & Data Sovereignty#
9.1 Hosting Architecture Overview#
Snowflake’s official position – and the contractually correct statement – is that all models available through Cortex AI run within the Snowflake security perimeter and governance boundary. As the Cortex REST API documentation states: “All inference runs within the Snowflake perimeter, so your data remains secure and within your governance boundary.” This applies uniformly to every model in the catalog, regardless of the underlying compute tier.
The underlying compute infrastructure varies by model vendor, but in all cases Snowflake manages the security envelope, authentication, audit, and data handling obligations:
| Infrastructure Tier | Models | Notes |
|---|---|---|
| Snowflake-Native GPU Clusters | Meta Llama family, Mistral family, DeepSeek R1, Snowflake Arctic, SwiftKV-optimized variants | Inference runs on hardware Snowflake owns and operates. |
| AWS Bedrock (within Snowflake’s perimeter) | Anthropic Claude family | Backed by Snowflake’s $200M strategic partnership with Anthropic. Inference is mediated through Snowflake’s governance layer on AWS. |
| Azure AI Foundry / Azure OpenAI (within Snowflake’s perimeter) | OpenAI GPT and o-series family | OpenAI’s primary cloud infrastructure is Azure. Snowflake accesses these via Azure AI Foundry, fully within the Snowflake governance envelope. |
The distinction between tiers matters primarily for region availability – not governance. Anthropic and OpenAI models are only available natively in the specific regions where AWS Bedrock / Azure AI Foundry host them. For EU accounts, this means cross-region inference may be required to reach Claude or GPT models even though data never escapes Snowflake’s governance boundary.
9.2 Complete Model Catalog – AI_COMPLETE / COMPLETE (as of April 2026)#
Anthropic – Claude Family (via AWS Bedrock)#
| Model ID | Generation | Context Window | Notes |
|---|---|---|---|
claude-4-opus | Claude 4 | 200K | Preview. Best-in-class coding & long-horizon agentic tasks. |
claude-4-sonnet | Claude 4 | 200K | GA. Default for Cortex Analyst (top priority). |
claude-3-7-sonnet | Claude 3.7 | 200K | GA. Extended thinking with tool use. Analyst fallback #2. |
claude-3-5-sonnet | Claude 3.5 | 200K | GA. Strong accuracy/latency balance. Analyst fallback #3. |
claude-haiku-4-5 | Claude 4 | 200K | Fast/lightweight Haiku variant. |
claude-sonnet-4-6 | Claude 4 | 200K | Latest Sonnet point release. |
Data flow: Request metadata + prompt -> Snowflake perimeter -> Anthropic inference on AWS Bedrock -> response back through Snowflake. EU impact: AWS Bedrock availability in EU regions determines whether these models are natively accessible from EU Snowflake accounts.
OpenAI – GPT & o-Series Family (via Azure AI Foundry / Azure OpenAI)#
| Model ID | Series | Context Window | Notes |
|---|---|---|---|
openai-gpt-4.1 | GPT-4.1 | 128K | GA. Cortex Analyst fallback #4. |
openai-gpt-5 | GPT-5 | TBD | Full GPT-5 flagship model. |
openai-gpt-5-chat | GPT-5 | TBD | Chat-optimized variant. |
openai-gpt-5-mini | GPT-5 | TBD | Efficient mid-tier variant. |
openai-gpt-5-nano | GPT-5 | TBD | Smallest/fastest variant. |
openai-gpt-5.1 | GPT-5.1 | TBD | Point release. |
openai-o4-mini | o4 | 128K | Reasoning-optimized; strong at STEM tasks. |
Data flow: Request metadata + prompt -> Snowflake perimeter -> Azure AI Foundry / Azure OpenAI -> response back through Snowflake.
EU impact: Azure OpenAI EU region availability determines native access. CORTEX_ENABLED_CROSS_REGION = 'AZURE_EU' routes to Azure EU regions.
Meta – Llama Family (Snowflake-Native GPU Infrastructure)#
| Model ID | Params | Context Window | Notes |
|---|---|---|---|
llama4-maverick | ~400B MoE | 128K | Latest Llama 4. Multimodal-capable. |
llama4-scout | ~109B MoE | 128K | Efficient MoE variant. |
llama3.1-405b | 405B | 128K | State-of-the-art open model. |
llama3.1-70b | 70B | 128K | Strong general-purpose; Analyst combo model. |
llama3.1-8b | 8B | 128K | Fast, lightweight. |
llama3.3-70b | 70B | 128K | Improved 70B benchmarks. |
llama3-70b | 70B | 8K | Legacy 70B. Still supported. |
llama3-8b | 8B | 8K | Legacy 8B. Still supported. |
Data flow: Entirely within Snowflake’s own GPU infrastructure.
EU impact: Natively available in EU Snowflake regions. EU accounts with DISABLED cross-region can still use all Llama models.
Snowflake – Proprietary & SwiftKV-Optimized Models (Snowflake-Native)#
| Model ID | Base | Notes |
|---|---|---|
snowflake-arctic | Snowflake Arctic | Snowflake’s own MoE model; optimized for enterprise SQL and data tasks. 4K context. |
snowflake-llama-3.1-405b | Llama 3.1 405B | SwiftKV-optimized: up to 75% inference cost reduction with minimal accuracy loss. |
snowflake-llama-3.3-70b | Llama 3.3 70B | SwiftKV-optimized; higher throughput, lower cost. |
Also used internally:
arctic-text2sql-r1– Arctic Text2SQL R1.5 with thinking (Cortex Analyst fallback #5)arctic-translate,arctic-extract,arctic-sentiment,arctic-parse-document,arctic-extract-answer,arctic-transcribe– Managed function model aliases
Data flow: Entirely within Snowflake’s own GPU infrastructure. EU impact: Natively available in EU regions. SwiftKV models recommended for cost-sensitive EU deployments.
Mistral AI – Mistral Family (Snowflake-Native GPU Infrastructure)#
| Model ID | Params | Context Window | Notes |
|---|---|---|---|
mistral-large2 | ~123B | 128K | Flagship Mistral; Analyst combo model. Strong multilingual. |
mistral-large | ~123B | 32K | Legacy large model. |
mixtral-8x7b | 8x7B MoE | 32K | Fast MoE; good for text gen, classification. |
mistral-7b | 7B | 32K | Lightest/fastest; used internally by SUMMARIZE. |
Data flow: Entirely within Snowflake’s own GPU infrastructure. EU impact: Mistral is a French AI company – all Mistral models are natively available in EU Snowflake regions with no cross-region inference required.
DeepSeek – Reasoning Family (Snowflake-Native GPU Infrastructure)#
| Model ID | Notes |
|---|---|
deepseek-r1 | Open-source reasoning model with chain-of-thought. Strong at math, code, and structured reasoning. |
Data flow: Hosted on Snowflake’s native GPU infrastructure (open-source weights). EU impact: Natively hosted; available in EU regions. Note: DeepSeek is a Chinese AI lab – enterprises with geopolitical data concerns should be aware, though inference runs entirely on Snowflake’s infrastructure.
9.3 Managed Function Model Aliases#
The task-specific AI Functions do not accept a model argument directly – they use Snowflake-managed internal model aliases. This group splits into two tiers based on what Snowflake publicly documents.
Tier A – Model alias publicly confirmed (via BCR-2220 documentation)
All are Snowflake-native infrastructure:
| Function | Internal Model Alias | Infrastructure |
|---|---|---|
AI_TRANSLATE / TRANSLATE | arctic-translate | Snowflake-native |
AI_TRANSCRIBE / TRANSCRIBE | arctic-transcribe | Snowflake-native |
AI_EXTRACT / EXTRACT_ANSWER | arctic-extract / arctic-extract-answer | Snowflake-native |
AI_PARSE_DOCUMENT / PARSE_DOCUMENT | arctic-parse-document | Snowflake-native |
AI_SENTIMENT / SENTIMENT / ENTITY_SENTIMENT | arctic-sentiment | Snowflake-native |
CLASSIFY_TEXT, AI_REDACT | llama3.1-70b | Snowflake-native (Meta Llama) |
SUMMARIZE | mistral-7b | Snowflake-native (Mistral) |
Tier B – “Snowflake managed model” (underlying model NOT publicly disclosed)
| Function | Documented Model | Context Window | Notes |
|---|---|---|---|
AI_CLASSIFY (text) | Snowflake managed model | 128K | RBAC-enforced; model not named |
AI_CLASSIFY (image) | Snowflake managed model | 128K | Only available in ~3 regions – strongly implies a multimodal frontier model |
AI_FILTER (text/image) | Snowflake managed model | 128K | RBAC-enforced; model not named |
AI_AGG | Snowflake managed model | 128K per row | RBAC-enforced; model not named |
AI_SUMMARIZE_AGG | Snowflake managed model | 128K per row | RBAC-enforced; model not named |
Governance implication: These functions were already subject to
CORTEX_MODELS_ALLOWLISTand model RBAC enforcement before BCR-2220. Snowflake’s choice not to disclose the specific model identity makes it impossible to confirm whether these use Snowflake-native infrastructure or a frontier model tier. The image classification variant’s very limited regional availability is a strong signal it relies on a multimodal frontier model. All executions remain within Snowflake’s governance perimeter regardless.
9.4 Data Sovereignty Summary by Model Family#
| Model Family | Compute Tier | EU-Native Availability | Notes |
|---|---|---|---|
| Llama (Meta) | Snowflake-native | Yes – all EU regions | Fully on Snowflake infrastructure |
| Snowflake Arctic / SwiftKV | Snowflake-native | Yes – all EU regions | Snowflake’s own model family |
| Mistral / Mixtral | Snowflake-native | Yes – all EU regions | French AI lab; natively hosted |
| DeepSeek R1 | Snowflake-native | Yes – all EU regions | Open-source weights; hosted by Snowflake |
| Claude (Anthropic) | AWS Bedrock (Snowflake perimeter) | AWS eu-central-1, eu-west-1 only | Requires cross-region for other EU regions |
| GPT / o-series (OpenAI) | Azure AI Foundry (Snowflake perimeter) | Azure West Europe only | Requires cross-region for other Azure EU regions |
For strict in-region processing requirements: Use only Snowflake-native models (Llama, Arctic, Mistral, DeepSeek) and set CORTEX_ENABLED_CROSS_REGION = 'DISABLED'. All governance obligations are met with any model – but native models avoid any cross-region routing entirely.
9.5 Model Availability via REST API#
All models available via SQL AI_COMPLETE / COMPLETE are also accessible through the Snowflake Cortex REST API:
POST https://<account>.snowflakecomputing.com/api/v2/cortex/inference:complete
Authorization: Bearer <token>
Content-Type: application/json
{
"model": "claude-4-sonnet",
"messages": [{"role": "user", "content": "..."}]
}Authentication uses the same Snowflake session tokens (OAuth, key-pair JWT). The same RBAC model restrictions (CORTEX_MODELS_ALLOWLIST and model application roles) apply to REST API calls identically to SQL calls. REST API usage appears in CORTEX_AISQL_USAGE_HISTORY.
10. Summary Matrix#
| Governance Control | Where Configured | Who Can Configure | Audit View |
|---|---|---|---|
| Feature-level AI access | SNOWFLAKE.CORTEX_USER / CORTEX_ANALYST_USER database roles | ACCOUNTADMIN | QUERY_HISTORY (GRANT/REVOKE) |
| Model allowlist | CORTEX_MODELS_ALLOWLIST account parameter | ACCOUNTADMIN | QUERY_HISTORY (ALTER ACCOUNT) |
| Model RBAC (fine-grained) | SNOWFLAKE."CORTEX-MODEL-ROLE-*" application roles | ACCOUNTADMIN | QUERY_HISTORY |
| Cross-region inference routing | CORTEX_ENABLED_CROSS_REGION account parameter | ACCOUNTADMIN | QUERY_HISTORY (ALTER ACCOUNT) |
| Cortex AI Function usage | – | – | CORTEX_AISQL_USAGE_HISTORY, CORTEX_AI_FUNCTIONS_USAGE_HISTORY |
| Cortex Analyst usage | – | – | CORTEX_ANALYST_USAGE_HISTORY |
| Cortex Agent traces | – | – | SNOWFLAKE.LOCAL.AI_OBSERVABILITY_EVENTS |
| Per-user AI spending limits | Custom role + Snowflake Task | ACCOUNTADMIN | CORTEX_AI_FUNCTIONS_USAGE_HISTORY |
| AI evaluation/tracing | AI Observability (TruLens) | Schema owner | Event table |
| Cortex Analyst disabled entirely | ENABLE_CORTEX_ANALYST = FALSE | ACCOUNTADMIN | QUERY_HISTORY |
Key Takeaways for Enterprise Deployments#
- Default is open:
SNOWFLAKE.CORTEX_USERis granted toPUBLICby default – explicitly revoke and re-grant to enforce least-privilege. - EU residency requires active configuration: Without
CORTEX_ENABLED_CROSS_REGION = 'DISABLED'or'AWS_EU', inference requests can route to US regions. - Cortex Analyst can silently degrade: If RBAC or region settings block the top models in the fallback chain, Analyst falls back to lower-capability models – or fails entirely if the entire chain is blocked. This is a silent quality risk, not always a visible error.
- BCR-2220 is a breaking change: If
CORTEX_MODELS_ALLOWLISTis customized andAI_TRANSLATE,AI_SENTIMENT, or similar functions are in use, those calls will start failing when the 2026_02 bundle is enabled unless the relevant model aliases are added to the allowlist. - No direct inference-region attribution in logs: Credits are always billed to the requesting region. There is currently no per-query log field indicating which remote region actually processed the inference.
CORTEX_AI_FUNCTIONS_USAGE_HISTORYis the most powerful view for real-time governance: it captures in-flight queries, role attribution, and supports automated runaway-query cancellation patterns.
References:
