Contextual AI

Contextual AI is an enterprise RAG platform built around a Grounded Language Model (GLM) engineered to minimize hallucinations. Its REST API exposes end-to-end RAG agents (create, configure, query) plus standalone component APIs - Generate, Rerank, Parse, and LMUnit - over datastores of ingested documents, all authenticated with a Bearer API key.

7 APIs 0 Features

AIRAGLLMGrounded Language ModelEnterprise

APIs

Contextual AI Agents API

Create, configure, edit, copy, reset, and delete enterprise RAG agents, including system prompts, suggested queries, templates, and associated datastores.

Contextual AI Agent Query API

Query an agent for grounded responses with inline attributions, retrieval contents, and groundedness scores; supports SSE token streaming via stream=true, retrievals-only mode, ...

Contextual AI Datastores & Documents API

Create and manage datastores and ingest documents (PDF, HTML, DOC(X), PPT(X), images) with custom metadata; list, retrieve, update, and delete documents and their parsed chunks.

Contextual AI Generate API

Standalone grounded generation with the Grounded Language Model (GLM v1/v2) - responses are grounded in supplied knowledge to minimize hallucinations, with a 32,000-token reques...

Contextual AI Rerank API

Instruction-following reranker (ctxl-rerank-v2 multilingual / mini and v1) that reorders retrieved passages by relevance, steerable with natural-language instructions on recency...

Contextual AI Parse API

Asynchronous document parsing that converts PDFs, Office files, and images into AI-ready markdown with inferred hierarchy and positional metadata; submit a job, then poll status...

Contextual AI LMUnit Evaluation API

Evaluate model responses with fine-grained natural-language unit tests, returning a continuous 1-5 score for criteria such as conciseness, technical precision, and groundedness.

Event Specifications

Contextual AI Agent Query Streaming (HTTP + SSE)

AsyncAPI 2.6 description of Contextual AI's **agent query streaming** surface. Contextual AI does not publish a WebSocket API. The only asynchronous / event-style transport docu...

ASYNCAPI

Visuals

Resources

👥

GitHubOrganization

Sources

aid: contextual-ai
url: https://raw.githubusercontent.com/api-evangelist/contextual-ai/refs/heads/main/apis.yml
name: Contextual AI
kind: company
description: Contextual AI is an enterprise RAG platform built around a Grounded
  Language Model (GLM) engineered to minimize hallucinations. Its REST API exposes
  end-to-end RAG agents (create, configure, query) plus standalone component APIs -
  Generate, Rerank, Parse, and LMUnit - over datastores of ingested documents, all
  authenticated with a Bearer API key.
image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
tags:
- AI
- RAG
- LLM
- Grounded Language Model
- Enterprise
created: '2026-06-20'
modified: '2026-06-20'
specificationVersion: '0.19'
apis:
- aid: contextual-ai:contextual-ai-agents-api
  name: Contextual AI Agents API
  tags:
  - Agents
  - RAG
  - Configuration
  image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
  humanURL: https://docs.contextual.ai/api-reference/agents/create-agent
  baseURL: https://api.contextual.ai/v1
  properties:
  - url: https://docs.contextual.ai/user-guides/beginner-guide
    type: Documentation
  - url: https://docs.contextual.ai/api-reference/agents/create-agent
    type: APIReference
  - url: openapi/contextual-ai-openapi.yml
    type: OpenAPI
  - url: collections/contextual-ai.postman_collection.json
    type: PostmanCollection
  description: Create, configure, edit, copy, reset, and delete enterprise RAG agents,
    including system prompts, suggested queries, templates, and associated datastores.
- aid: contextual-ai:contextual-ai-agent-query-api
  name: Contextual AI Agent Query API
  tags:
  - Query
  - RAG
  - Grounded
  - Streaming
  image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
  humanURL: https://docs.contextual.ai/api-reference/agents-query/query
  baseURL: https://api.contextual.ai/v1
  properties:
  - url: https://docs.contextual.ai/api-reference/agents-query/query
    type: Documentation
  - url: https://docs.contextual.ai/api-reference/agents-query/query
    type: APIReference
  - url: openapi/contextual-ai-openapi.yml
    type: OpenAPI
  - url: asyncapi/contextual-ai-asyncapi.yml
    type: AsyncAPI
  - url: collections/contextual-ai.postman_collection.json
    type: PostmanCollection
  description: Query an agent for grounded responses with inline attributions, retrieval
    contents, and groundedness scores; supports SSE token streaming via stream=true,
    retrievals-only mode, conversation continuity, and feedback.
- aid: contextual-ai:contextual-ai-datastores-api
  name: Contextual AI Datastores & Documents API
  tags:
  - Datastores
  - Documents
  - Ingestion
  image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
  humanURL: https://docs.contextual.ai/api-reference/datastores/create-datastore
  baseURL: https://api.contextual.ai/v1
  properties:
  - url: https://docs.contextual.ai/api-reference/datastores/create-datastore
    type: Documentation
  - url: https://docs.contextual.ai/api-reference/datastores-documents/ingest-document
    type: APIReference
  - url: openapi/contextual-ai-openapi.yml
    type: OpenAPI
  - url: collections/contextual-ai.postman_collection.json
    type: PostmanCollection
  description: Create and manage datastores and ingest documents (PDF, HTML, DOC(X),
    PPT(X), images) with custom metadata; list, retrieve, update, and delete documents
    and their parsed chunks.
- aid: contextual-ai:contextual-ai-generate-api
  name: Contextual AI Generate API
  tags:
  - Generate
  - Grounded Language Model
  - Generation
  image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
  humanURL: https://docs.contextual.ai/api-reference/generate/generate
  baseURL: https://api.contextual.ai/v1
  properties:
  - url: https://docs.contextual.ai/api-reference/generate/generate
    type: Documentation
  - url: https://docs.contextual.ai/api-reference/generate/generate
    type: APIReference
  - url: openapi/contextual-ai-openapi.yml
    type: OpenAPI
  - url: collections/contextual-ai.postman_collection.json
    type: PostmanCollection
  description: Standalone grounded generation with the Grounded Language Model (GLM
    v1/v2) - responses are grounded in supplied knowledge to minimize hallucinations,
    with a 32,000-token request limit.
- aid: contextual-ai:contextual-ai-rerank-api
  name: Contextual AI Rerank API
  tags:
  - Rerank
  - Retrieval
  - Instruction Following
  image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
  humanURL: https://docs.contextual.ai/api-reference/rerank/rerank
  baseURL: https://api.contextual.ai/v1
  properties:
  - url: https://docs.contextual.ai/how-to-guides/rerank
    type: Documentation
  - url: https://docs.contextual.ai/api-reference/rerank/rerank
    type: APIReference
  - url: openapi/contextual-ai-openapi.yml
    type: OpenAPI
  - url: collections/contextual-ai.postman_collection.json
    type: PostmanCollection
  description: Instruction-following reranker (ctxl-rerank-v2 multilingual / mini and
    v1) that reorders retrieved passages by relevance, steerable with natural-language
    instructions on recency, document type, or source.
- aid: contextual-ai:contextual-ai-parse-api
  name: Contextual AI Parse API
  tags:
  - Parse
  - Document Parsing
  - OCR
  image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
  humanURL: https://docs.contextual.ai/api-reference/parse/parse-file
  baseURL: https://api.contextual.ai/v1
  properties:
  - url: https://docs.contextual.ai/how-to-guides/parse
    type: Documentation
  - url: https://docs.contextual.ai/api-reference/parse/parse-file
    type: APIReference
  - url: openapi/contextual-ai-openapi.yml
    type: OpenAPI
  - url: collections/contextual-ai.postman_collection.json
    type: PostmanCollection
  description: Asynchronous document parsing that converts PDFs, Office files, and
    images into AI-ready markdown with inferred hierarchy and positional metadata;
    submit a job, then poll status and results (basic text or standard multimodal).
- aid: contextual-ai:contextual-ai-lmunit-api
  name: Contextual AI LMUnit Evaluation API
  tags:
  - LMUnit
  - Evaluation
  - Unit Testing
  image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
  humanURL: https://docs.contextual.ai/api-reference/lmunit/lmunit
  baseURL: https://api.contextual.ai/v1
  properties:
  - url: https://docs.contextual.ai/how-to-guides/lmunit
    type: Documentation
  - url: https://docs.contextual.ai/api-reference/lmunit/lmunit
    type: APIReference
  - url: openapi/contextual-ai-openapi.yml
    type: OpenAPI
  - url: collections/contextual-ai.postman_collection.json
    type: PostmanCollection
  description: Evaluate model responses with fine-grained natural-language unit tests,
    returning a continuous 1-5 score for criteria such as conciseness, technical
    precision, and groundedness.
common:
- type: GitHubOrganization
  url: https://github.com/ContextualAI
- type: LinkedIn
  url: https://www.linkedin.com/company/contextual-ai
- type: Website
  url: https://contextual.ai/
- type: Documentation
  url: https://docs.contextual.ai
- type: Plans
  url: plans/contextual-ai-plans-pricing.yml
- type: RateLimits
  url: rate-limits/contextual-ai-rate-limits.yml
- type: FinOps
  url: finops/contextual-ai-finops.yml
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com