Update Model Catalog Entry

Endpoint

PUT /apiops/projects/{projectName}/llm-models/{modelName}/

Authentication

Requires a Personal API Access Token.

Header

Authorization: Bearer YOUR_TOKEN

Request

Headers

Header	Value	Required
Authorization	Bearer {token}	Yes
Content-Type	application/json	Yes

Path Parameters

Parameter	Type	Required	Description
projectName	string	Yes	Project name
modelName	string	Yes	Model catalog entry name. If the body name is blank it falls back to this value; otherwise the two must match (case-insensitive)

Query Parameters

None

Request Body

Full JSON Body Example

{
  "name": "openai/gpt-5-mini",
  "providerDefinitionId": "6640aa12c2e4b8000000ef01",
  "providerCode": "openai",
  "modelId": "gpt-5-mini",
  "displayName": "GPT-5 Mini",
  "contextWindow": 128000,
  "maxOutputTokens": 32768,
  "pricePerMillionInput": 0.20,
  "pricePerMillionOutput": 1.80,
  "pricePerMillionCached": 0.020,
  "pricePerImage": null,
  "pricePerAudioMinute": null,
  "pricePerCharacterTts": null,
  "capabilities": ["chat", "function_calling", "json_mode", "reasoning"],
  "modality": "TEXT",
  "isDeprecated": false,
  "deprecatedAt": null,
  "sunsetAt": null,
  "builtIn": false
}

Request Body Fields

Field	Type	Required	Default	Description
name	string	No	path value	Catalog name in \{providerCode\}/\{modelId\} form. If blank, the modelName path parameter is used; otherwise it must match the path
providerDefinitionId	string	No	-	Reference to the owning LLM provider definition
providerCode	string	Yes	-	Provider code (e.g. openai). Required for custom entries
modelId	string	Yes	-	Provider-facing model identifier (e.g. gpt-5-mini). Required for custom entries
displayName	string	No	-	Human-readable label
contextWindow	integer	No	-	Context window size in tokens
maxOutputTokens	integer	No	-	Maximum output tokens; omit to use the provider default
pricePerMillionInput	number	No	-	USD per 1M input tokens
pricePerMillionOutput	number	No	-	USD per 1M output tokens
pricePerMillionCached	number	No	-	USD per 1M cached input tokens
pricePerImage	number	No	-	USD per generated image
pricePerAudioMinute	number	No	-	USD per minute of audio (STT)
pricePerCharacterTts	number	No	-	USD per input character (TTS)
capabilities	array[string]	No	-	Capability tags (e.g. chat, function_calling, vision, embedding, json_mode, reasoning)
modality	string	No	-	Model modality: TEXT, VISION, AUDIO, EMBEDDING, RERANK, MULTIMODAL, IMAGE
isDeprecated	boolean	No	false	Whether the model is deprecated
deprecatedAt	string	No	-	Deprecation announcement time (ISO-8601)
sunsetAt	string	No	-	Planned removal time (ISO-8601)
builtIn	boolean	No	false	See the built-in note below.

Notes

• Entry must exist: Unlike POST (upsert), PUT requires the named entry to already exist in the project, otherwise a 400 is returned.
• Name fallback: If name is blank in the body, the modelName path parameter is used. If both are present they must match (case-insensitive).
• id / projectId are server-managed: The existing entry's id is reused and the entry stays scoped to the path project — a projectId change in the body is rejected (cross-project transfer guard).
• Built-in entries (builtIn=true): Only the price fields (pricePerMillionInput/Output/Cached, pricePerImage, pricePerAudioMinute, pricePerCharacterTts) are applied; all other fields (name, limits, capabilities, modality) are preserved from the seed.

Response

Success Response (200 OK)

{
  "status": "SUCCESS",
  "deploymentResult": {
    "success": true
  }
}

Response Fields

Field	Type	Description
status	string	Response status: SUCCESS or FAILURE
deploymentResult	object	Result of the update operation
deploymentResult.success	boolean	Whether the operation completed successfully

Error Response (400 Bad Request)

{
  "status": "FAILURE",
  "resultMessage": "Model catalog entry (name: openai/gpt-5-mini) was not found!"
}

or

{
  "status": "FAILURE",
  "resultMessage": "Model catalog entry name in path (openai/gpt-5-mini) does not match name in body (openai/gpt-5)!"
}

Error Response (401 Unauthorized)

{
  "status": "FAILURE",
  "resultMessage": "Token is not valid!"
}

cURL Example

curl -X PUT \
  "https://demo.apinizer.com/apiops/projects/MyProject/llm-models/openai%2Fgpt-5-mini/" \
  -H "Authorization: Bearer YOUR_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "openai/gpt-5-mini",
    "providerCode": "openai",
    "modelId": "gpt-5-mini",
    "displayName": "GPT-5 Mini",
    "contextWindow": 128000,
    "maxOutputTokens": 32768,
    "pricePerMillionInput": 0.20,
    "pricePerMillionOutput": 1.80,
    "pricePerMillionCached": 0.020,
    "capabilities": ["chat", "function_calling", "json_mode", "reasoning"],
    "modality": "TEXT",
    "builtIn": false
  }'

Notes and Warnings

• Create vs update: Use Create Model Catalog Entry (POST) if you want create-or-update (upsert) semantics; PUT fails when the entry does not exist.
• Built-in price-only edit: For builtIn=true entries, editing anything other than the price fields has no effect — the seed values are authoritative for structure and capabilities.
• Name form: The catalog name uses the {providerCode}/{modelId} format. URL-encode the / as %2F in the path.
• No secret fields: The catalog carries no @SecretData fields and no _class discriminator — nothing is masked, and there is no blank-secret-preservation behaviour.

Related Documentation

• Create Model Catalog Entry - Create or upsert an entry
• Delete Model Catalog Entry - Delete a custom entry
• Model Catalog API - Resource overview
• Authentication Guide - How to obtain and use API tokens
• Error Handling - Error response formats