How much does Databricks Mosaic AI cost?

Consumption-based pricing (Databricks DBUs) on AWS, Azure, and GCP, with a free trial and pay-as-you-go Foundation Model APIs (pay-per-token or provisioned throughput); enterprise committed-use contracts available.

Does Databricks Mosaic AI support MCP and tool calling?

Full under the Agentic Index verification standard. Databricks Mosaic AI publishes public evidence of Model Context Protocol (MCP) support, tool calling, and API or SDK extensibility for connecting agents to external tools. Evidence basis: Databricks documentation, the Agent Bricks and Unity AI Gateway product pages, and Data and AI Summit 2026 announcements confirm tool calling with a Tool Catalog and MCP native tool access, multi agent orchestration with a Supervisor Agent. Graded from public evidence only against the Agentic Index 14 point capability taxonomy. No vendor pays for placement.

Does Databricks Mosaic AI have SOC 2, SSO and role based access control?

Full under the Agentic Index verification standard. Databricks Mosaic AI publishes public evidence of enterprise security and identity controls, covering a compliance posture such as SOC 2 or ISO 27001, single sign on (SSO or SAML), and role based access control (RBAC). Evidence basis: Databricks documentation, the Agent Bricks and Unity AI Gateway product pages, and Data and AI Summit 2026 announcements confirm tool calling with a Tool Catalog and MCP native tool access, multi agent orchestration with a Supervisor Agent. Graded from public evidence only against the Agentic Index 14 point capability taxonomy. No vendor pays for placement.

Can Databricks Mosaic AI be self hosted or run in a private VPC?

Full under the Agentic Index verification standard. Databricks Mosaic AI publishes public evidence of self hosted or private VPC deployment, along with data residency options for controlling where agent data is processed and stored. Evidence basis: Databricks documentation, the Agent Bricks and Unity AI Gateway product pages, and Data and AI Summit 2026 announcements confirm tool calling with a Tool Catalog and MCP native tool access, multi agent orchestration with a Supervisor Agent. Graded from public evidence only against the Agentic Index 14 point capability taxonomy. No vendor pays for placement.

Back to vendors

Databricks Mosaic AI

Q: Who is Databricks Mosaic AI for?

Enterprise data & AI teams, Databricks customers, ML / AI engineers

Q: What are the best alternatives to Databricks Mosaic AI?

Based on documented capability coverage across the Agentic Index 14 point taxonomy, the closest alternatives to Databricks Mosaic AI among multi-agent platforms are Rasa, Akka, CrewAI, Dataiku. Each is graded on the same public evidence, and no vendor pays for placement.

Also known as: Databricks Mosaic AI, Mosaic AI, MosaicML, Mosaic AI Agent Framework

Visit site

Multi-agent platformacquiredVerified 2026-06-28

Entry priceFree trial · usage based (DBUs)Full pricing detail

Databricks Mosaic AI platform for building, deploying, and orchestrating multi-agent systems.

Mosaic AI is the artificial-intelligence product layer of the Databricks Data Intelligence Platform, the suite Databricks uses to build, evaluate, deploy, and govern production-grade AI agents, RAG applications, and machine-learning models. It originated with Databricks' 2023 acquisition of MosaicML and has since been fully integrated and substantially expanded; 'Mosaic AI' now spans Foundation Model APIs, Model Serving, Vector Search, and the Agent Framework itself.

The Mosaic AI Agent Framework lets developers build tool-calling agents, retrieval-augmented applications, and multi-agent systems that connect enterprise data in Delta Lake to LLMs through a governed, auditable stack. Unlike an open-source library, it is a platform layer: data, models, deployment, and governance live in one environment under Unity Catalog. Agents can be authored in LangChain, LangGraph, or native Python, logged and traced with MLflow, and served via Model Serving. Agent Evaluation grades output quality with built-in AI judges and human-in-the-loop review, and the no-code AI Playground lets teams prototype by selecting a model, adding tools, and testing before exporting to code.

In 2025 Databricks launched Agent Bricks, which uses Mosaic AI Research techniques to auto-generate domain-specific synthetic data and task-aware benchmarks, then automatically optimizes agents for cost and quality. Governance is a core selling point: guardrails, access controls, rate limits, and data lineage across every model, plus an AI Gateway governing LLMs and MCP. Enterprises including FactSet, Block, Intercontinental Exchange, Comcast, Corning, and AstraZeneca have built agent systems on it. Databricks serves 15,000+ organizations, including roughly 70% of the Fortune 500, with consumption-based pricing on AWS, Azure, and GCP.

Vendor details

Canonical URL

https://www.databricks.com/product/mosaic-ai

Subcategory

Enterprise agent platform on Databricks (Mosaic AI)

Funding status

Mosaic AI is the AI/ML product layer of Databricks (the company; 15,000+ organizations, ~70% of the Fortune 500). Built on Databricks' 2023 acquisition of MosaicML, now fully integrated and expanded across the Databricks Data Intelligence Platform.

Company status

acquired

Use cases & customers

Primary use cases

Building production tool-calling agents and RAG applications on enterprise dataMulti-agent system development with governed data accessAgent evaluation and quality assurance (AI judges + human review)Serving and governing LLMs and agents (Model Serving, AI Gateway, Unity Catalog)Domain-specific agent optimization via Agent Bricks (synthetic data + benchmarks)

Target customers

Enterprise data & AI teamsDatabricks customersML / AI engineers

Deployment options

SaaS (Databricks platform)Cloud (AWS, Azure, GCP)

Integrations

Native to the Databricks Data Intelligence Platform: connects enterprise data in Delta Lake to LLMs via Vector Search, Model Serving, Foundation Model APIs (serving OpenAI, Anthropic, and others), MLflow tracing/evaluation, and Unity Catalog governance. Supports tool-calling agents, RAG, and multi-agent systems authored in LangChain, LangGraph, or native Python, with a Tool Catalog for function-calling and an AI Gateway governing LLMs and MCP. Runs on AWS, Azure, and GCP.

In practice

Your agents need enterprise data, but the data and the models live in different worlds. Mosaic AI builds agents on Databricks where the data, models, and governance sit in one environment under Unity Catalog.

You can't tell whether your agent's output is actually good. Mosaic AI's Agent Evaluation grades quality with built-in AI judges and human review before you ship.

Tuning an agent for cost and quality is endless manual work. Databricks' Agent Bricks auto-generates task benchmarks and optimizes the agent against them.

Sources & related URLs

Research sources

https://www.databricks.com/product/artificial-intelligence https://www.databricks.com/blog/mosaic-ai-build-and-deploy-production-quality-compound-ai-systems https://www.databricks.com/company/newsroom/press-releases/databricks-launches-agent-bricks-new-approach-building-ai-agents https://docs.databricks.com/aws/en/generative-ai/agent-framework/build-agents

Agentic Index coverage score

12.0 / 14 capabilities · 86%

Integrations & Tool CallingDatabricks documentation, the Agent Bricks and Unity AI Gateway product pages, and Data and AI Summit 2026 announcements confirm tool calling with a Tool Catalog and MCP native tool access, multi agent orchestration with a Supervisor Agent and LangGraph and CrewAI harness support, flagship retrieval with Mosaic AI Vector Search and Genie Ontology, guardrails, PII detection, and human approval policies, deep governance under Unity Catalog with RBAC and ABAC plus Databricks security certifications, MLflow tracing with Lakewatch observability and audit logs, managed Agent Memory Services backed by Lakebase, multi cloud deployment across AWS, Azure, and GCP with serverless Databricks Apps, model flexibility and routing across OpenAI, Anthropic, Google, and open source through the AI Gateway, broad APIs, SDKs, and MCP extensibility, and built in Agent Evaluation with AI judges and human review.	Full
Workflow OrchestrationDatabricks documentation, the Agent Bricks and Unity AI Gateway product pages, and Data and AI Summit 2026 announcements confirm tool calling with a Tool Catalog and MCP native tool access, multi agent orchestration with a Supervisor Agent and LangGraph and CrewAI harness support, flagship retrieval with Mosaic AI Vector Search and Genie Ontology, guardrails, PII detection, and human approval policies, deep governance under Unity Catalog with RBAC and ABAC plus Databricks security certifications, MLflow tracing with Lakewatch observability and audit logs, managed Agent Memory Services backed by Lakebase, multi cloud deployment across AWS, Azure, and GCP with serverless Databricks Apps, model flexibility and routing across OpenAI, Anthropic, Google, and open source through the AI Gateway, broad APIs, SDKs, and MCP extensibility, and built in Agent Evaluation with AI judges and human review.	Full
Knowledge Grounding & RAGDatabricks documentation, the Agent Bricks and Unity AI Gateway product pages, and Data and AI Summit 2026 announcements confirm tool calling with a Tool Catalog and MCP native tool access, multi agent orchestration with a Supervisor Agent and LangGraph and CrewAI harness support, flagship retrieval with Mosaic AI Vector Search and Genie Ontology, guardrails, PII detection, and human approval policies, deep governance under Unity Catalog with RBAC and ABAC plus Databricks security certifications, MLflow tracing with Lakewatch observability and audit logs, managed Agent Memory Services backed by Lakebase, multi cloud deployment across AWS, Azure, and GCP with serverless Databricks Apps, model flexibility and routing across OpenAI, Anthropic, Google, and open source through the AI Gateway, broad APIs, SDKs, and MCP extensibility, and built in Agent Evaluation with AI judges and human review.	Full
Human Oversight & GuardrailsDatabricks documentation, the Agent Bricks and Unity AI Gateway product pages, and Data and AI Summit 2026 announcements confirm tool calling with a Tool Catalog and MCP native tool access, multi agent orchestration with a Supervisor Agent and LangGraph and CrewAI harness support, flagship retrieval with Mosaic AI Vector Search and Genie Ontology, guardrails, PII detection, and human approval policies, deep governance under Unity Catalog with RBAC and ABAC plus Databricks security certifications, MLflow tracing with Lakewatch observability and audit logs, managed Agent Memory Services backed by Lakebase, multi cloud deployment across AWS, Azure, and GCP with serverless Databricks Apps, model flexibility and routing across OpenAI, Anthropic, Google, and open source through the AI Gateway, broad APIs, SDKs, and MCP extensibility, and built in Agent Evaluation with AI judges and human review.	Full
Security, Identity & GovernanceDatabricks documentation, the Agent Bricks and Unity AI Gateway product pages, and Data and AI Summit 2026 announcements confirm tool calling with a Tool Catalog and MCP native tool access, multi agent orchestration with a Supervisor Agent and LangGraph and CrewAI harness support, flagship retrieval with Mosaic AI Vector Search and Genie Ontology, guardrails, PII detection, and human approval policies, deep governance under Unity Catalog with RBAC and ABAC plus Databricks security certifications, MLflow tracing with Lakewatch observability and audit logs, managed Agent Memory Services backed by Lakebase, multi cloud deployment across AWS, Azure, and GCP with serverless Databricks Apps, model flexibility and routing across OpenAI, Anthropic, Google, and open source through the AI Gateway, broad APIs, SDKs, and MCP extensibility, and built in Agent Evaluation with AI judges and human review.	Full
Observability & AuditabilityDatabricks documentation, the Agent Bricks and Unity AI Gateway product pages, and Data and AI Summit 2026 announcements confirm tool calling with a Tool Catalog and MCP native tool access, multi agent orchestration with a Supervisor Agent and LangGraph and CrewAI harness support, flagship retrieval with Mosaic AI Vector Search and Genie Ontology, guardrails, PII detection, and human approval policies, deep governance under Unity Catalog with RBAC and ABAC plus Databricks security certifications, MLflow tracing with Lakewatch observability and audit logs, managed Agent Memory Services backed by Lakebase, multi cloud deployment across AWS, Azure, and GCP with serverless Databricks Apps, model flexibility and routing across OpenAI, Anthropic, Google, and open source through the AI Gateway, broad APIs, SDKs, and MCP extensibility, and built in Agent Evaluation with AI judges and human review.	Full
Memory & State PersistenceDatabricks documentation, the Agent Bricks and Unity AI Gateway product pages, and Data and AI Summit 2026 announcements confirm tool calling with a Tool Catalog and MCP native tool access, multi agent orchestration with a Supervisor Agent and LangGraph and CrewAI harness support, flagship retrieval with Mosaic AI Vector Search and Genie Ontology, guardrails, PII detection, and human approval policies, deep governance under Unity Catalog with RBAC and ABAC plus Databricks security certifications, MLflow tracing with Lakewatch observability and audit logs, managed Agent Memory Services backed by Lakebase, multi cloud deployment across AWS, Azure, and GCP with serverless Databricks Apps, model flexibility and routing across OpenAI, Anthropic, Google, and open source through the AI Gateway, broad APIs, SDKs, and MCP extensibility, and built in Agent Evaluation with AI judges and human review.	Full
Deployment & Data ResidencyDatabricks documentation, the Agent Bricks and Unity AI Gateway product pages, and Data and AI Summit 2026 announcements confirm tool calling with a Tool Catalog and MCP native tool access, multi agent orchestration with a Supervisor Agent and LangGraph and CrewAI harness support, flagship retrieval with Mosaic AI Vector Search and Genie Ontology, guardrails, PII detection, and human approval policies, deep governance under Unity Catalog with RBAC and ABAC plus Databricks security certifications, MLflow tracing with Lakewatch observability and audit logs, managed Agent Memory Services backed by Lakebase, multi cloud deployment across AWS, Azure, and GCP with serverless Databricks Apps, model flexibility and routing across OpenAI, Anthropic, Google, and open source through the AI Gateway, broad APIs, SDKs, and MCP extensibility, and built in Agent Evaluation with AI judges and human review.	Full
Prebuilt Agents, Templates & PacksPrebuilt content centers on configurable Agent Bricks blueprint types (Knowledge Assistant, Information Extraction, Supervisor Agent, Document Intelligence) and a Tool Catalog rather than a large library of turnkey vertical agents, and triggers are strong through Lakeflow Jobs and REST endpoints while consumer channel coverage (Slack, Teams, voice) is limited compared with API first deployment and Genie conversational surfaces.	Partial
Triggers & Channel CoveragePrebuilt content centers on configurable Agent Bricks blueprint types (Knowledge Assistant, Information Extraction, Supervisor Agent, Document Intelligence) and a Tool Catalog rather than a large library of turnkey vertical agents, and triggers are strong through Lakeflow Jobs and REST endpoints while consumer channel coverage (Slack, Teams, voice) is limited compared with API first deployment and Genie conversational surfaces.	Partial
Model Flexibility & RoutingDatabricks documentation, the Agent Bricks and Unity AI Gateway product pages, and Data and AI Summit 2026 announcements confirm tool calling with a Tool Catalog and MCP native tool access, multi agent orchestration with a Supervisor Agent and LangGraph and CrewAI harness support, flagship retrieval with Mosaic AI Vector Search and Genie Ontology, guardrails, PII detection, and human approval policies, deep governance under Unity Catalog with RBAC and ABAC plus Databricks security certifications, MLflow tracing with Lakewatch observability and audit logs, managed Agent Memory Services backed by Lakebase, multi cloud deployment across AWS, Azure, and GCP with serverless Databricks Apps, model flexibility and routing across OpenAI, Anthropic, Google, and open source through the AI Gateway, broad APIs, SDKs, and MCP extensibility, and built in Agent Evaluation with AI judges and human review.	Full
APIs, SDKs & MCP ExtensibilityDatabricks documentation, the Agent Bricks and Unity AI Gateway product pages, and Data and AI Summit 2026 announcements confirm tool calling with a Tool Catalog and MCP native tool access, multi agent orchestration with a Supervisor Agent and LangGraph and CrewAI harness support, flagship retrieval with Mosaic AI Vector Search and Genie Ontology, guardrails, PII detection, and human approval policies, deep governance under Unity Catalog with RBAC and ABAC plus Databricks security certifications, MLflow tracing with Lakewatch observability and audit logs, managed Agent Memory Services backed by Lakebase, multi cloud deployment across AWS, Azure, and GCP with serverless Databricks Apps, model flexibility and routing across OpenAI, Anthropic, Google, and open source through the AI Gateway, broad APIs, SDKs, and MCP extensibility, and built in Agent Evaluation with AI judges and human review.	Full
Testing, Debugging & OptimizationDatabricks documentation, the Agent Bricks and Unity AI Gateway product pages, and Data and AI Summit 2026 announcements confirm tool calling with a Tool Catalog and MCP native tool access, multi agent orchestration with a Supervisor Agent and LangGraph and CrewAI harness support, flagship retrieval with Mosaic AI Vector Search and Genie Ontology, guardrails, PII detection, and human approval policies, deep governance under Unity Catalog with RBAC and ABAC plus Databricks security certifications, MLflow tracing with Lakewatch observability and audit logs, managed Agent Memory Services backed by Lakebase, multi cloud deployment across AWS, Azure, and GCP with serverless Databricks Apps, model flexibility and routing across OpenAI, Anthropic, Google, and open source through the AI Gateway, broad APIs, SDKs, and MCP extensibility, and built in Agent Evaluation with AI judges and human review.	Full
Browser & Computer UseDatabricks Mosaic AI operates on governed lakehouse data through APIs, tools, and MCP and does not provide browser or computer use automation.	Unable to verify

The Agentic Index coverage score grades every vendor Full, Partial or Unable to verify against the same 14 buyer facing capabilities, from public evidence only. Each capability links to how all vendors in the index score on it. How this evidence is graded

Recent platform changes

2026-06-13·Workflow orchestrationVerified

Databricks announced Omnigent, an open-source meta-harness above existing agents that adds multi-agent composition, contextual policies, real-time collaboration, cloud execution, and multi-harness authoring.

Bears on: Workflow orchestration

View source

2026-06-11·MCP / tool calling / APIVerified

Agent Bricks Supervisor Agent added support for Unity Catalog volumes as subagent tools.

Bears on: MCP / tool calling / API

View source

View all 2 changes for Databricks Mosaic AI →Tracked since Jun 2026 · Verified from public vendor sources

Pricing

Free trial · usage based (DBUs)

usage (DBUs)

Trial available

Included quota

There is no fixed seat price. A free trial lets teams evaluate the platform, after which usage is billed by DBU consumption across model serving, vector search, agent execution, and jobs, plus per token Foundation Model API usage. Enterprise committed use contracts bundle volume at a discount. Available on AWS, Azure, and GCP.

What is public

Public: the consumption based model, per DBU rates by cloud and workload, and per token Foundation Model API rates. Not public as a single figure: total cost, which depends entirely on consumption, and enterprise committed use discounts, which are negotiated.

Billing mechanics

Consumption based billing in Databricks Units (DBUs), where each workload (model serving, vector search, agent execution, jobs) consumes DBUs at a published rate that varies by cloud and compute type. Foundation Model APIs are billed pay as you go per token or by provisioned throughput. Committed use contracts give volume discounts. Underlying cloud infrastructure is billed by the cloud provider.

Cost watchouts

DBU consumption spans multiple workloads (model serving, vector search, agent execution, jobs) that bill in parallel, and underlying cloud compute is billed by the cloud provider on top. Foundation Model API token costs scale with usage. Real spend is hard to predict from the rate card alone and depends on architecture and volume.

Variable cost rationale

Billing is purely consumption based on DBUs and per token model usage, so cost scales directly with agent activity, model serving, vector search, and job volume. Long running or high throughput agent systems accumulate cost across several workloads at once, and underlying cloud infrastructure is billed separately, so exposure is high, though committed use contracts and provisioned throughput can make spend more predictable.

Additional watchouts

Consumption based billing means cost tracks usage across several workloads plus underlying cloud compute, which is billed separately. Committed use pricing is negotiated. Realistic budgeting requires estimating DBU and token consumption for your workloads.

Overage / add-ons

There are no fixed caps; usage bills by DBU consumption and per token model usage. Committed use contracts prepay volume at a discount, and provisioned throughput reserves capacity for steadier cost.

Sales call required

Mixed (some tiers require a call)

Free / trial

A free trial is available to evaluate the Databricks platform and Mosaic AI before committing to consumption billing.

Lowest paid plan

Pay as you go consumption on Databricks Units, with published per DBU and per token rates, above a free trial.

Commercial notes

The agent layer of the Databricks Data Intelligence Platform, so pricing follows the Databricks consumption model rather than a standalone agent subscription. Most compelling for teams already on Databricks, where data, models, governance, and agents live in one environment under Unity Catalog. Serves roughly 70% of the Fortune 500.

Key ambiguities

Total cost depends entirely on consumption across workloads and on the cloud, so a single entry price is not meaningful. Enterprise committed use discounts are negotiated and not public.

Support SLA / resale

Support tiers follow the Databricks platform (business, enhanced, production, and mission critical), with enterprise SLAs available on committed contracts. Available through AWS, Azure, and GCP marketplaces.

Missing data

Exact per DBU and per token rates by cloud and workload, and enterprise committed use discount levels, are not captured here and vary by cloud, region, and contract.

Agentic Index verified 2026-07-01

Official pricing page

Related vendors

Alternatives to Databricks Mosaic AI

The closest documented capability profiles to Databricks Mosaic AI among multi-agent platforms tracked by Agentic Index, ordered by similarity on the same 14 point evidence the rankings use. No vendor pays for placement.

Rasa12.5 / 14Fuller documented coverage on Triggers & Channel Coverage
Akka12.0 / 14Fuller documented coverage on Triggers & Channel CoverageDatabricks Mosaic AI vs Akka →
CrewAI13.0 / 14Adds documented Browser & Computer UseDatabricks Mosaic AI vs CrewAI →
Dataiku12.0 / 14Fuller documented coverage on Prebuilt Agents, Templates & PacksDatabricks Mosaic AI vs Dataiku →
Legion Intelligence12.0 / 14Fuller documented coverage on Prebuilt Agents, Templates & Packs
Distyl AI11.5 / 14Fuller documented coverage on Triggers & Channel CoverageDatabricks Mosaic AI vs Distyl AI →

Similarity is computed from each vendor's Agentic Index coverage score evidence, axis by axis, not from the totals. How this evidence is graded

Compare Databricks Mosaic AI with other vendors →Compare all multi-agent platforms →See where Databricks Mosaic AI ranks →

Data confidence: high

Head to head

Databricks Mosaic AI vs Distyl AI Databricks Mosaic AI vs CrewAI Databricks Mosaic AI vs Dataiku Databricks Mosaic AI vs Akka