Understudy Labs
Understudy Labs (YC S26) is an LLM gateway and model-optimization platform that helps teams move repeated production LLM workloads onto open-weight models they own. The Understudy gateway is a drop-in replacement for the Anthropic and OpenAI API endpoints that captures request/response traces by project and workload, routes measured slices of traffic to managed open models, and falls back safely. A REST control plane manages keys, projects, workloads, routing, captures, evaluation cohorts, and reporting, while the MIT-licensed understudy-agent-tools repo ships a CLI, a coding-agent skill library, a local MCP server, and Understudy Desktop with a documented loopback OpenAPI 3.1 contract.
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 Understudy Labs the way a machine reads it — 18 machine-readable artifacts across 12 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 — Understudy Labs scores 47.2/100 (developing), with a separate agent-readiness read of 69/100 (agent native). 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 Understudy Labs
Each block below is one kind of artifact we hold for Understudy Labs. 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 12
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.
Understudy Gateway API
Anthropic- and OpenAI-compatible LLM proxy at api.understudylabs.com. POST /v1/messages (Anthropic Messages), POST /v1/chat/completions (OpenAI Chat Completions), POST /v1/messa...
Understudy Control Plane API
REST surface behind the dashboard and CLI, served from the gateway host under /admin/v1 and /customer/v1, org-scoped and authenticated with sk_* bearer keys. Covers API key mint...
Understudy Labs Capabilities API
The Capabilities API from Understudy Labs — 1 operation(s) for capabilities.
Understudy Labs Conversations API
The Conversations API from Understudy Labs — 1 operation(s) for conversations.
Understudy Labs Downloads API
The Downloads API from Understudy Labs — 3 operation(s) for downloads.
Understudy Labs Feedback API
The Feedback API from Understudy Labs — 1 operation(s) for feedback.
Understudy Labs Metrics API
The Metrics API from Understudy Labs — 1 operation(s) for metrics.
Understudy Labs Models API
The Models API from Understudy Labs — 2 operation(s) for models.
Understudy Labs Residency API
The Residency API from Understudy Labs — 6 operation(s) for residency.
Understudy Labs Runs API
The Runs API from Understudy Labs — 2 operation(s) for runs.
Understudy Labs Status API
The Status API from Understudy Labs — 1 operation(s) for status.
Understudy Labs Supervision API
The Supervision API from Understudy Labs — 1 operation(s) for supervision.
Scroll within the panel for all 12 ·
Arazzo Workflows 2
Real integrations are rarely a single call. Arazzo describes the multi-step sequences — auth, then create, then confirm — so both a human and an agent can follow the choreography, not just the endpoints.
Multi-step API workflows described with the Arazzo specification.
_Index
ARAZZODownload, warm, and chat with a local model on Understudy Desktop
The core Understudy Desktop journey over the loopback Agent API - pick a model from the catalog, start and track its download, add a residency slot, assign and warm the model in...
ARAZZOMCP 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.
understudy-labs-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 Understudy Labs — 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 5
MCP servers, agent skills, and machine-readable catalogs
Design & Contract 6
Pagination, idempotency, versioning, errors, and events
Build 3
SDKs, sample code, and the tooling you integrate with
Access & Security 2
Authentication, authorization, and security posture
Operate 2
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/understudy-labs · machine-readable index on apis.io