Gentrace website screenshot

Gentrace

Gentrace was a developer platform for evaluating and testing LLM and AI applications ("evals as infrastructure"). It provided pipelines, datasets, experiments, and test cases so teams could run offline and online evaluations, grade model outputs, track regressions, and observe AI features in production via OpenTelemetry-based instrumentation. The platform shipped a REST API (v4) secured with bearer API keys, first-party Python and TypeScript/Node SDKs, and a documented object model of pipelines, datasets, experiments, and test cases. Gentrace was based in San Francisco and backed by Matrix Partners. The company has since shut down its hosted product, but its OpenAPI specification, SDK packages, and documentation mirror remain publicly available.

Gentrace publishes 4 APIs on the APIs.io network, including Datasets API, Experiments API, Pipelines API, and 1 more. Tagged areas include Company, Ai, LLM, Evaluation, and Testing.

Gentrace’s developer surface includes authentication, documentation, API reference, and 15 more developer resources.

33.0/100 thin ▬ flat Agent 39/100 agent ready Full breakdown ↓
scored 2026-08-10 · rubric v0.9.1
AccessSelf serve
4 APIs 1 MCP Servers
CompanyAiLLMEvaluationTestingObservabilityMachine LearningDeveloper Tools

Kin Score

Kin Score Kin Score How this is scored →
scored 2026-08-10 · rubric v0.9.1
Composite quality — 33.0/100 · thin
Contract Quality 15.5 / 25
Developer Ergonomics 7.3 / 20
Commercial Clarity 0.0 / 20
Operational Transparency 0.7 / 13
Governance 1.4 / 12
Discoverability 8.2 / 10
Agent readiness — 39/100 · agent ready
Machine-Readable Contract 18 / 18
Agentic Access Contract 10 / 10
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 0 / 4
Consent & Bot Identity 0 / 3
A2A Agent Card 0 / 8
Dry-Run / Simulate Mode 0 / 4
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/gentrace: 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 4

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

Gentrace Datasets API

The Datasets API from Gentrace — 2 operation(s) for datasets.

Gentrace Experiments API

The Experiments API from Gentrace — 2 operation(s) for experiments.

Gentrace Pipelines API

The Pipelines API from Gentrace — 2 operation(s) for pipelines.

Gentrace TestCases API

The TestCases API from Gentrace — 2 operation(s) for testcases.

MCP Servers 1

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

gentrace-mcp.yml

MCP SERVER

Security Posture 2

Authentication, domain security, vulnerability disclosure, and trust-center signals.

Gentrace Authentication

http · 1 scheme

SECURITY

Gentrace Domain Security

TLSv1.3 · DMARC

SECURITY

Agentic Access 1

Recommended x-agentic-access execution contracts for AI agents.

Gentrace Agentic Access

16 operations · 8 acting

16 operations · 8 acting

AGENTIC

Resources

Documentation 2

Reference material describing how the API behaves

Agent Surfaces 4

MCP servers, agent skills, and machine-readable catalogs

Design & Contract 5

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

Company 1

The organization behind the API

Other 1

Properties that don't map to a standard resource type

Source (apis.yml)

apis.yml Raw ↑
aid: gentrace
name: Gentrace
description: Gentrace was a developer platform for evaluating and testing LLM and AI applications ("evals as infrastructure").
  It provided pipelines, datasets, experiments, and test cases so teams could run offline and online evaluations, grade model
  outputs, track regressions, and observe AI features in production via OpenTelemetry-based instrumentation. The platform
  shipped a REST API (v4) secured with bearer API keys, first-party Python and TypeScript/Node SDKs, and a documented object
  model of pipelines, datasets, experiments, and test cases. Gentrace was based in San Francisco and backed by Matrix Partners.
  The company has since shut down its hosted product, but its OpenAPI specification, SDK packages, and documentation mirror
  remain publicly available.
url: https://raw.githubusercontent.com/api-evangelist/gentrace/refs/heads/main/apis.yml
x-type: company
x-source: vc-portfolio
x-backed-by:
- matrix-partners
x-tier: stub
x-tier-reason: portfolio-lead
x-status: shutdown
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: '2026-07-19'
image: https://mintcdn.com/gentrace/9dIPysEl4JbHm2X9/logo/dark.svg
tags:
- Company
- Ai
- LLM
- Evaluation
- Testing
- Observability
- Machine Learning
- Developer Tools
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com
- FN: APIs.json
  email: info@apis.io
apis:
- aid: gentrace:gentrace-datasets-api
  name: Gentrace Datasets API
  description: The Datasets API from Gentrace — 2 operation(s) for datasets.
  humanURL: https://gentrace.ai
  baseURL: https://gentrace.ai/api
  tags:
  - Datasets
  properties:
  - type: OpenAPI
    url: openapi/gentrace-datasets-api-openapi.yml
  - type: Documentation
    url: https://docs.gentrace.ai
  - type: APIReference
    url: https://docs.gentrace.ai/reference
- aid: gentrace:gentrace-experiments-api
  name: Gentrace Experiments API
  description: The Experiments API from Gentrace — 2 operation(s) for experiments.
  humanURL: https://gentrace.ai
  baseURL: https://gentrace.ai/api
  tags:
  - Experiments
  properties:
  - type: OpenAPI
    url: openapi/gentrace-experiments-api-openapi.yml
  - type: Documentation
    url: https://docs.gentrace.ai
  - type: APIReference
    url: https://docs.gentrace.ai/reference
- aid: gentrace:gentrace-pipelines-api
  name: Gentrace Pipelines API
  description: The Pipelines API from Gentrace — 2 operation(s) for pipelines.
  humanURL: https://gentrace.ai
  baseURL: https://gentrace.ai/api
  tags:
  - Pipelines
  properties:
  - type: OpenAPI
    url: openapi/gentrace-pipelines-api-openapi.yml
  - type: Documentation
    url: https://docs.gentrace.ai
  - type: APIReference
    url: https://docs.gentrace.ai/reference
- aid: gentrace:gentrace-testcases-api
  name: Gentrace TestCases API
  description: The TestCases API from Gentrace — 2 operation(s) for testcases.
  humanURL: https://gentrace.ai
  baseURL: https://gentrace.ai/api
  tags:
  - TestCases
  properties:
  - type: OpenAPI
    url: openapi/gentrace-testcases-api-openapi.yml
  - type: Documentation
    url: https://docs.gentrace.ai
  - type: APIReference
    url: https://docs.gentrace.ai/reference
common:
- type: DomainSecurity
  url: security/gentrace-domain-security.yml
- type: AgenticAccess
  url: agentic-access/gentrace-agentic-access.yml
- type: Authentication
  url: authentication/gentrace-authentication.yml
- type: Website
  url: https://gentrace.ai
- type: Documentation
  url: https://docs.gentrace.ai
- type: APIReference
  url: https://docs.gentrace.ai/reference
- type: GitHubOrganization
  url: https://github.com/gentrace
- type: Packages
  url: packages/gentrace-packages.yml
- type: SDKs
  url: packages/gentrace-packages.yml
- type: ErrorCatalog
  url: errors/gentrace-problem-types.yml
- type: Conventions
  url: conventions/gentrace-conventions.yml
- type: DataModel
  url: data-model/gentrace-data-model.yml
- type: Overlay
  url: overlays/gentrace-openapi-overlay.yaml
- type: Conformance
  url: conformance/gentrace-conformance.yml
- type: MCPServer
  url: mcp/gentrace-mcp.yml
- type: LLMsTxt
  url: llms/gentrace-llms.txt
- type: Lifecycle
  url: lifecycle/gentrace-lifecycle.yml
- type: AgentSkill
  url: skills/_index.yml
x-enrichment:
  date: '2026-07-19'
  status: backfilled
  pass: local-v1
  note: backfilled from .gitignore signal + verified work evidence