> ## Documentation Index
> Fetch the complete documentation index at: https://docs.praxis-ai.com/llms.txt
> Use this file to discover all available pages before exploring further.
# Create a new AI model
> Creates a new AI model configuration. The handler validates the `client_library` / `api_url` / `api_key` combination via `validateAIModelConfig` before saving — openai_cli requires both `api_url` and `api_key`; mistral_cli and xai_cli require `api_key`; bedrock_cli requires neither (uses AWS credentials). When `institution` is omitted, the caller's institution is used.
## OpenAPI
````yaml /mdx/api-reference/admin/admin-api.json post /api/admin/aimodel
openapi: 3.0.0
info:
title: Pria Admin API
version: 2.0.1
description: >-
Pria API Documentation Praxis's developer platform is a core part of our
mission to empower organizations to grow better. Our APIs are designed to
enable teams of any shape or size to build robust integrations that help
them customize and get the most value out of Pria. All Pria APIs are built
using REST conventions and designed to have a predictable URL structure.
They use many standard HTTP features, including methods (POST,
GET, PUT, DELETE) and error response codes.
All API calls are
made under https://hiimpria.ai/api and all responses return standard JSON.
In these docs, you'll find lists of all available endpoints for a given API,
along with interactive code blocks for building requests. For walkthroughs
of basic usage for these APIs, check out the API guides.
servers:
- url: https://pria.praxislxp.com
description: Pria API Server
security: []
tags:
- name: Authentication
description: User authentication, registration, and password management (/api/auth)
- name: OAuth
description: OAuth authentication providers - Google, GitHub, SSO (/api/auth/oauth)
- name: User
description: User profile management and account operations (/api/user)
- name: User Institutions
description: User institution memberships and switching (/api/user/institution)
- name: User Tools
description: Available tools for authenticated users (/api/user/tools)
- name: Institutions
description: Institution settings and configuration (/api/user/institution)
- name: Conversation
description: AI conversation and Q&A endpoints (/api/ai)
- name: Realtime
description: Real-time voice AI and WebRTC sessions (/api/ai/rt)
- name: Assistant
description: AI assistant configuration and management (/api/user/assistant)
- name: History
description: Conversation history and favorites (/api/user/history)
- name: RAG
description: >-
Document upload, embedding, and retrieval-augmented generation
(/api/user/files, /api/user/rag)
- name: Setting
description: Instance variables and settings management (/api/user/setting)
- name: Branding
description: Digital twin branding and customization (/api/agent/branding)
- name: Agent
description: Agent engagement and session management (/api/agent)
- name: SDK Launch
description: >-
SDK launch token signing and verification for secure iframe embedding
(/api/auth/sdk-sign, /api/auth/sdk-verify)
- name: Testing
description: Health checks, diagnostics, and test endpoints (/api/test)
- name: Admin Accounts
description: Account management for super admins (/api/admin/account)
- name: Admin Institutions
description: Institution management for admins (/api/admin/institution)
- name: Admin Users
description: User management for admins (/api/admin/user)
- name: Admin Entitlements
description: >-
User-institution relationships and permissions
(/api/admin/userInstitution)
- name: Admin Sessions
description: Session management for admins (/api/admin/session)
- name: Admin Histories
description: Conversation history management and analytics (/api/admin/history)
- name: Admin Assistants
description: AI assistant management for admins (/api/admin/assistant)
- name: Admin Questions
description: Institution question and prompt management (/api/admin/question)
- name: Admin Tools
description: Tool configuration management (/api/admin/tool)
- name: Admin AI Models
description: AI model configuration (/api/admin/aimodel)
- name: Admin MCP Servers
description: Model Context Protocol server management (/api/admin/mcpserver)
- name: Admin Feedbacks
description: User feedback management (/api/admin/feedback)
- name: Admin Uploads
description: Upload management (/api/admin/upload)
- name: Admin Charts
description: Analytics and visualization chart management (/api/admin/chart)
- name: Admin Memory
description: Admin inspection and editing of user/instance memory parameters.
- name: Admin Usage Limits
description: Per-user usage-vs-cap reporting and account-wide at-limit counts.
paths:
/api/admin/aimodel:
post:
tags:
- Admin AI Models
summary: Create a new AI model
description: >-
Creates a new AI model configuration. The handler validates the
`client_library` / `api_url` / `api_key` combination via
`validateAIModelConfig` before saving — openai_cli requires both
`api_url` and `api_key`; mistral_cli and xai_cli require `api_key`;
bedrock_cli requires neither (uses AWS credentials). When `institution`
is omitted, the caller's institution is used.
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/AIModelCreateRequest'
responses:
'201':
description: AI model created successfully
content:
application/json:
schema:
$ref: '#/components/schemas/AIModelCreateResponse'
'400':
description: >-
Missing properties, invalid api_url / api_key for the chosen
client_library, duplicate name, or other validation failure.
'401':
description: Authentication required / invalid request.
'403':
description: Caller is not an admin or super user.
security:
- apiKeyAuth: []
components:
schemas:
AIModelCreateRequest:
type: object
required:
- name
properties:
name:
type: string
description: Model name (must be unique per institution + model_use).
institution:
type: string
description: Institution ID. Defaults to the caller's institution when omitted.
model_use:
type: string
enum:
- conversationModel
- imageGenerationModel
- audioGenerationModel
- videoGenerationModel
- imageAnalysisModel
- embeddingsModel
- audioAnalysisModel
- videoAnalysisModel
- ttsModel
- summaryModel
- rtModel
- moderationModel
default: conversationModel
description:
type: string
client_library:
type: string
enum:
- openai_cli
- anthropic_cli
- bedrock_cli
- google_cli
- mistral_cli
- xai_cli
- stability_cli
default: openai_cli
description: SDK / dispatch backend used to talk to the provider.
api_url:
type: string
description: Provider base URL. Required for openai_cli custom models.
api_key:
type: string
description: >-
Provider API key. Required for openai_cli, mistral_cli, and xai_cli
custom models.
default_headers:
type: object
additionalProperties:
type: string
features:
$ref: '#/components/schemas/AIModelFeatures'
input_media:
$ref: '#/components/schemas/AIModelInputMedia'
output_media:
$ref: '#/components/schemas/AIModelOutputMedia'
max_input_tokens:
type: integer
default: 128000
max_output_tokens:
type: integer
default: 64000
reasoning_effort:
type: string
enum:
- none
- low
- medium
- high
- max
nullable: true
extended_context:
type: boolean
default: false
status:
type: string
enum:
- active
- inactive
default: active
picture_url:
type: string
AIModelCreateResponse:
type: object
properties:
success:
type: boolean
id:
type: string
description: The new AI model's ObjectId.
message:
type: string
example: AIModel created!
AIModelFeatures:
type: object
description: Capability flags advertised by the model.
properties:
stream:
type: boolean
default: false
description: Supports streaming responses.
tools:
type: boolean
default: false
description: Supports tool / function calling.
code:
type: boolean
default: false
description: Supports a built-in code-execution tool.
vision:
type: boolean
default: false
description: Supports image inputs.
mcp:
type: boolean
default: false
description: Supports Model Context Protocol tool servers.
AIModelInputMedia:
type: object
description: Input modalities the model accepts.
properties:
text:
type: boolean
default: true
image:
type: boolean
default: false
audio:
type: boolean
default: false
video:
type: boolean
default: false
pdf:
type: boolean
default: false
AIModelOutputMedia:
type: object
description: Output modalities the model can produce.
properties:
text:
type: boolean
default: true
audio:
type: boolean
default: false
video:
type: boolean
default: false
image:
type: boolean
default: false
securitySchemes:
apiKeyAuth:
type: apiKey
in: header
name: x-access-token
description: JWT token passed in x-access-token header
````