Arcee AI
Arcee AI is an American open-intelligence research lab that builds and releases small, efficient open-weight language models (the Trinity family, AFM-4.5B, and Virtuoso/Maestro derivatives) along with a developer platform for running them. The Arcee Platform exposes an OpenAI-compatible inference API at api.arcee.ai (chat completions, model listing, and usage/credits endpoints) secured with bearer API keys, plus Arcee Conductor (model routing), Arcee Orchestra (agentic workflows with their own invocation API), and AnyMCP for hosting Model Context Protocol servers. Arcee also maintains widely used open-source model tooling including mergekit, DistillKit, and DALM. Models can be consumed through the hosted API or self-deployed on vLLM, SGLang, llama.cpp, and Ollama.
Real signal across most facets with visible, nameable gaps — the contract exists but is thin, or the portal is good while governance and commercial terms are absent.
API Evangelist profiles Arcee AI the way a machine reads it — 33 machine-readable artifacts across 29 APIs, pulled from the provider's own public surface and indexed so a developer, an analyst, or an AI agent can evaluate it against every other provider on the network.
Every provider in the network is reduced to the same set of machine-readable artifacts — OpenAPI contracts, event specifications, GraphQL schemas, runnable collections, pricing and rate-limit signals, security posture, OAuth scopes, and the agent surfaces (MCP servers and skills) that let software drive the API on its own. We profile them because the interface is the part of a company you can actually inspect: it is a truer signal of what a provider does than any marketing page. From those artifacts we compute the Kin Score — Arcee AI scores 46.1/100 (developing), with a separate agent-readiness read of 48/100 (agent ready). The full breakdown is below, followed by every artifact we hold — each card links through to its machine-readable definition on apis.io.
Kin Score
This is the API Evangelist rating — a single, repeatable read computed from the artifacts on this page. Green fill is points earned; the red track is points possible, so every bar shows earned-versus-possible at a glance.
Kin Score
How this is scored →scored 2026-07-27 · rubric v0.5
How we profile Arcee AI
Each block below is one kind of artifact we hold for Arcee AI. For each we say what it is and why it earns a place in the profile, then list every one we've indexed — capped at two rows, scroll within the panel for the rest.
APIs 29
Each API is captured as its own OpenAPI definition — every operation, parameter, and response. This is the single most useful machine-readable description of what an API does, and it's what lets us score, lint, mock, and generate against it without asking the provider for anything.
Individual APIs this provider publishes, each with its own machine-readable definition.
Arcee AI Access Profiles API
The Access Profiles API from Arcee AI — 3 operation(s) for access profiles.
Arcee AI AFM API API
The AFM API API from Arcee AI — 1 operation(s) for afm api.
Arcee AI Analytics API
The Analytics API from Arcee AI — 29 operation(s) for analytics.
Arcee AI Arcee-Admin API
The Arcee-Admin API from Arcee AI — 12 operation(s) for arcee-admin.
Arcee AI Auth API
The Auth API from Arcee AI — 21 operation(s) for auth.
Arcee AI Automated Reports API
The Automated Reports API from Arcee AI — 7 operation(s) for automated reports.
Arcee AI Billing API
The Billing API from Arcee AI — 4 operation(s) for billing.
Arcee AI Chat API
The Chat API from Arcee AI — 12 operation(s) for chat.
Arcee AI Completions API
The Completions API from Arcee AI — 7 operation(s) for completions.
Arcee AI Demo Mode API
The Demo Mode API from Arcee AI — 5 operation(s) for demo mode.
Arcee AI Dev Mode API
The Dev Mode API from Arcee AI — 4 operation(s) for dev mode.
Arcee AI Device Auth API
The Device Auth API from Arcee AI — 5 operation(s) for device auth.
Arcee AI Feedback API
The Feedback API from Arcee AI — 3 operation(s) for feedback.
Arcee AI Health API
The Health API from Arcee AI — 1 operation(s) for health.
Arcee AI Keys API
The Keys API from Arcee AI — 7 operation(s) for keys.
Arcee AI Metrics API
The Metrics API from Arcee AI — 1 operation(s) for metrics.
Arcee AI Models API
The Models API from Arcee AI — 2 operation(s) for models.
Arcee AI Organizations API
The Organizations API from Arcee AI — 20 operation(s) for organizations.
Arcee AI Partners API
The Partners API from Arcee AI — 2 operation(s) for partners.
Arcee AI RAG API
The RAG API from Arcee AI — 9 operation(s) for rag.
Arcee AI Rate Limit Profiles API
The Rate Limit Profiles API from Arcee AI — 2 operation(s) for rate limit profiles.
Arcee AI Registry API
The Registry API from Arcee AI — 6 operation(s) for registry.
Arcee AI S3 API
The S3 API from Arcee AI — 8 operation(s) for s3.
Arcee AI Search API
The Search API from Arcee AI — 1 operation(s) for search.
Arcee AI System Prompts API
The System Prompts API from Arcee AI — 3 operation(s) for system prompts.
Arcee AI Transaction API
The Transaction API from Arcee AI — 6 operation(s) for transaction.
Arcee AI Usage API
The Usage API from Arcee AI — 6 operation(s) for usage.
Arcee AI User API
The User API from Arcee AI — 12 operation(s) for user.
Arcee AI Webhooks API
The Webhooks API from Arcee AI — 1 operation(s) for webhooks.
Scroll within the panel for all 29 ·
MCP Servers 1
Model Context Protocol servers expose these APIs directly to AI agents. We profile them because agent-native access is the fastest-growing way this provider's capabilities actually get used.
Model Context Protocol servers that expose these APIs to AI agents.
arcee-ai-mcp.yml
MCP SERVERSecurity Posture 2
Authentication, domain security, vulnerability disclosure, and trust-center signals — the evidence that a provider takes security seriously enough to document it. We profile it because you can't govern what you can't see.
Authentication, domain security, vulnerability disclosure, and trust-center signals.
Agentic Access 1
An x-agentic-access contract marks which operations are safe for an agent to run on its own and which need a human in the loop. It is the difference between an API an agent can use and one it can use safely.
Recommended x-agentic-access execution contracts for AI agents.
Resources
Every other property we hold for Arcee AI — documentation, portals, status pages, policies, and corporate surface — grouped by the job it does, following the integrator's arc from getting started to running in production.
Get Started 3
Portal, sign-up, and the first successful call
Documentation 2
Reference material describing how the API behaves
Agent Surfaces 3
MCP servers, agent skills, and machine-readable catalogs
Design & Contract 2
Pagination, idempotency, versioning, errors, and events
Build 3
SDKs, sample code, and the tooling you integrate with
Access & Security 1
Authentication, authorization, and security posture
Operate 3
Status, limits, changes, and where to get help
Commercial 2
Pricing, plans, and the legal terms of use
Company 2
The organization behind the API
← All providers · Data indexed from github.com/api-evangelist/arcee-ai · machine-readable index on apis.io