Bespoke Labs

Bespoke Labs is an applied AI research lab building environment infrastructure, data curation, and evaluation tooling for AI agents and post-training. Its open-source Bespoke Curator library generates high-quality synthetic data at scale for model finetuning and structured extraction, and its Bespoke MiniCheck ("Argus") API offers a lightweight grounded-factuality / hallucination-detection service that scores whether a claim is supported by a given context. The lab is also known for OpenThoughts reasoning datasets, Terminal-Bench, the GEPA prompt optimizer, MiniChart, and OpenThinker. Backed by 8VC, Mayfield, and Wing Venture Capital.

Bespoke Labs publishes 1 API on the APIs.io network: Minicheck API. Tagged areas include Company, Artificial Intelligence, Machine Learning, LLM, and Synthetic Data.

Bespoke Labs’ developer surface includes authentication, documentation, API reference, getting-started guide, signup flow, support, engineering blog, and 19 more developer resources.

🌐 Visit website 📡 Source on GitHub

43.7/100 thin ▬ flat Agent 69/100 agent native Full breakdown ↓
scored 2026-07-28 · rubric v0.5

AccessSelf serve

1 APIs 1 MCP Servers

CompanyArtificial IntelligenceMachine LearningLLMSynthetic DataData CurationFact CheckingHallucination DetectionAI AgentsEvaluation

Kin Score

Kin Score How this is scored →
scored 2026-07-28 · rubric v0.5

Composite quality — 43.7/100 · thin

Contract Quality 12.2 / 25

Developer Ergonomics 14.8 / 20

Commercial Clarity 6.8 / 20

Operational Transparency 0.7 / 13

Governance 0.0 / 12

Discoverability 9.3 / 10

Agent readiness — 69/100 · agent native

Machine-Readable Contract 18 / 18

Agentic Access Contract 15 / 15

MCP Server 12 / 12

Machine-Readable Auth 10 / 10

Idempotency 0 / 9

Stable Error Semantics 8 / 8

Request/Response Examples 0 / 7

Rate-Limit Signaling 0 / 7

Typed Event Surface 0 / 6

Agent Skills 5 / 5

Well-Known Catalog 4 / 4

Consent & Bot Identity 0 / 3

Improve this rating by publishing the missing artifacts — every area above can be raised, and the full rubric is at apis.io/rating/. This rating is computed from github.com/api-evangelist/bespoke-labs: open an issue to ask a question, or submit a pull request to add artifacts. Want it done for you? Prioritized profiling — $2,500 →

APIs 1

Individual APIs this provider publishes, each with its own machine-readable definition.

Bespoke Labs Minicheck API

The Minicheck API from Bespoke Labs — 1 operation(s) for minicheck.

MCP Servers 1

Model Context Protocol servers that expose these APIs to AI agents.

AGENTIC

Resources

Get Started 3

Portal, sign-up, and the first successful call

DeveloperPortal

DeveloperPortal

GettingStarted

GettingStarted

SignUp

SignUp

Documentation 2

Reference material describing how the API behaves

Documentation

Documentation

APIReference

APIReference

Agent Surfaces 5

MCP servers, agent skills, and machine-readable catalogs

AgenticAccess

WellKnown

MCPServer

LLMsTxt

AgentSkill

Design & Contract 5

Pagination, idempotency, versioning, errors, and events

Conformance

ErrorCatalog

Lifecycle

Conventions

DataModel

Build 3

SDKs, sample code, and the tooling you integrate with

Packages

Packages

SDKs

SDKs

GitHubOrganization

GitHubOrganization

Access & Security 2

Authentication, authorization, and security posture

Authentication

Authentication

DomainSecurity

DomainSecurity

Operate 2

Status, limits, changes, and where to get help

Support

Support

Community

Community

Commercial 2

Pricing, plans, and the legal terms of use

TermsOfService

TermsOfService

PrivacyPolicy

PrivacyPolicy

Company 2

The organization behind the API

Blog

Blog

Website

Website

Source (apis.yml)

aid: bespoke-labs
name: Bespoke Labs
description: Bespoke Labs is an applied AI research lab building environment infrastructure, data curation, and evaluation
  tooling for AI agents and post-training. Its open-source Bespoke Curator library generates high-quality synthetic data at
  scale for model finetuning and structured extraction, and its Bespoke MiniCheck ("Argus") API offers a lightweight grounded-factuality
  / hallucination-detection service that scores whether a claim is supported by a given context. The lab is also known for
  OpenThoughts reasoning datasets, Terminal-Bench, the GEPA prompt optimizer, MiniChart, and OpenThinker. Backed by 8VC, Mayfield,
  and Wing Venture Capital.
url: https://raw.githubusercontent.com/api-evangelist/bespoke-labs/refs/heads/main/apis.yml
x-type: company
x-source: vc-portfolio
x-backed-by:
- 8vc
- mayfield
- wing-venture-capital
x-tier: active
x-tier-reason: enriched-real-api
accessModel:
  pricing: unknown
  onboarding: self-serve
  trial: false
  try_now: false
  public: false
  label: Self-serve signup
  confidence: medium
  source:
  - authentication
  generated: '2026-07-22'
  method: derived
specificationVersion: '0.20'
created: '2026-07-17'
modified: '2026-07-18'
image: https://framerusercontent.com/images/3uXQTaKpkGh6gD7qAWsAwPMhk.png
tags:
- Company
- Artificial Intelligence
- Machine Learning
- LLM
- Synthetic Data
- Data Curation
- Fact Checking
- Hallucination Detection
- AI Agents
- Evaluation
apis:
- aid: bespoke-labs:bespoke-labs-minicheck-api
  name: Bespoke Labs Minicheck API
  description: The Minicheck API from Bespoke Labs — 1 operation(s) for minicheck.
  humanURL: https://docs.bespokelabs.ai/models/bespoke-minicheck/api
  baseURL: https://api.bespokelabs.ai
  tags:
  - Minicheck
  properties:
  - type: OpenAPI
    url: openapi/bespoke-labs-minicheck-api-openapi.yml
  - type: Documentation
    url: https://docs.bespokelabs.ai/models/bespoke-minicheck.md
  - type: APIReference
    url: https://docs.bespokelabs.ai/models/bespoke-minicheck/api
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com
- FN: APIs.json
  email: info@apis.io
common:
- type: AgenticAccess
  url: agentic-access/bespoke-labs-agentic-access.yml
- type: Authentication
  url: authentication/bespoke-labs-authentication.yml
- type: DomainSecurity
  url: security/bespoke-labs-domain-security.yml
- type: Packages
  url: packages/bespoke-labs-packages.yml
- type: SDKs
  url: packages/bespoke-labs-packages.yml
- type: WellKnown
  url: well-known/bespoke-labs-well-known.yml
- type: MCPServer
  url: mcp/bespoke-labs-mcp.yml
- type: LLMsTxt
  url: llms/bespoke-labs-llms.txt
- type: Conformance
  url: conformance/bespoke-labs-conformance.yml
- type: ErrorCatalog
  url: errors/bespoke-labs-problem-types.yml
- type: Lifecycle
  url: lifecycle/bespoke-labs-lifecycle.yml
- type: Conventions
  url: conventions/bespoke-labs-conventions.yml
- type: DataModel
  url: data-model/bespoke-labs-data-model.yml
- type: AgentSkill
  url: skills/_index.yml
- type: DeveloperPortal
  url: https://docs.bespokelabs.ai
- type: Documentation
  url: https://docs.bespokelabs.ai
- type: APIReference
  url: https://docs.bespokelabs.ai/models/bespoke-minicheck/api
- type: GettingStarted
  url: https://docs.bespokelabs.ai/bespoke-curator/getting-started
- type: SignUp
  url: https://console.bespokelabs.ai
- type: Support
  url: https://bespokelabs.ai/contact
- type: Community
  url: https://discord.com/invite/KqpXvpzVBS
- type: Blog
  url: https://bespokelabs.ai/blog
- type: GitHubOrganization
  url: https://github.com/bespokelabsai
- type: TermsOfService
  url: https://bespokelabs.ai/legal/terms-of-use
- type: PrivacyPolicy
  url: https://bespokelabs.ai/legal/privacy-policy
- type: Website
  url: https://bespokelabs.ai
x-enrichment:
  date: '2026-07-19'
  status: backfilled
  pass: local-v1
  note: backfilled from .gitignore signal + verified work evidence