Skip to main content
PUT
/
api
/
admin
/
aimodel
/
{id}
Update AI model
curl --request PUT \
  --url https://pria.praxislxp.com/api/admin/aimodel/{id} \
  --header 'Content-Type: application/json' \
  --header 'x-access-token: <api-key>' \
  --data '
{
  "name": "<string>",
  "institution": "<string>",
  "description": "<string>",
  "api_url": "<string>",
  "api_key": "<string>",
  "default_headers": {},
  "features": {
    "stream": false,
    "tools": false,
    "code": false,
    "vision": false,
    "mcp": false
  },
  "input_media": {
    "text": true,
    "image": false,
    "audio": false,
    "video": false,
    "pdf": false
  },
  "output_media": {
    "text": true,
    "audio": false,
    "video": false,
    "image": false
  },
  "max_input_tokens": 123,
  "max_output_tokens": 123,
  "extended_context": true,
  "picture_url": "<string>"
}
'
{
  "success": true,
  "message": "User institution deleted successfully"
}

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.

Authorizations

​
x-access-token
string
header
required

JWT token passed in x-access-token header

Path Parameters

​
id
string
required

AI Model ID

Body

application/json

Partial update. Every field is optional; only the keys provided are written. The handler merges client_library / api_url / api_key with the stored document before re-validating, so you can update one field without resending the others.

​
name
string
​
institution
string
​
model_use
enum<string>
Available options:
conversationModel,
imageGenerationModel,
audioGenerationModel,
videoGenerationModel,
imageAnalysisModel,
embeddingsModel,
audioAnalysisModel,
ttsModel,
summaryModel,
rtModel,
moderationModel
​
description
string
​
client_library
enum<string>
Available options:
openai_cli,
anthropic_cli,
bedrock_cli,
google_cli,
mistral_cli,
xai_cli,
stability_cli,
lemonslice_cli
​
api_url
string
​
api_key
string
​
default_headers
object
​
features
object

Capability flags advertised by the model.

​
input_media
object

Input modalities the model accepts.

​
output_media
object

Output modalities the model can produce.

​
max_input_tokens
integer
​
max_output_tokens
integer
​
reasoning_effort
enum<string> | null
Available options:
none,
low,
medium,
high,
max
​
extended_context
boolean
​
status
enum<string>
Available options:
active,
inactive
​
picture_url
string

Response

AI model updated successfully

​
success
boolean
Example:

true

​
message
string

Success message

Example:

"User institution deleted successfully"