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 Agent API

The Agent API from Helicone — 8 operation(s) for agent.

Documentation Provider Profile APIs.io OpenAPI GitHub

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

Tagged areas include Agents. 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 9 operations across 8 paths, and defines 35 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/.

9 operations 8 paths 35 schemas 1 DELETE2 GET6 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 Agent 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 9

Across 8 paths, the API surfaces 9 operations — 1 DELETE, 2 GET, 6 POST. Each is listed below with its method, path, parameters, and response codes.

Agent 9
POST
/v1/agent/generate
Generate body → 200
POST
/v1/agent/thread/{sessionId}/message
UpsertThreadMessage 1 param body → 200
DELETE
/v1/agent/thread/{sessionId}
DeleteThread 1 param → 200
GET
/v1/agent/thread/{sessionId}
GetThread 1 param → 200
POST
/v1/agent/thread/{sessionId}/escalate
EscalateThread 1 param → 200
POST
/v1/agent/thread/create-and-escalate
CreateAndEscalateThread → 200
POST
/v1/agent/thread/{sessionId}/reopen
ReopenThread 1 param → 200
GET
/v1/agent/threads
GetAllThreads → 200
POST
/v1/agent/mcp/search
SearchDocs body → 200

Schemas 35

The contract defines 35 schemas that model the data the API accepts and returns. The most detailed are OpenAIChatRequest (31 properties), InAppThread (9 properties), ChatCompletion (8 properties), ThreadSummary (8 properties). Each schema is shown below with its type and property counts.

Record_string.string_
object
Construct a type with a set of properties K of type T
CompletionUsage.CompletionTokensDetails
object
Breakdown of tokens used in a completion.
4 properties
ResultSuccess_ChatCompletion-or-_content-string--reasoning-string--calls-any__
object
2 properties 2 required
ChatCompletionMessageCustomToolCall.Custom
object
The custom tool that the model called.
2 properties 2 required
InAppThread
object
9 properties 9 required
OpenAIChatRequest
object
Simplified interface for the OpenAI Chat request format
31 properties
CompletionUsage.PromptTokensDetails
object
Breakdown of tokens used in the prompt.
2 properties
Result_InAppThread.string_
ChatCompletionMessageToolCall
A call to a function tool created by the model.
Record_string.any_
object
Construct a type with a set of properties K of type T
ChatCompletionMessage.Annotation.URLCitation
object
A URL citation when using web search.
4 properties 4 required
ChatCompletionMessageFunctionToolCall
object
A call to a function tool created by the model.
3 properties 3 required
ResultSuccess_string_
object
2 properties 2 required
ResultError_string_
object
2 properties 2 required
Result__success-boolean_.string_
ChatCompletionMessageCustomToolCall
object
A call to a custom tool created by the model.
3 properties 3 required
ThreadSummary
object
8 properties 5 required
CompletionUsage
object
Usage statistics for the completion request.
5 properties 3 required
ChatCompletion
object
Represents a chat completion response returned by model, based on the provided input.
8 properties 5 required
ChatCompletionAudio
object
If the audio output modality is requested, this object contains data about the audio response from the model. [Learn more](https://platform.openai.com/docs/gui…
4 properties 4 required
ChatCompletionMessage
object
A chat completion message generated by the model.
7 properties 3 required
Result_ChatCompletion-or-_content-string--reasoning-string--calls-any_.string_
ChatCompletion.Choice
object
4 properties 4 required
ChatCompletion.Choice.Logprobs
object
Log probability information for the choice.
2 properties 2 required
ChatCompletionMessage.FunctionCall
object
2 properties 2 required
ResultSuccess_ThreadSummary-Array_
object
2 properties 2 required
Record_string.number_
object
Construct a type with a set of properties K of type T
ChatCompletionMessageFunctionToolCall.Function
object
The function that the model called.
2 properties 2 required
ChatCompletionTokenLogprob
object
4 properties 4 required
Result_ThreadSummary-Array.string_
ChatCompletionMessage.Annotation
object
A URL citation when using web search.
2 properties 2 required
ChatCompletionTokenLogprob.TopLogprob
object
3 properties 3 required
ResultSuccess_InAppThread_
object
2 properties 2 required
Result_string.string_
ResultSuccess__success-boolean__
object
2 properties 2 required

Specification

The full machine-readable OpenAPI contract behind this narrative.

Source

helicone-agent-api-openapi.yml Raw ↑

Other APIs Helicone publishes across the network.

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 Experiment 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
#Agents
← Back to H APIs
API Details
ID
helicone:helicone-agent-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-agent-api&limit=10"
Everything under a tag 
curl "https://api.apievangelist.com/v1/tags/helicone-agent-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 Agent 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.