How AI is applied across API Evangelist and APIs.io. Read my AI disclosure →
API Evangelist API Evangelist
Discovery
Learnings
Guidance
Toolbox
Alignment
API Evangelist LLC
Discovery
Learnings
Guidance
Toolbox
Alignment
API Evangelist LLC

Need help?

Contact us
Helicone

Helicone Experiment API

The Experiment API from Helicone — 40 operation(s) for experiment.

Documentation Provider Profile APIs.io OpenAPI GitHub

Helicone Experiment API is one of 33 APIs that Helicone publishes on the APIs.io network, described by a machine-readable OpenAPI specification.

Tagged areas include Experiment. The published artifact set on APIs.io includes an OpenAPI specification, API documentation, a getting-started guide, pricing, an API reference, and an engineering blog.

This API exposes 44 operations across 40 paths, and defines 72 schemas. It is described by OpenAPI 3.2.0, at version 1.0.0.

Requests are made against 2 base URLs: https://api.helicone.ai/, http://localhost:8585/.

44 operations 40 paths 72 schemas 6 DELETE9 GET1 PATCH28 POST

Metadata

The identity and technical contract details declared by the specification.

Specification
OpenAPI 3.2.0
API Version
1.0.0
Base URL
https://ai-gateway.helicone.ai
Authentication
API Key
License
MIT
Resource Areas
1

Authentication & Security 1

Helicone Experiment API declares 1 security scheme for authenticating requests. An API key is passed in the header as Authorization (api_key).

  • api_key — Bearer token authentication. Format: 'Bearer YOURAPIKEY'

Paths & Operations 44

Across 40 paths, the API surfaces 44 operations — 6 DELETE, 9 GET, 1 PATCH, 28 POST. Each is listed below with its method, path, parameters, and response codes.

Experiment 44
POST
/v2/experiment/create/empty
CreateEmptyExperiment → 200
POST
/v2/experiment/create/from-request/{requestId}
CreateExperimentFromRequest 1 param → 200
POST
/v2/experiment/new
CreateNewExperiment body → 200
GET
/v2/experiment
GetExperiments → 200
DELETE
/v2/experiment/{experimentId}
DeleteExperiment 1 param → 200
GET
/v2/experiment/{experimentId}
GetExperimentById 1 param → 200
POST
/v2/experiment/{experimentId}/prompt-version
CreateNewPromptVersionForExperiment 1 param body → 200
DELETE
/v2/experiment/{experimentId}/prompt-version/{promptVersionId}
DeletePromptVersion 2 params → 200
GET
/v2/experiment/{experimentId}/prompt-versions
GetPromptVersionsForExperiment 1 param → 200
GET
/v2/experiment/{experimentId}/input-keys
GetInputKeysForExperiment 1 param → 200
POST
/v2/experiment/{experimentId}/add-manual-row
AddManualRowToExperiment 1 param body → 200
POST
/v2/experiment/{experimentId}/add-manual-rows-batch
AddManualRowsToExperimentBatch 1 param body → 200
DELETE
/v2/experiment/{experimentId}/rows
DeleteExperimentTableRows 1 param body → 200
POST
/v2/experiment/{experimentId}/row/insert/batch
CreateExperimentTableRowBatch 1 param body → 200
POST
/v2/experiment/{experimentId}/row/insert/dataset/{datasetId}
CreateExperimentTableRowFromDataset 2 params → 200
POST
/v2/experiment/{experimentId}/row/update
UpdateExperimentTableRow 1 param body → 200
POST
/v2/experiment/{experimentId}/run-hypothesis
RunHypothesis 1 param body → 200
GET
/v2/experiment/{experimentId}/evaluators
GetExperimentEvaluators 1 param → 200
POST
/v2/experiment/{experimentId}/evaluators
CreateExperimentEvaluator 1 param body → 200
DELETE
/v2/experiment/{experimentId}/evaluators/{evaluatorId}
DeleteExperimentEvaluator 2 params → 200
POST
/v2/experiment/{experimentId}/evaluators/run
RunExperimentEvaluators 1 param → 200
GET
/v2/experiment/{experimentId}/should-run-evaluators
ShouldRunEvaluators 1 param → 200
GET
/v2/experiment/{experimentId}/{promptVersionId}/scores
GetExperimentPromptVersionScores 2 params → 200
GET
/v2/experiment/{experimentId}/{requestId}/{scoreKey}
GetExperimentScore 3 params → 200
POST
/v1/experiment/new-empty
CreateNewEmptyExperiment body → 200
POST
/v1/experiment/table/new
CreateNewExperimentTable body → 200
POST
/v1/experiment/table/{experimentTableId}/query
GetExperimentTableById 1 param → 200
POST
/v1/experiment/table/{experimentTableId}/metadata/query
GetExperimentTableMetadata 1 param → 200
POST
/v1/experiment/tables/query
GetExperimentTables → 200
POST
/v1/experiment/table/{experimentTableId}/cell
CreateExperimentCell 1 param body → 200
PATCH
/v1/experiment/table/{experimentTableId}/cell
UpdateExperimentCell 1 param body → 200
POST
/v1/experiment/table/{experimentTableId}/column
CreateExperimentColumn 1 param body → 200
POST
/v1/experiment/table/{experimentTableId}/row/new
CreateExperimentTableRow 1 param body → 200
DELETE
/v1/experiment/table/{experimentTableId}/row/{rowIndex}
DeleteExperimentTableRow 2 params → 200
POST
/v1/experiment/table/{experimentTableId}/row/insert/batch
CreateExperimentTableRowWithCellsBatch 1 param body → 200
POST
/v1/experiment/update-meta
UpdateExperimentMeta body → 200
POST
/v1/experiment
CreateNewExperimentOld body → 200
POST
/v1/experiment/hypothesis
CreateNewExperimentHypothesis body → 200
POST
/v1/experiment/hypothesis/{hypothesisId}/scores/query
GetExperimentHypothesisScores 1 param → 200
GET
/v1/experiment/{experimentId}/evaluators
GetExperimentEvaluators 1 param → 200
POST
/v1/experiment/{experimentId}/evaluators
CreateExperimentEvaluatorOld 1 param body → 200
POST
/v1/experiment/{experimentId}/evaluators/run
RunExperimentEvaluatorsOld 1 param → 200
DELETE
/v1/experiment/{experimentId}/evaluators/{evaluatorId}
DeleteExperimentEvaluatorOld 2 params → 200
POST
/v1/experiment/query
GetExperimentsOld body → 200

Schemas 72

The contract defines 72 schemas that model the data the API accepts and returns. The most detailed are PromptVersionResult (11 properties), ExperimentV2PromptVersion (11 properties), EvaluatorResult (9 properties), Experiment (8 properties). Each schema is shown below with its type and property counts.

ResultSuccess_ExperimentTable_
object
2 properties 2 required
Result_Experiment-Array.string_
Record_string.string_
object
Construct a type with a set of properties K of type T
ResultSuccess_Experiment-Array_
object
2 properties 2 required
Result_ScoreV2-or-null.string_
Result_ExperimentTable.string_
Result_PromptVersionResult.string_
RequestObj
object
2 properties 2 required
ExtendedExperimentData
object
7 properties 7 required
Result__hypothesisId-string_.string_
ExperimentTable
object
5 properties 4 required
ExperimentV2Row
object
5 properties 5 required
ExperimentDatasetRow
object
5 properties 5 required
ResultSuccess_PromptVersionResult_
object
2 properties 2 required
ExperimentV2
object
6 properties 6 required
ResultSuccess_ExperimentV2PromptVersion-Array_
object
2 properties 2 required
Pick_FilterLeaf.experiment_
object
From T, pick a set of properties whose keys are in the union K
1 property
ResultSuccess_null_
object
2 properties 2 required
ResultSuccess_Record_string.ScoreV2__
object
2 properties 2 required
ExperimentV2PromptVersion
object
11 properties 11 required
ResultSuccess_ScoreV2-or-null_
object
2 properties 2 required
Partial_TextOperators_
object
Make all properties in T optional
6 properties
Record_string.any_
object
Construct a type with a set of properties K of type T
ExperimentTableSimplified
object
6 properties 5 required
ResultSuccess_ExperimentTableSimplified_
object
2 properties 2 required
EvaluatorResult
object
9 properties 9 required
ResultSuccess_string_
object
2 properties 2 required
ResultError_string_
object
2 properties 2 required
Score
object
2 properties 2 required
ResultSuccess__tableId-string--experimentId-string__
object
2 properties 2 required
Result_ExtendedExperimentData.string_
ExperimentFilterNode
ResultSuccess_ExtendedExperimentData_
object
2 properties 2 required
Result_ExperimentTableSimplified.string_
ResultSuccess_ExperimentV2-Array_
object
2 properties 2 required
ResultSuccess_boolean_
object
2 properties 2 required
Result_null.string_
ResultSuccess_unknown_
object
2 properties 2 required
ResponseObj
object
8 properties 8 required
Json
NewExperimentParams
object
5 properties 4 required
CreateNewPromptVersionForExperimentParams
object
6 properties 2 required
Result_ExperimentV2PromptVersion-Array.string_
ResultSuccess__hypothesisId-string__
object
2 properties 2 required
Result__tableId-string--experimentId-string_.string_
Result__experimentId-string_.string_
Result_boolean.string_
Result_string-Array.string_
CreateExperimentTableParams
object
7 properties 6 required
PromptVersionResult
object
11 properties 8 required
FilterLeafSubset_experiment_
ExperimentTableColumn
object
6 properties 4 required
Record_string.ScoreV2_
object
Construct a type with a set of properties K of type T
IncludeExperimentKeys
object
4 properties
Result_Record_string.ScoreV2_.string_
Result_ExperimentV2-Array.string_
ResultSuccess_ExperimentTableSimplified-Array_
object
2 properties 2 required
Record_string.Score_
object
Construct a type with a set of properties K of type T
ResultSuccess__experimentId-string__
object
2 properties 2 required
ExperimentFilterBranch
object
3 properties 3 required
Partial_ExperimentToOperators_
object
Make all properties in T optional
2 properties
Result__runsCount-number--scores-Record_string.Score__.string_
ExperimentV2Output
object
6 properties 6 required
ResultSuccess__runsCount-number--scores-Record_string.Score___
object
2 properties 2 required
ScoreV2
object
4 properties 4 required
ExperimentScores
object
2 properties 2 required
Result_string.string_
ResultSuccess_string-Array_
object
2 properties 2 required
ResultSuccess_EvaluatorResult-Array_
object
2 properties 2 required
Result_EvaluatorResult-Array.string_
Result_ExperimentTableSimplified-Array.string_
Experiment
object
8 properties 8 required

Specification

The full machine-readable OpenAPI contract behind this narrative.

Source

helicone-experiment-api-openapi.yml Raw ↑

Other APIs Helicone publishes across the network.

Helicone Agent API
AE Profile APIs.io
Helicone API Key API
AE Profile APIs.io
Helicone Comparison API
AE Profile APIs.io
Helicone Credits API
AE Profile APIs.io
Helicone Customer API
AE Profile APIs.io
Helicone Dashboard API
AE Profile APIs.io
Helicone Dataset API
AE Profile APIs.io
Helicone Evals API
AE Profile APIs.io
Helicone Evaluator API
AE Profile APIs.io
Helicone HeliconeSql API
AE Profile APIs.io
Helicone Integration API
AE Profile APIs.io
Helicone Metrics API
AE Profile APIs.io
#Experiment
← Back to H APIs
API Details
ID
helicone:helicone-experiment-api
Base URL
https://ai-gateway.helicone.ai
Docs
https://www.helicone.ai/
Provider
Helicone
APIs.io →  GitHub →
Explore more
All APIs Providers APIs.io Network
Work with this as data

Every API here is available over the API and to AI agents over MCP. APIs is not yet its own endpoint on the v1 API. Reach this content through network search and the tag graph, or the MCP server below.

Installs https://mcp.apievangelist.com/mcp in Claude, Cursor, VS Code and the rest — one button, every client.

MCP tools for apis
4 tools reach this content
  • search_api_evangelistSearch every content type across the network at once.
  • find_relatedThe shared-tag relevance graph — what else covers this.
  • get_tagEverything one tag labels, across all content types.
  • guide_topicPRO — a curated bundle for a topic: area, guidance, rules, papers, stories, services.
All tools & prompts
Call it yourself
curl for this page
Search the network for this 
curl "https://api.apievangelist.com/v1/search?q=helicone-experiment-api&limit=10"
Everything under a tag 
curl "https://api.apievangelist.com/v1/tags/helicone-experiment-api"

Discovery needs no key. Full bodies and the synthesis endpoints are Pro.

Get an API key

Free tier, no email required. Sign in with whichever identity you already have.

GitHub Google LinkedIn

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

Where this information came from

This is an independent, third-party profile of Helicone Experiment API, published by API Evangelist. We do not operate, host, resell, or support these APIs, and we are not affiliated with or endorsed by the company unless stated above. Everything here is built from publicly available information — the company's own site, developer portal, documentation, public repositories, and the specifications it publishes for public use. Nothing is obtained by breaching a system, defeating an access control, or using credentials.

The Kin Score and Agent Readiness rating are independently calculated assessments of a company's public API artifacts, scored against a published rubric. They are not certifications, endorsements, security assessments, or audits.

Corrections, re-scores, and removal are free — no partnership or purchase required, and you do not need to justify the request. A removed company is recorded as unrated, never scored zero for having asked. Acknowledgement within one business day; removal within two.

info@apievangelist.com · Read the full data-sourcing policy →
On a security or compliance team? Put security in the subject line and you will get a person, not a form — we will tell you exactly which public URLs this profile was built from.