Overview
Architecture
Architecture

Product video
Spice.ai Enterprise is a portable (<150MB) compute engine built in Rust for data-intensive and intelligent applications. It accelerates SQL queries across databases, data warehouses, and data lakes using Apache Arrow, DataFusion, DuckDB, or SQLite. Integrated and co-deployed with data-intensive applications, Spice materializes and accelerates data from object storage, ensuring sub-second query performance and resilient AI applications. Deployable as a container on AWS ECS, EKS, or hybrid cloud & edge, it includes enterprise licensing, support, and SLAs.
Note: Spice.ai Enterprise requires an existing commercial license. For details, please contact sales@spice.ai .
Highlights
- Unified data query and AI engine accelerating SQL queries across databases, data warehouses, and data lakes. Delivers sub-second query performance while grounding mission-critical AI applications with real-time context to minimize errors and hallucinations.
- Advanced AI and retrieval tools, featuring vector and hybrid search, text-to-SQL, and LLM memory, enabling data-grounded AI applications with more than 25 data connectors enabling federated queries and real-time applications.
- Deployable as a container on AWS ECS, EKS, or on-premises, with dedicated support and SLAs for scalable, secure integration into any architecture.
Details
Features and programs
Financing for AWS Marketplace purchases
Pricing
Vendor refund policy
Refunds for Spice.ai Enterprise container subscriptions are not available after activation, as usage begins immediately upon deployment. Ensure compatibility with AWS ECS, EKS, or on-premises setups before purchase. For billing inquiries, contact AWS Marketplace support or Spice AI directly at support@spice.ai .
How can we make this page better?
Legal
Vendor terms and conditions
Content disclaimer
Delivery details
Container Deployment
- Amazon ECS
- Amazon EKS
- Amazon ECS Anywhere
Container image
Containers are lightweight, portable execution environments that wrap server application software in a filesystem that includes everything it needs to run. Container applications run on supported container runtimes and orchestration services, such as Amazon Elastic Container Service (Amazon ECS) or Amazon Elastic Kubernetes Service (Amazon EKS). Both eliminate the need for you to install and operate your own container orchestration software by managing and scheduling containers on a scalable cluster of virtual machines.
Version release notes
Spice v2.4.2-enterprise is the enterprise release of v2.4.2, a patch release that continues security hardening and fixes Snowflake key-pair authentication. Security fixes limit the nesting depth, the expanded size, and the memory use of SQL queries, and HTTP datasets refuse redirects to other internal hosts. The release also fixes several SQL, Spice Cayenne, and runtime issues.
What's New in v2.4.2-enterprise
SQL Query Limits Protect the Runtime
Spice now limits the nesting depth, the expanded size, and the memory use of SQL queries. A query over a limit fails with HTTP 400 on /v1/sql, or with InvalidArgument on Flight SQL. The runtime continues to serve other queries. Before this release, any client that could send SQL could stop the runtime with one query. A deeply nested query overflowed the stack, and the process stopped with fatal runtime error: stack overflow, aborting. Other queries made one function or one plan allocate memory without a limit.
The checks apply to HTTP /v1/sql, /v1/nsql, Flight SQL statements and prepared statements, Flight SQL updates, and transactions. The checks cover these shapes:
- Long expressions. A chain of +, ||, AND, or OR terms deeper than 512 levels fails. This includes a /v1/search where condition.
- Nested queries. Subqueries, or common table expressions (CTEs) that each read the CTE before them, fail past 64 levels.
- CTE expansion. A query fails when its CTE references expand to more than 4096 table references. The planner makes a copy of the plan of a CTE for each reference to it.
- Nested data types. A data type such as ARRAY<ARRAY<...>> fails past 32 levels. A type such as INT[][]... fails past 64 levels.
- Arrow type strings. An Arrow type string, such as an arrow_cast argument or a column type that a dataset declares, fails past 64 levels.
- Grouping sets. A GROUP BY that expands to more than 4096 grouping sets fails. CUBE of 13 expressions makes 8192 sets. 4096 is also the limit in PostgreSQL.
- Search keywords. A /v1/search request with more than 512 keywords fails with HTTP 400.
These scalar functions now keep their output within runtime.query.memory_limit, or within a fixed cap:
- lpad and rpad charge the whole output buffer to the memory limit. This includes an empty fill string and negative lengths. A query that does not fit fails with Resources exhausted.
- array_repeat and list_repeat charge the real size of a list, struct, binary, boolean, or NULL element. Before this release, they charged 1 byte for each copy of such an element.
- flatten_json_properties, json_tree, and flatten_json stop at 32 x max_bytes of output for one document. max_depth is limited to 128. A small JSON schema with repeated allOf or $ref entries no longer expands exponentially.
- truncate cuts text by characters, not bytes. Non-ASCII text made the query fail with Query driver task ended unexpectedly.
Flight SQL metadata requests also have limits. GetSqlInfo info IDs and GetTables table types are limited to 1024 entries. GetTables and GetDbSchemas filter patterns are limited to 1024 bytes.
The limits are:
| Shape | Limit |
|---|---|
| Expression depth, such as a chain of AND, OR, +, or || | 512 levels |
| Query nesting: subqueries, or CTEs that read each other | 64 levels |
| Table references after CTE expansion | 4096 |
| SQL data type nesting with ARRAY, STRUCT, MAP, and similar keywords | 32 levels |
| SQL data type nesting with [] | 64 levels |
| Arrow type string nesting | 64 levels |
| GROUP BY grouping sets | 4096 (CUBE of up to 12 expressions) |
| /v1/search keywords | 512 |
| Flight SQL GetSqlInfo info IDs and GetTables table types | 1024 entries |
| Flight SQL GetTables and GetDbSchemas filter patterns | 1024 bytes |
CTEs that do not read each other are not limited by depth. Table references outside of CTEs do not count toward the expansion limit.
Credentials Stay out of API Responses and Logs
GET /v1/datasets and GET /v1/catalogs no longer return credentials from the from value of a component. Before this release, any API key that could list components could read a password in a source URL, such as https://user:password@host/file.csv. This included a read-only key. The runtime now removes user:password@ from each URL. It replaces values of query keys such as password, secret, token, and sig with ***. With status=true, /v1/datasets also removes credentials from error_message. Sources with no credentials do not change.
The runtime also removes credentials from these errors and log lines:
- ADBC connection errors. Setup errors no longer contain adbc_uri. The runtime replaces each configured secret in the driver message with ***. Before this release, the full URI went to the warning log and to /v1/datasets?status=true.
- MCP transport errors. The error no longer contains the URL of the MCP server. A URL can contain a credential.
- .env files. The warning for a malformed line gives only the line number, not the line content.
HTTP Datasets Refuse Redirects to Other Internal Hosts
An http or https dataset in a file format, such as CSV or Parquet, no longer follows a redirect to an internal host. An internal host is a different host that is a loopback, private, or link-local address, or that resolves to one. The dataset fails with this error:
Refused to connect to <target>: the HTTPS data connector does not follow a redirect to a private, loopback, or link-local addressThe host of the dataset itself is always allowed, also when it is internal. Redirects that stay on that host still work. SPICE_URL_TABLE_ALLOW_PRIVATE_HOSTS=true turns off the check.
Snowflake Key-Pair Authentication Fix
Snowflake datasets with key-pair authentication now load correctly. Before this release, such a dataset stopped at Initializing with this error:
Could not automatically determine the process-level CryptoProvider from jsonwebtoken crate features.Other Bug Fixes
- IS [NOT] DISTINCT FROM with AND or OR. These queries no longer return wrong boolean results or fail with an integer type error. For example, SELECT true IS DISTINCT FROM true OR true now returns true, not false. The comparison now binds before AND or OR.
- COUNT(DISTINCT ...) on list or struct columns. A query with two or more COUNT(DISTINCT ...) aggregates no longer fails with Resources exhausted when one of them reads a list or struct column. Before this release, the query failed at about 50,000 rows and requested tens of GB. Each stored value held a reference to its whole input batch. This applied to federated and Cayenne queries, with or without GROUP BY.
- Spice Cayenne file mode. At startup, a file-mode acceleration checks that the data files in its metastore exist and have the expected size. If they do not match, the acceleration reloads from the source or fails to load, and it does not serve incomplete data. Accelerations on S3 and in memory mode are not checked.
- Queries after a burst of stale cache hits. With stale_while_revalidate_ttl set on the SQL results cache , new client queries no longer wait behind background revalidations. In a test, 600 stale hits made the next uncached query wait 321.8 seconds, and 6.3 seconds with this fix. At most one quarter of the query admission limit runs revalidations at the same time. A stale hit over that limit gets the cached result with no revalidation, and results_cache_stale_swr_count counts it. The runtime cancels a revalidation after 5 minutes and records the outcome timed_out.
- truncate on numbers. truncate no longer returns wrong values for integers and decimals near the limits of their type. For example, truncate(100, arrow_cast(50, 'Int8')) returned 56, and the correct result is 0. A result that does not fit its type is now an error.
- SQL scalar functions with no arguments. A from: sql scalar function with no arguments no longer fails on every call.
- Certificate errors in the CLI. spice HTTP commands, such as status and refresh, report a TLS certificate failure as a TLS error. In v2.4.1, the release build reported it as The Spice runtime is unavailable.
- AWS session tokens. The runtime no longer sends an empty AWS session token together with static keys. A secret that is not set gives an empty token. This applies to S3, Delta Lake, and AWS SDK connectors.
Dependency Updates
- arrow-rs (Spice fork): 59.3.0 -> 59.3.2. This update fixes RUSTSEC-2026-0442 in run-end-encoded array validation, and it adds the 64-level limit for Arrow type strings.
- azure_security_keyvault_secrets: 0.10.0 -> 1.0.1. This update fixes RUSTSEC-2026-0438 in the Azure Key Vault secret store. azure_identity and azure_core move to the 1.x line for that store.
- sqlparser: 0.62.0, vendored with the precedence fix from apache/datafusion-sqlparser-rs#2436.
- DataFusion (Spice fork): the pin adds the fixes for COUNT(DISTINCT ...) memory and for nested SQL data types.
Breaking Changes
Query limits. Queries and requests over the new limits fail with HTTP 400 or Flight InvalidArgument. Most of them stopped the runtime before this release, but some ran in v2.4.1. Examples are a GROUP BY CUBE of 13 expressions, a /v1/search request with more than 512 keywords, and a query whose CTEs expand to more than 4096 table references. For each limit, see SQL Query Limits Protect the Runtime .
HTTP dataset redirects. An http or https dataset in a file format fails when its server redirects to a different internal host. To allow it, set SPICE_URL_TABLE_ALLOW_PRIVATE_HOSTS=true.
JSON flattening. flatten_json, json_tree, and flatten_json_properties stop at 32 x max_bytes of output for one document (256 MiB by default). They return the rows up to that point, with no error. The limit is on output, so a small document with long, deeply nested keys can reach it. To get all rows, increase max_bytes.
Upgrading
To upgrade to v2.4.2-enterprise, use one of the following methods:
Docker:
Run using the 2.4.2 Docker enterprise image:
docker run --name spiceai-enterprise \ -p 50051:50051 -p 8090:8090 \ 709825985650.dkr.ecr.us-east-1.amazonaws.com/spice-ai/spiceai-enterprise-byol:2.4.2-enterprise-models --http 0.0.0.0:8090 --flight 0.0.0.0:50051For available tags, see GHCR .
Helm:
helm pull oci://709825985650.dkr.ecr.us-east-1.amazonaws.com/spice-ai/spiceai-enterprise-byol --version 2.4.2-enterprise-helmCookbook Updates
No new cookbook recipes.
The Spice Cookbook provides recipes to help you get started with Spice.
What's Changed
The v2.4.2 changelog lists every change.
Additional details
Usage instructions
The docker image expects a spicepod.yaml in the /app directory. Mount a volume into the container with the configured spicepod.yaml.
By default the endpoints only listen on 127.0.0.1, to access the endpoints from outside of the docker container, specify the endpoints to listen on 0.0.0.0 as shown below.
i.e. to mount the current directory into /app: docker run --name spiceai-enterprise -v .:/app -p 50051:50051 -p 8090:8090 709825985650.dkr.ecr.us-east-1.amazonaws.com/spice-ai/spiceai-enterprise-byol:2.4.2-enterprise-models --http 0.0.0.0:8090 --flight 0.0.0.0:50051
Resources
Vendor resources
Support
Vendor support
Spice.ai Enterprise includes 24/7 dedicated support with a dedicated Slack/Team channel, priority email and ticketing, ensuring critical issues are addressed per the Enterprise SLA.
Detailed enterprise support information is available in the Support Policy & SLA document provided at onboarding.
For general support, please email support@spice.ai .
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.