Fleet
Fleet (Fleet AI, Inc.) is an applied research lab that builds environments: diverse, high-fidelity simulated training gyms that model real-world work so AI agents can practice tasks while humans provide supervision. It works with frontier labs, hyperscalers and enterprises on evals and environments for agents, and is backed by Sequoia Capital, Menlo Ventures and SV Angel. Its public site lists no public API; its documentation host (docs.fleetai.com) redirects to a login page.
Fleet publishes 13 API contracts indexed on the APIs.io network, including Account API, Browsers API, Cost Attribution API, and 10 more. Tagged areas include Company, Artificial Intelligence, AI Agents, Reinforcement Learning Environments, and Evaluation.
The Fleet catalog on APIs.io includes 1 JSON-LD context and 1 Spectral governance ruleset.
Fleet’s developer surface includes CLI, authentication, and 42 more developer resources.
What this lets a business do 1
Business capabilities this provider's published APIs can perform, derived from its own contracts. Browse all capabilities →
Kin Score
Standards implemented 2
Standards this provider implements or carries. De facto ones are profiled and measured by the API Commons; formal ones come from the standards directory and are linked by the provider's own tags. The evidence column says how each claim was established — not that it was made.
APIs 13
Individual APIs this provider publishes, each with its own machine-readable definition.
Fleet Account API
The account API from Fleet — 2 operation(s) for account.
Fleet Browsers API
The browsers API from Fleet — 3 operation(s) for browsers.
Fleet Cost Attribution API
The cost-attribution API from Fleet — 1 operation(s) for cost-attribution.
Fleet Instances API
The instances API from Fleet — 13 operation(s) for instances.
Fleet Jobs API
The jobs API from Fleet — 20 operation(s) for jobs.
Fleet Matg API
The matg API from Fleet — 18 operation(s) for matg.
Fleet Provenance Audits API
The provenance-audits API from Fleet — 2 operation(s) for provenance-audits.
Fleet Seed Gen API
The seed-gen API from Fleet — 16 operation(s) for seed-gen.
Fleet Seeds API
The seeds API from Fleet — 1 operation(s) for seeds.
Fleet Sessions API
The sessions API from Fleet — 4 operation(s) for sessions.
Fleet Task Groups API
The task-groups API from Fleet — 2 operation(s) for task-groups.
Fleet Tasks API
The tasks API from Fleet — 31 operation(s) for tasks.
Fleet Verifiers API
The verifiers API from Fleet — 9 operation(s) for verifiers.
Scroll for all 13
MCP Servers 1
Model Context Protocol servers that expose these APIs to AI agents.
FleetCode MCP server (Fleet)
Fleet's official fleet-python SDK (PyPI fleet-python 0.2.133, Apache-2.0, repository github.com/fleet-ai/fleet-sdk) ships a local stdio MCP server, FastMCP("fleetcode"), exposed...
MCP SERVERAgent Skills 4
Packaged agent skills for driving this provider's APIs from an AI assistant.
fleetai-com-author-tasks-in-a-project
AGENT SKILLfleetai-com-execute-a-verifier
AGENT SKILLfleetai-com-launch-and-monitor-a-job
AGENT SKILLFleet API pricing
Pricing Plans 1
Published pricing tiers and plan structures.
Fleet Plans Pricing
PLANSRate Limits 1
Documented rate limits and quota policies.
Fleet Rate Limits
RATE LIMITSService Levels 1
Uptime the provider promises or reports, as SLA4OAI. Read from its own pages; APIs.io runs no monitors.
Fleet
SLATerms of Service 1
What its API terms permit and prohibit, quoted from its own page.
Privacy & Data 1
Its role, the data it processes, retention and transfers, quoted from its own privacy page.
Eligibility 1
Who may sign up and where, quoted from its own terms.
AI Preferences 1
Its stance on AI training, inference and agents, quoted from its own pages.
Data License 1
How its data and outputs may be reused, quoted from its own terms.
Semantic Vocabularies 1
JSON-LD contexts and semantic vocabularies used across these APIs.
Fleetai Com Context
JSON-LDSpectral Rules 1
Spectral governance rulesets for linting and validating these APIs. Counts are the severity each rule declares, not results of running them.
Fleet API Rules
SPECTRALOpenAPI Overlays 4
Overlays applied on top of this provider's contracts. Each card says who wrote it: a document the provider publishes, or one API Evangelist derived or generated.
Fleet Openapi Overlay
GENERATEDJSON Schema 34
Standalone JSON Schema definitions for this provider's data models.
AccountResponse
JSON SCHEMAAPIKeyIdentity
JSON SCHEMAArtifactOut
JSON SCHEMAAttachmentListResponse
JSON SCHEMAAuditList
JSON SCHEMAAuditReceipt
JSON SCHEMABrowserMcpToolsResource
JSON SCHEMABrowserResource
JSON SCHEMACounselDeskTaskQAStateResponse
JSON SCHEMAInstanceRequest
JSON SCHEMAInstanceResponse
JSON SCHEMAJobCreateRequestPayload
JSON SCHEMANetworkNdjsonReplayRequest
JSON SCHEMANetworkNdjsonReplayResponse
JSON SCHEMAPreflightRequest
JSON SCHEMAPublicBrowserCreateRequest
JSON SCHEMAResumeRequest
JSON SCHEMARetryRequest
JSON SCHEMARunRequest
JSON SCHEMASalesProductOptionsResponse
JSON SCHEMASeedDownloadURLResponse
JSON SCHEMASeedGenCandidateDetail
JSON SCHEMASeedGenReview
JSON SCHEMASeedGenRunDetail
JSON SCHEMASeedGenSeedView
JSON SCHEMASeedGenTableRows
JSON SCHEMASessionGradingResponse
JSON SCHEMASessionReferenceTracesResponse
JSON SCHEMAStuckCancellationRequest
JSON SCHEMATaskGroupCreateRequest
JSON SCHEMATaskGroupResponse
JSON SCHEMATaskRequest
JSON SCHEMAUploadAudit
JSON SCHEMAVerifiersExecuteRequest
JSON SCHEMAScroll for all 34
Security Posture 3
Authentication, domain security, vulnerability disclosure, and trust-center signals.
Agentic Access (API Evangelist recommendations) 1
Recommended x-agentic-access execution contracts for AI agents.
Resources
Get Started 1
Portal, sign-up, and the first successful call
Documentation 1
Reference material describing how the API behaves
Agent Surfaces 4
MCP servers, agent skills, and machine-readable catalogs
Design & Contract 9
Pagination, idempotency, versioning, errors, and events
Scroll for all 9
Build 5
SDKs, sample code, and the tooling you integrate with
Access & Security 7
Authentication, authorization, and security posture
Scroll for all 7
Operate 1
Status, limits, changes, and where to get help
Commercial 4
Pricing, plans, and the legal terms of use
Company 4
The organization behind the API
Other 8
Properties that don't map to a standard resource type
Scroll for all 8
Source (apis.yml)
Fleet API — frequently asked questions
Does Fleet have an API?
Yes. APIs.io lists 13 APIs from Fleet, including Fleet Account API, Fleet Browsers API and Fleet Cost Attribution API, and 10 more.
Is there an OpenAPI specification for the Fleet API?
Yes. APIs.io indexes 13 OpenAPI specifications for Fleet, each linked for download from this page.
How do I authenticate with the Fleet API?
Fleet uses bearer-token authentication (http · 1 scheme). The details are profiled on APIs.io as Fleet Authentication.
Does Fleet have an MCP server?
Yes. APIs.io lists 1 MCP server for Fleet: Fleet's official fleet-python SDK (PyPI fleet-python 0.2.133, Apache-2.0, repository github.com/fleet-ai/fleet-sdk) ships a local stdio MCP server, FastMCP("fleetcode"), exposed as the console script
Is the Fleet API ready for AI agents?
Fleet has a Kin Score of 53.0 out of 100 (developing) and an Agent Readiness score of 42.5 (agent-native), scored by API Evangelist on 2026-11-13.
Work with this as data
Every provider here is available over the APIs.io API and to AI agents over MCP.