Skip to main content
POST
/
assets
/
models
Create Model
curl --request POST \
  --url https://api.example.com/assets/models \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "credentials": {
    "api_key": "sk-..."
  },
  "litellm_model": "openai/gpt-4o",
  "mode": "chat",
  "name": "GPT-4o",
  "provider": "openai",
  "tags": [
    "production",
    "openai"
  ]
}
'
{
  "id": "<string>",
  "resource_uri": "<string>",
  "name": "<string>",
  "litellm_model": "<string>",
  "organization_id": "<string>",
  "project_id": "<string>",
  "owner_id": "<string>",
  "created_at": "2023-11-07T05:31:56Z",
  "updated_at": "2023-11-07T05:31:56Z",
  "created_by": "<string>",
  "updated_by": "<string>",
  "description": "<string>",
  "tags": [],
  "provider": "<string>",
  "api_base": "<string>",
  "api_version": "<string>",
  "max_input_tokens": 123,
  "max_output_tokens": 123,
  "rpm": 123,
  "tpm": 123,
  "default_temperature": 123,
  "default_max_tokens": 123,
  "timeout": 123,
  "status_message": "<string>"
}

Authorizations

​
Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Headers

​
X-Project-ID
string | null

Body

application/json

Request body for creating a model configuration.

​
name
string
required
Required string length: 1 - 255
​
litellm_model
string
required
Required string length: 1 - 500
​
credentials
Credentials · object
required

Credentials for the model provider. Stored as secrets.

​
resource_uri
string | null

Custom kebab-case name for the resource URI. Auto-generated from name if omitted.

Pattern: ^[a-z0-9-]+$
​
provider
string | null
Maximum string length: 100
​
description
string | null
Maximum string length: 1000
​
tags
string[]
​
api_base
string | null
Maximum string length: 1000
​
api_version
string | null
Maximum string length: 50
​
mode
enum<string> | null

Supported model modes.

Available options:
chat,
completion,
embedding,
image_generation,
audio_transcription
​
max_input_tokens
integer | null
​
max_output_tokens
integer | null
​
rpm
integer | null
​
tpm
integer | null
​
default_temperature
number | null
Required range: 0 <= x <= 9.99
​
default_max_tokens
integer | null
​
timeout
integer | null

Response

Successful Response

Full model representation.

​
id
string
required
​
resource_uri
string
required
​
name
string
required
​
litellm_model
string
required
​
status
enum<string>
required

Status of a model configuration.

Available options:
PENDING,
ACTIVE,
ERROR,
DEPRECATED,
DISABLED
​
organization_id
string
required
​
project_id
string
required
​
owner_id
string
required
deprecated

Deprecated: use created_by instead. Will be removed in a future release.

​
created_at
string<date-time>
required
​
updated_at
string<date-time>
required
​
created_by
string
required
​
updated_by
string
required
​
description
string | null
​
tags
string[]
​
provider
string | null
​
api_base
string | null
​
api_version
string | null
​
mode
enum<string> | null

Supported model modes.

Available options:
chat,
completion,
embedding,
image_generation,
audio_transcription
​
max_input_tokens
integer | null
​
max_output_tokens
integer | null
​
rpm
integer | null
​
tpm
integer | null
​
default_temperature
number | null
​
default_max_tokens
integer | null
​
timeout
integer | null
​
status_message
string | null