EvalGate Evaluations API

The evaluations API from EvalGate — 89 operation(s) for evaluations.

GitHub OpenAPI

Operations 126

GET /api/evaluations/{id}/agent-workflows Get evaluations agent workflows #
POST /api/evaluations/{id}/agent-workflows Create evaluations agent workflows #
GET /api/evaluations/{id}/alerts Get evaluations alerts #
POST /api/evaluations/{id}/artifacts/{artifactId}/accept Create evaluations accept #
DELETE /api/evaluations/{id}/artifacts/{artifactId} Delete evaluations artifactId #
GET /api/evaluations/{id}/artifacts Get evaluations artifacts #
POST /api/evaluations/{id}/artifacts Create evaluations artifacts #
GET /api/evaluations/{id}/auto-readiness Get evaluations auto readiness #
GET /api/evaluations/{id}/auto-sessions/{sessionId}/anti-gaming Get evaluations anti gaming #
GET /api/evaluations/{id}/auto-sessions/{sessionId}/experiments/compare Get evaluations compare #
GET /api/evaluations/{id}/auto-sessions/{sessionId}/experiments Get evaluations experiments #
GET /api/evaluations/{id}/auto-sessions/{sessionId}/ikb Get evaluations ikb #
GET /api/evaluations/{id}/auto-sessions/{sessionId}/ledger Get evaluations ledger #
GET /api/evaluations/{id}/auto-sessions/{sessionId}/rounds Get evaluations rounds #
POST /api/evaluations/{id}/auto-sessions/{sessionId}/run Create evaluations run #
GET /api/evaluations/{id}/auto-sessions/{sessionId}/status Get evaluations status #
POST /api/evaluations/{id}/auto-sessions/{sessionId}/stop Create evaluations stop #
GET /api/evaluations/{id}/auto-sessions Get evaluations auto sessions #
POST /api/evaluations/{id}/auto-sessions Create evaluations auto sessions #
GET /api/evaluations/{id}/calibration Get evaluations calibration #
POST /api/evaluations/{id}/calibration Create evaluations calibration #
GET /api/evaluations/{id}/dataset-bindings Get evaluations dataset bindings #
POST /api/evaluations/{id}/dataset-bindings Create evaluations dataset bindings #
POST /api/evaluations/{id}/failure-memory/{entryId}/quarantine Create evaluations quarantine #
POST /api/evaluations/{id}/failure-memory/{entryId}/trust Create evaluations trust #
GET /api/evaluations/{id}/failure-memory/audit Get evaluations audit #
POST /api/evaluations/{id}/human-review/reviews Create evaluations reviews #
GET /api/evaluations/{id}/human-review Get evaluations human review #
POST /api/evaluations/{id}/human-review Create evaluations human review #
GET /api/evaluations/{id}/imported-verdict-authority Get evaluations imported verdict authority #
PUT /api/evaluations/{id}/imported-verdict-authority Replace evaluations imported verdict authority #
GET /api/evaluations/{id}/integrity Get evaluations integrity #
POST /api/evaluations/{id}/integrity Create evaluations integrity #
GET /api/evaluations/{id}/knowledge/{hintId} Get evaluations hintId #
PATCH /api/evaluations/{id}/knowledge/{hintId} Update evaluations hintId #
GET /api/evaluations/{id}/knowledge/health Get evaluations health #
POST /api/evaluations/{id}/knowledge/merge Create evaluations merge #
GET /api/evaluations/{id}/knowledge Get evaluations knowledge #
DELETE /api/evaluations/{id}/knowledge Delete evaluations knowledge #
GET /api/evaluations/{id}/labeled-cases List labeled cases for an evaluation #
POST /api/evaluations/{id}/labeled-cases Create a manual labeled case for an evaluation #
DELETE /api/evaluations/{id}/labeled-cases Delete evaluations labeled cases #
GET /api/evaluations/{id}/metrics Get evaluations metrics #
POST /api/evaluations/{id}/playground/assistant Create evaluations assistant #
POST /api/evaluations/{id}/playground/cases/from-trace Create evaluations from trace #
POST /api/evaluations/{id}/playground/cases/generate Create evaluations generate #
POST /api/evaluations/{id}/playground/cases/import Create evaluations import #
POST /api/evaluations/{id}/playground/cases Create evaluations cases #
GET /api/evaluations/{id}/playground/export Get evaluations export #
POST /api/evaluations/{id}/playground/promote-to-experiment Create evaluations promote to experiment #
POST /api/evaluations/{id}/playground/proposals/{proposalId} Create evaluations proposalId #
GET /api/evaluations/{id}/playground/proposals Get evaluations proposals #
GET /api/evaluations/{id}/playground Get evaluations playground #
POST /api/evaluations/{id}/playground Create evaluations playground #
PATCH /api/evaluations/{id}/playground Update evaluations playground #
POST /api/evaluations/{id}/playground/run-all Create evaluations run all #
POST /api/evaluations/{id}/playground/run-row Create evaluations run row #
POST /api/evaluations/{id}/playground/run-selection Create evaluations run selection #
POST /api/evaluations/{id}/playground/runs/{runId}/cancel Create evaluations cancel #
GET /api/evaluations/{id}/playground/runs Get evaluations runs #
POST /api/evaluations/{id}/playground/scorers/test Create evaluations test #
GET /api/evaluations/{id}/playground/variants/{variantId} Get evaluations variantId #
PATCH /api/evaluations/{id}/playground/variants/{variantId} Update evaluations variantId #
DELETE /api/evaluations/{id}/playground/variants/{variantId} Delete evaluations variantId #
POST /api/evaluations/{id}/playground/variants/{variantId}/set-baseline Create evaluations set baseline #
GET /api/evaluations/{id}/playground/variants Get evaluations variants #
POST /api/evaluations/{id}/playground/variants Create evaluations variants #
GET /api/evaluations/{id}/playground/winner Get evaluations winner #
POST /api/evaluations/{id}/playground/winner Create evaluations winner #
GET /api/evaluations/{id}/program Get evaluations program #
PUT /api/evaluations/{id}/program Replace evaluations program #
GET /api/evaluations/{id}/prompts/{promptId}/active Get evaluations active #
POST /api/evaluations/{id}/prompts/{promptId}/active Create evaluations active #
POST /api/evaluations/{id}/prompts/{promptId}/rollback Create evaluations rollback #
GET /api/evaluations/{id}/prompts/{promptId}/versions Get evaluations versions #
GET /api/evaluations/{id}/prompts Get evaluations prompts #
POST /api/evaluations/{id}/prompts Create evaluations prompts #
GET /api/evaluations/{id}/proposed-changes Get evaluations proposed changes #
POST /api/evaluations/{id}/publish-run Create evaluations publish run #
POST /api/evaluations/{id}/publish Create evaluations publish #
DELETE /api/evaluations/{id}/publish Delete evaluations publish #
POST /api/evaluations/{id}/regression Create evaluations regression #
PUT /api/evaluations/{id}/regression Replace evaluations regression #
GET /api/evaluations/{id}/report Get evaluations report #
POST /api/evaluations/{id}/report Create evaluations report #
GET /api/evaluations/{id} Get evaluations id #
PATCH /api/evaluations/{id} Update evaluations id #
DELETE /api/evaluations/{id} Delete evaluations id #
POST /api/evaluations/{id}/runs/{runId}/analyze Create evaluations analyze #
POST /api/evaluations/{id}/runs/{runId}/candidates Prepare a regression candidate from verified executed failure evidence #
POST /api/evaluations/{id}/runs/{runId}/cluster Create evaluations cluster #
GET /api/evaluations/{id}/runs/{runId}/dataset-snapshots Get evaluations dataset snapshots #
POST /api/evaluations/{id}/runs/{runId}/dataset Create evaluations dataset #
POST /api/evaluations/{id}/runs/{runId}/debug Create evaluations debug #
GET /api/evaluations/{id}/runs/{runId}/diff/{compareRunId} Get evaluations compareRunId #
POST /api/evaluations/{id}/runs/{runId}/evidence Create evaluations evidence #
GET /api/evaluations/{id}/runs/{runId}/export Get evaluations export #
GET /api/evaluations/{id}/runs/{runId}/progress Get evaluations progress #
GET /api/evaluations/{id}/runs/{runId} Get evaluations runId #
POST /api/evaluations/{id}/runs/import Create evaluations import #
GET /api/evaluations/{id}/runs Get evaluations runs #
POST /api/evaluations/{id}/runs Create evaluations runs #
GET /api/evaluations/{id}/schedule Get evaluations schedule #
POST /api/evaluations/{id}/schedule Create evaluations schedule #
PATCH /api/evaluations/{id}/schedule Update evaluations schedule #
DELETE /api/evaluations/{id}/schedule Delete evaluations schedule #
POST /api/evaluations/{id}/synthetic-candidates/{candidateId}/promote Create evaluations promote #
POST /api/evaluations/{id}/synthetic-candidates/{candidateId}/review Create evaluations review #
GET /api/evaluations/{id}/synthetic-candidates Get evaluations synthetic candidates #
POST /api/evaluations/{id}/test-cases/{testCaseId}/activate Activate a reviewed test case #
POST /api/evaluations/{id}/test-cases/{testCaseId}/archive Create evaluations archive #
POST /api/evaluations/{id}/test-cases/{testCaseId}/deprecate Create evaluations deprecate #
POST /api/evaluations/{id}/test-cases/{testCaseId}/restore Create evaluations restore #
PUT /api/evaluations/{id}/test-cases/{testCaseId} Replace evaluations testCaseId #
DELETE /api/evaluations/{id}/test-cases/{testCaseId} Delete evaluations testCaseId #
POST /api/evaluations/{id}/test-cases/{testCaseId}/supersede Create evaluations supersede #
GET /api/evaluations/{id}/test-cases Get evaluations test cases #
POST /api/evaluations/{id}/test-cases Create evaluations test cases #
DELETE /api/evaluations/{id}/test-cases Delete evaluations test cases #
GET /api/evaluations/{id}/versions Get evaluations versions #
POST /api/evaluations/{id}/versions Create evaluations versions #
GET /api/evaluations List evaluations evaluations #
POST /api/evaluations Create evaluations evaluations #
PUT /api/evaluations Replace evaluations evaluations #
DELETE /api/evaluations Delete evaluations evaluations #

Work with this as data

Every API here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for apis

7 MCP tools reach this
  • find_apisBrowse and filter every API in the catalog.
  • get_api_artifactsOne API's artifacts, grouped by type.
  • get_openapiThe primary OpenAPI for this API.
  • find_similar_apisAPIs that look like this one.
  • apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
  • resolveTurn a domain, URL or GitHub org into the provider it belongs to.
  • find_cohortsEvery scored population of providers in the catalog.
All 92 tools →

Call it yourself

curl for this page
This API
curl "https://apis.io/api/v1/apis/evalgate-com:evalgate-com-evaluations-api"
All apis
curl "https://apis.io/api/v1/apis?limit=25"

Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

A second provider on the same verified email joins the account you already have.

OpenAPI Specification

evalgate-com-evaluations-api-openapi.yml Raw ↑
openapi: 3.2.0
info:
  title: EvalGate Evaluations API
  version: 18.13.0
  description: EvalGate API. See docs/api-contract.md for stability commitments.
servers:
- url: https://evalgate.com
  description: Production
- url: http://localhost:3000
  description: Local
tags:


# --- truncated at 32 KB (2765 KB total) ---
# Full source: https://artifacts.apis.io/evalgate-com/openapi/evalgate-com-evaluations-api-openapi.yml