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 Models API

The Models API from H2O.ai — 19 operation(s) for models.

Documentation Provider Profile APIs.io OpenAPI GitHub

H2O.ai Models 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 Models. 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 20 operations across 19 paths, and defines 18 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.

20 operations 19 paths 18 schemas 1 DELETE12 GET7 POST

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 Models 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 20

Across 19 paths, the API surfaces 20 operations — 1 DELETE, 12 GET, 7 POST. Each is listed below with its method, path, parameters, and response codes.

Models 20
POST
/collections/{collection_id}/topic_model
Creates a topic model on the collection.
create_topic_model 2 params → 204400401default
DELETE
/collections/{collection_id}/topic_model
Deletes the topic model from the collection.
delete_topic_model 1 param → 204400401default
GET
/models
Lists all available large language models.
list_models → 200400401default
GET
/embedding_models
Lists all available embedding models.
list_embedding_models → 200400401default
GET
/embedding_models/default
Gets default embedding model.
get_default_embedding_model → 200400401404default
POST
/embedding_models/{model_id}/encode_chunks_for_retrieval
Encode texts for semantic searching.
encode_chunks_for_retrieval 1 param body → 200400401default
POST
/models/{model_name}/self_test/{mode}
Runs a self-test for a given model.
run_model_self_test 2 params → 200400401default
POST
/models/{model_name}/answer_question
Send a message and get a response from an LLM.
answer_question 1 param body → 200400401default
POST
/models/{model_name}/summarize_content
Summarize one or more contexts using an LLM.
summarize_content 1 param body → 200400401default
POST
/models/{model_name}/extract_data
Extract information from one or more contexts using an LLM.
extract_data 1 param body → 200400401default
GET
/models/vision_capable_model_names
Lists names of available vision-capable multi-modal LLMs in the environment.
get_vision_capable_model_names → 200400401default
GET
/models/model_to_vision_model_mapping
Get mapping of llm to its visionmodel when ["auto"] is passed as visiblevisionmodels.
get_model_to_vision_model_mapping → 200400401default
GET
/models/reasoning_capable_model_names
Lists names of available reasoning-capable (that can natively reason) in the environment.
get_reasoning_capable_model_names → 200400401default
GET
/models/model_to_reasoning_model_mapping
Get mapping of llm to its reasoningmodel when ["auto"] is passed as visiblereasoningmodels.
get_model_to_reasoning_model_mapping → 200400401default
POST
/guardrails_settings
Helper to get reasonable (easy to use) defaults for Guardrails/PII settings.
create_guardrails_settings body → 200400401default
GET
/stats/usage
Returns usage statistics for all models.
get_usage_stats 1 param → 200400401default
GET
/stats/usage_by_model
Returns usage statistics grouped by models.
get_usage_stats_by_model 1 param → 200400401default
GET
/stats/usage_by_user
Returns usage statistics grouped by users.
get_usage_stats_by_user 1 param → 200400401default
GET
/stats/usage_by_model_and_user
Returns usage statistics grouped by models and users.
get_usage_stats_by_model_and_user 1 param → 200400401default
GET
/stats/performance_by_model
Returns performance statistics grouped by models.
get_performance_stats_by_model 1 param → 200400401default

Schemas 18

The contract defines 18 schemas that model the data the API accepts and returns. The most detailed are GuardrailsSettings (21 properties), QuestionRequest (9 properties), SelfTestResult (8 properties), SummarizeRequest (7 properties). Each schema is shown below with its type and property counts.

ModelAnswer
object
7 properties 3 required
UsageStatsPerModel
object
5 properties 5 required
EmbeddingModel
object
4 properties 4 required
EndpointError
object
2 properties 2 required
ExtractionRequest
object
7 properties
ModelUsageStatsPerUser
object
7 properties 7 required
UsageStatsPerUser
object
4 properties 4 required
ModelExtractionAnswer
object
5 properties 3 required
Model
object
2 properties 2 required
GuardrailsSettings
object
21 properties
UsageStatsPerModelAndUser
object
6 properties 6 required
PerformanceStatsPerModel
object
6 properties 6 required
QuestionRequest
object
9 properties 1 required
GuardrailsSettingsCreateRequest
object
5 properties
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…
SummarizeRequest
object
7 properties
SelfTestResult
object
8 properties 6 required
UsageStats
object
4 properties 4 required

Specification

The full machine-readable OpenAPI contract behind this narrative.

Source

h2o-ai-models-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 Chat 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
#Models
← Back to H APIs
API Details
ID
h2o-ai:h2o-ai-models-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-models-api&limit=10"
Everything under a tag 
curl "https://api.apievangelist.com/v1/tags/h2o-ai-models-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 Models 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.