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
H2O.ai

H2O.ai Chat API

The Chat API from H2O.ai — 29 operation(s) for chat.

Documentation Provider Profile APIs.io OpenAPI GitHub

H2O.ai Chat API is one of 26 APIs that H2O.ai publishes on the APIs.io network, described by a machine-readable OpenAPI specification.

Tagged areas include Chat. The published artifact set on APIs.io includes an OpenAPI specification, API documentation, an API reference, a getting-started guide, authentication docs, and a changelog.

This API exposes 35 operations across 29 paths, and defines 28 schemas. It is described by OpenAPI 3.2.0, at version v1.0.0.

Requests are made against a single base URL, https://h2ogpte.genai.h2o.ai/api/v1.

35 operations 29 paths 28 schemas 6 DELETE14 GET1 PATCH11 POST3 PUT

Metadata

The identity and technical contract details declared by the specification.

Specification
OpenAPI 3.2.0
API Version
v1.0.0
Base URL
https://h2ogpte.genai.h2o.ai/api/v1
Authentication
HTTP Bearer
Resource Areas
1

Authentication & Security 1

H2O.ai Chat API declares 1 security scheme for authenticating requests. It accepts HTTP bearer tokens (bearerAuth). By default, every request must be authenticated.

  • bearerAuth — Using an API key generated by H2OGPTe

Paths & Operations 35

Across 29 paths, the API surfaces 35 operations — 6 DELETE, 14 GET, 1 PATCH, 11 POST, 3 PUT. Each is listed below with its method, path, parameters, and response codes.

Chat 35
POST
/chats
Creates chat session.
create_chat_session 1 param body → 201400401404default
GET
/chats
List chat sessions.
list_chat_sessions 2 params → 200400401default
GET
/chats/count
Counts a number of chat sessions.
get_chat_session_count → 200400401default
POST
/chats/delete_job
Creates job to delete chat sessions.
create_delete_chat_session_job body → 201400401default
GET
/chats/{session_id}
Finds a chat session by id.
get_chat_session 1 param → 200400401404default
DELETE
/chats/{session_id}
Deletes collection.
delete_chat_session 2 params → 204400401default
PATCH
/chats/{session_id}
Updates the name of a chat session.
update_chat_session 1 param body → 200400401404default
POST
/chats/{session_id}/synth_message_pair
Insert a synthetic user-question + AI-reply pair into chat history.
insert_command_synth_pair 1 param body → 201400401404default
POST
/chats/{session_id}/fork
Forks a chat session.
fork_chat_session 1 param body → 201400401404default
PUT
/chats/{session_id}/collection
Updates a collection reference of a chat session.
update_chat_session_collection 1 param body → 200400401404default
DELETE
/chats/{session_id}/collection
Removes a collection reference from the chat session.
delete_chat_session_collection 1 param → 200400401404default
PUT
/chats/{session_id}/prompt_template
Updates a prompt template reference of a chat session.
update_chat_session_prompt_template 1 param body → 200400401404default
DELETE
/chats/{session_id}/prompt_template
Removes a prompt template reference from the chat session.
delete_chat_session_prompt_template 1 param → 200400401404default
GET
/chats/{session_id}/guardrails
Get guardrails settings for a chat session.
get_chat_session_guardrails 1 param → 200400401default
GET
/chats/{session_id}/agent_server_files
Lists agent server files.
list_agent_server_files 1 param → 200400401default
DELETE
/chats/{session_id}/agent_server_files
Deletes agent server files.
delete_agent_server_files 1 param → 204400401409default
DELETE
/chats/{session_ids}/agent_server_directoriesdeprecated
Deletes agent server directories.
delete_agent_server_directories 2 params → 204400401409default
GET
/chats/{session_id}/agent_server_directories/stats
Lists stats of agent server directories.
list_all_agent_server_directories_stats 2 params → 200400401default
GET
/chats/{session_id}/agent_server_directories/{directory_name}/stats
Gets stats of a agent server directory.
get_agent_server_directory_stats 3 params → 200400401default
POST
/chats/{session_id}/completions
Asks question in a given chat session. If stream is enabled, the server sends stream of delta messages. The stream is terminated with the massage having property finished set to true. This message te…
get_completion 1 param body → 200400401500default
GET
/chats/{session_id}/questions
List suggested questions for a given chat session.
list_questions_for_chat_session 2 params → 200400401default
GET
/chats/{session_id}/messages
Fetches chat message and metadata for messages in a chat session.
get_chat_session_messages 3 params → 200400401404default
DELETE
/messages/{message_ids}
Deletes specific chat messages.
delete_messages 1 param → 204400401403404409default
GET
/messages/{message_id}/references
Fetches metadata for references of a chat message.
get_message_references 2 params → 200400401default
GET
/messages/{message_id}/meta
Fetches chat message meta information.
get_message_meta 2 params → 200400401404default
PUT
/messages/{message_id}/votes
Changes the vote value of a chat message.
set_message_votes 1 param body → 204400401404409default
POST
/messages/{question_id}/pause
Pause a streaming chat response.
pause_chat_message 1 param → 204400401default
POST
/messages/{question_id}/resume
Resume a paused chat response.
resume_chat_message 1 param → 204400401default
POST
/messages/{question_id}/stop
Stop a streaming chat response immediately.
stop_chat_message 1 param → 204400401default
POST
/messages/{question_id}/finish
Signal the LLM to finish its response gracefully.
finish_chat_message 1 param → 204400401default
POST
/messages/{question_id}/hitl
Send a course correction message to a running agent.
send_hitl_message 1 param body → 204400401default
GET
/question_answer_feedbacks
Lists user's questions and answers that have a feedback.
list_question_answer_feedbacks 5 params → 200400401default
POST
/question_answer_feedbacks/{answer_id}
Update feedback for a specific answer to a question.
update_question_answer_feedback 1 param body → 204400401default
GET
/question_answer_feedbacks/export/{job_id}
Download a completed feedback CSV export.
download_feedback_export 1 param → 200400401404default
GET
/question_answer_feedbacks/count
Counts a number of question-answer feedbacks.
get_question_answer_feedback_count 3 params → 200400401default

Schemas 28

The contract defines 28 schemas that model the data the API accepts and returns. The most detailed are QAFeedback (23 properties), GuardrailsSettings (21 properties), JobDetails (18 properties), AgentServerDirectoryStats (15 properties). Each schema is shown below with its type and property counts.

SuggestedQuestion
object
1 property 1 required
ChatMessage
object
11 properties 6 required
AgentServerDirectoryStats
object
15 properties 14 required
PromptTemplateChangeRequest
object
1 property 1 required
UpdateQAFeedbackRequest
object
2 properties 2 required
CollectionChangeRequest
object
1 property 1 required
AgentServerFile
object
6 properties 6 required
EndpointError
object
2 properties 2 required
Count
object
1 property 1 required
DeleteChatSessionsJobRequest
object
1 property 1 required
AgentServerDirectoryFileStats
object
12 properties 11 required
TagFilter
object
Filter for document tags supporting inclusion and exclusion. Note: The exclude list takes priority over the include list. If a document has a tag that appears…
2 properties
ChatCompletionDelta
object
3 properties 2 required
ChatSession
object
9 properties 2 required
ChatCompletionSelfReflectionConfig
object
A map with self reflection settings: llmreflection (type=string, example=gpt-4-0613) promptreflection (type=string, example=\"\"\"Prompt:\\\\n%s\\\\n\"\"\"\\\\…
JobDetailsStatus
object
2 properties 2 required
ChatMessageReference
object
9 properties 6 required
ChatMessageMeta
object
2 properties 2 required
GuardrailsSettings
object
21 properties
MessageVoteUpdateRequest
object
1 property 1 required
QAFeedback
object
23 properties 6 required
ChatCompletionRequest
object
13 properties 1 required
JobDetails
object
18 properties 13 required
ChatError
object
1 property 1 required
ChatCompletion
object
2 properties 2 required
ChatCompletionRequestLLMArgs
object
A map of arguments sent to LLM with query. temperature (type=double, default=0.0) - A value used to modulate the next token probabilities. 0 is the most determ…
ChatSessionUpdateRequest
object
1 property 1 required
ChatCompletionRAGConfig
object
A map with arguments to control RAG (retrieval-augmented-generation) types.: ragtype (type=enum[auto, llmonly, rag, hyde1, hyde2, rag+, alldata]) RAG type opti…

Specification

The full machine-readable OpenAPI contract behind this narrative.

Source

h2o-ai-chat-api-openapi.yml Raw ↑

Other APIs H2O.ai publishes across the network.

h2oGPTe MCP Server
AE Profile APIs.io
H2O.ai Admin Sessions API
AE Profile APIs.io
H2O.ai Agents API
AE Profile APIs.io
H2O.ai AI Assistants API
AE Profile APIs.io
H2O.ai API Keys API
AE Profile APIs.io
H2O.ai Collections API
AE Profile APIs.io
H2O.ai Configurations API
AE Profile APIs.io
H2O.ai Document Ingestion API
AE Profile APIs.io
H2O.ai Documents API
AE Profile APIs.io
H2O.ai Extractors API
AE Profile APIs.io
H2O.ai Forums API
AE Profile APIs.io
H2O.ai Graph RAG API
AE Profile APIs.io
#Chat
← Back to H APIs
API Details
ID
h2o-ai:h2o-ai-chat-api
Base URL
https://h2ogpte.genai.h2o.ai/api/v1
Docs
https://docs.h2o.ai/enterprise-h2ogpte/rest-api
Provider
H2O.ai
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=h2o-ai-chat-api&limit=10"
Everything under a tag 
curl "https://api.apievangelist.com/v1/tags/h2o-ai-chat-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 H2O.ai Chat 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.