Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Snowflake / Arctic-TILT legacy document service

Arctic-TILT Legacy

Managed inference for legacy Document AI builds migrated into Snowflake Model Registry before the old interface was decommissioned.

restrictedClosed-source managed componentDocument extractionOCR
Official documentation (opens in a new tab)Reviewed 15 Oct 2026
7 of 19 specification fields collected
Context windowNot collectedAwaiting source review
Maximum outputNot collectedAwaiting source review
Input billingSee ratesSnowflake legacy AI_EXTRACT
Output billingSee ratesPublished units and conditions below

Specifications

Provider-documented facts. “Not collected” means we have not verified that field yet, not that the feature is unsupported.

Context / input limit
Not collected

No exact hosted model specification established. SQL execution and research-only limits do not imply a general chat API capability.

Maximum input tokens
Not collected

No exact hosted model specification established. SQL execution and research-only limits do not imply a general chat API capability.

Maximum output
Not collected

No exact hosted model specification established. SQL execution and research-only limits do not imply a general chat API capability.

Maximum input content size
Not collected

No exact hosted model specification established. SQL execution and research-only limits do not imply a general chat API capability.

Parameters
Not collected

No exact hosted model specification established. SQL execution and research-only limits do not imply a general chat API capability.

Reasoning
Not collected

No exact hosted model specification established. SQL execution and research-only limits do not imply a general chat API capability.

Tool calling
Not collected

No exact hosted model specification established. SQL execution and research-only limits do not imply a general chat API capability.

Structured output
SupportedSource for Structured output (opens in a new tab)

JSON follows the existing model build entity/table schema; not an arbitrary constrained-decoding API.

Streaming
Not collected

No exact hosted model specification established. SQL execution and research-only limits do not imply a general chat API capability.

Batch processing
Not collected

No exact hosted model specification established. SQL execution and research-only limits do not imply a general chat API capability.

Fine-tuning
Not supportedSource for Fine-tuning (opens in a new tab)

Migrated fine-tuned legacy models can still run inference, but a new version cannot be fine-tuned. New tuning uses Arctic-Extract.

Context caching
Not collected

No exact hosted model specification established. SQL execution and research-only limits do not imply a general chat API capability.

Release date
Not collected

No exact hosted model specification established. SQL execution and research-only limits do not imply a general chat API capability.

Knowledge cutoff
Not collected

No exact hosted model specification established. SQL execution and research-only limits do not imply a general chat API capability.

Request limits
Legacy model build should contain no more than 100 entities.Source for Request limits (opens in a new tab)
Output formats
Entity and table extraction JSON; confidence scores are not supported.Source for Output formats (opens in a new tab)
Published price
Distinct Snowflake AI Credit rates for entity and table extractionSource for Published price (opens in a new tab)

Access & pricing

Prices belong to an endpoint and billing tier. A provider listing does not guarantee access for every account or region.

Snowflake legacy AI_EXTRACT

Provider source (opens in a new tab)
API model ID
Not collected

No public checkpoint selector: the base function is implicit, while custom model builds use an account-specific registry name.

Access
Only Document AI builds migrated to Model Registry before March 16, 2026. Requires SNOWFLAKE.CORTEX_USER and model OWNERSHIP. Model authorization also applies: model RBAC is checked first, then CORTEX_MODELS_ALLOWLIST; if neither permits access the call fails.
Regions
AWS Canada Central, Frankfurt, Ireland, N. Virginia, Ohio, Oregon; Azure Australia East, East US 2, Southeast Asia, West Europe, West US 2. Other regions require cross-region inference; unavailable in PR China.
API endpoint URL
AI_EXTRACT(model => 'database.schema.model_name', file => TO_FILE(...))Source for API endpoint URL (opens in a new tab)
API parameters
Uses the model default version; change it with ALTER MODEL ... SET DEFAULT_VERSION.Source for API parameters (opens in a new tab)
Billing scope
Consumption label: arctic-tilt-entitySource for Billing scope (opens in a new tab)
Authentication
In addition to function/object privileges, model access must be granted via model RBAC or the model/alias must be permitted by CORTEX_MODELS_ALLOWLIST. All allows fallback access; otherwise an unpermitted call fails.Source for Authentication (opens in a new tab)

The base AI_EXTRACT governance alias is arctic-extract. Account-specific custom model privileges still apply.

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 15 Oct 2026
CategoryUsageRateUnit
Inference AI CreditsLegacy entity extraction · AI Credits19.5 credits1M processed tokens

Rate conditions

  1. Snowflake AI Credits, not USD. Contract credit conversion, warehouse/storage and other platform charges are separate. Page and prompt/output token accounting follows the relevant endpoint documentation.
Pricing source (opens in a new tab)

Data & enterprise terms

Snowflake states that customer data is not used to train models made available to its customer base. Except as elected, AI models run inside its security/governance perimeter. Cross-region processing can transiently transmit prompts/results outside the account region; exact contractual retention terms are not established here.

Read the service policy (opens in a new tab)

Snowflake legacy AI_EXTRACT

Provider source (opens in a new tab)
API model ID
Not collected

No public checkpoint selector: the base function is implicit, while custom model builds use an account-specific registry name.

Access
Only Document AI builds migrated to Model Registry before March 16, 2026. Requires SNOWFLAKE.CORTEX_USER and model OWNERSHIP. Model authorization also applies: model RBAC is checked first, then CORTEX_MODELS_ALLOWLIST; if neither permits access the call fails.
Regions
AWS Canada Central, Frankfurt, Ireland, N. Virginia, Ohio, Oregon; Azure Australia East, East US 2, Southeast Asia, West Europe, West US 2. Other regions require cross-region inference; unavailable in PR China.
API endpoint URL
AI_EXTRACT(model => 'database.schema.model_name', file => TO_FILE(...))Source for API endpoint URL (opens in a new tab)
API parameters
Uses the model default version; change it with ALTER MODEL ... SET DEFAULT_VERSION.Source for API parameters (opens in a new tab)
Billing scope
Consumption label: arctic-tilt-tableSource for Billing scope (opens in a new tab)
Authentication
In addition to function/object privileges, model access must be granted via model RBAC or the model/alias must be permitted by CORTEX_MODELS_ALLOWLIST. All allows fallback access; otherwise an unpermitted call fails.Source for Authentication (opens in a new tab)

The base AI_EXTRACT governance alias is arctic-extract. Account-specific custom model privileges still apply.

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 15 Oct 2026
CategoryUsageRateUnit
Inference AI CreditsLegacy table extraction · AI Credits128.4 credits1M processed tokens

Rate conditions

  1. Snowflake AI Credits, not USD. Contract credit conversion, warehouse/storage and other platform charges are separate. Page and prompt/output token accounting follows the relevant endpoint documentation.
Pricing source (opens in a new tab)

Data & enterprise terms

Snowflake states that customer data is not used to train models made available to its customer base. Except as elected, AI models run inside its security/governance perimeter. Cross-region processing can transiently transmit prompts/results outside the account region; exact contractual retention terms are not established here.

Read the service policy (opens in a new tab)

Caching

Caching can reuse earlier input processing. Availability, lifetime and billing depend on the endpoint. A cache hit still generates a new response.

01 / INITIAL INPUTProcess & retain

The system processes eligible input and retains reusable state.

02 / LATER REQUESTCheck available state

Reuse depends on matching input, session state and the cache policy.

03 / CACHE HITReuse & generate

Reusing state can reduce repeated work. Any charges follow the billing rules below.

Snowflake legacy AI_EXTRACT

Not verified

AI_EXTRACT prompt caching and discounted cached-token rates are not established.

How it works
Not collected

AI_EXTRACT prompt caching and discounted cached-token rates are not established.

Minimum reusable input
Not collected

AI_EXTRACT prompt caching and discounted cached-token rates are not established.

Lifetime & refresh
Not collected

AI_EXTRACT prompt caching and discounted cached-token rates are not established.

How to enable it
Not collected

AI_EXTRACT prompt caching and discounted cached-token rates are not established.

Usage fields
Not collected

AI_EXTRACT prompt caching and discounted cached-token rates are not established.

Billing rules
Not collected

AI_EXTRACT prompt caching and discounted cached-token rates are not established.

Limits & data boundaries
Published automatic response caching covers text-only AI_COMPLETE, not AI_EXTRACT. Its 24-hour TTL and free cache hits must not be applied to document extraction.Source for Limits & data boundaries (opens in a new tab)

No verified cache rate for this endpoint. An empty rate is not a zero charge.

Caching reviewed 15 Oct 2026

Snowflake legacy AI_EXTRACT

Not verified

AI_EXTRACT prompt caching and discounted cached-token rates are not established.

How it works
Not collected

AI_EXTRACT prompt caching and discounted cached-token rates are not established.

Minimum reusable input
Not collected

AI_EXTRACT prompt caching and discounted cached-token rates are not established.

Lifetime & refresh
Not collected

AI_EXTRACT prompt caching and discounted cached-token rates are not established.

How to enable it
Not collected

AI_EXTRACT prompt caching and discounted cached-token rates are not established.

Usage fields
Not collected

AI_EXTRACT prompt caching and discounted cached-token rates are not established.

Billing rules
Not collected

AI_EXTRACT prompt caching and discounted cached-token rates are not established.

Limits & data boundaries
Published automatic response caching covers text-only AI_COMPLETE, not AI_EXTRACT. Its 24-hour TTL and free cache hits must not be applied to document extraction.Source for Limits & data boundaries (opens in a new tab)

No verified cache rate for this endpoint. An empty rate is not a zero charge.

Caching reviewed 15 Oct 2026

What the measurements say

No benchmark observations have been added for this model. We do not turn a vendor description into a performance score.

Latency and throughput depend on the host, request size, reasoning settings and load. There is no measured speed or global usage figure in this record.

The record behind the model

Why it is included

Managed access to customer-specific legacy Document AI builds migrated to Snowflake Model Registry. Exact deployed checkpoint mapping is not established. Public Arctic-TILT v1.3 weights are excluded, and this record is not counted as a separate private base checkpoint.

Classification evidence (opens in a new tab)

Lifecycle dates

Document AI UI and model_build_name!PREDICT decommissioned; only previously migrated builds remain usable through AI_EXTRACT16 Mar 2026Source (opens in a new tab)

Sources reviewed