Create custom model

POST /api/models

Python

import requests

url = "https://api.keywordsai.co/api/models/"
headers = {
    "Authorization": "Bearer YOUR_API_KEY",
    "Content-Type": "application/json"
}
payload = {
    "model_name": "my-custom-gpt-4",
    "base_model_name": "gpt-4",
    "display_name": "My Custom GPT-4",
    "custom_provider_id": "my-azure-provider",
    "input_cost": 0.025,
    "output_cost": 0.075
}

response = requests.post(url, headers=headers, json=payload)
print(response.json())

201 Created

{
  "id": "my-custom-gpt-4",
  "model_name": "my-custom-gpt-4",
  "display_name": "My Custom GPT-4",
  "base_model_name": "gpt-4",
  "affiliation_category": "custom",
  "is_called_by_custom_name": false,
  "input_cost": 0.025,
  "output_cost": 0.075,
  "cache_hit_input_cost": 0.0,
  "cache_creation_input_cost": 0.0,
  "max_context_window": 8192,
  "streaming_support": 1,
  "function_call": 1,
  "image_support": 0,
  "source": "db",
  "provider": {
    "id": "my-custom-provider",
    "provider_id": "my-custom-provider",
    "provider_name": "My Custom Provider",
    "organization_id": 123
  }
}

Create a new custom model or update an existing one (upsert by model_name). Custom models allow you to define organization-specific configurations with custom pricing, capabilities, and provider associations.

Upsert behavior: If a model with the same model_name already exists in your organization, it will be updated with the new values.

Request body

model_name · string · required

Unique model name within your organization. This will be used to reference the model in API calls.

Example

"model_name": "my-custom-gpt-4"

base_model_name · string

Base model to inherit properties from. Can be a global model (e.g., "gpt-4") or another custom model.

Example

"base_model_name": "gpt-4"

display_name · string

Human-readable display name for the model.

Example

"display_name": "My Custom GPT-4"

custom_provider_id · integer | string

ID or provider_id of the custom provider to associate with this model. See Custom Providers.

Example

"custom_provider_id": "my-azure-provider"

provider_id · integer | string

Alternative to custom_provider_id. Either one can be used.

Pricing

input_cost · float

Cost per 1M input tokens in USD.

Example

"input_cost": 0.025

output_cost · float

Cost per 1M output tokens in USD.

Example

"output_cost": 0.075

cache_hit_input_cost · float

Cost per 1M cached input tokens in USD.

cache_creation_input_cost · float

Cost per 1M cache creation tokens in USD.

Capabilities

max_context_window · integer

Maximum context window size for the model.

Example

"max_context_window": 8192

streaming_support · integer

Streaming support. 0 for no, 1 for yes.

function_call · integer

Function calling support. 0 for no, 1 for yes.

image_support · integer

Image/vision support. 0 for no, 1 for yes.

supported_params_override · object

Override UI parameter support for this model in the Playground. See the model detail endpoint for current values.

Example

{
  "supported_params_override": {
    "temperature": {
      "name": "temperature",
      "type": "number",
      "default": 0.7,
      "min": 0,
      "max": 1.5
    }
  }
}

Response

Returns the created or updated model object.

201 Created

{
  "id": "my-custom-gpt-4",
  "model_name": "my-custom-gpt-4",
  "display_name": "My Custom GPT-4",
  "base_model_name": "gpt-4",
  "affiliation_category": "custom",
  "is_called_by_custom_name": false,
  "input_cost": 0.025,
  "output_cost": 0.075,
  "cache_hit_input_cost": 0.0,
  "cache_creation_input_cost": 0.0,
  "max_context_window": 8192,
  "streaming_support": 1,
  "function_call": 1,
  "image_support": 0,
  "source": "db",
  "provider": {
    "id": "my-custom-provider",
    "provider_id": "my-custom-provider",
    "provider_name": "My Custom Provider",
    "organization_id": 123
  }
}

Python

import requests

url = "https://api.keywordsai.co/api/models/"
headers = {
    "Authorization": "Bearer YOUR_API_KEY",
    "Content-Type": "application/json"
}
payload = {
    "model_name": "my-custom-gpt-4",
    "base_model_name": "gpt-4",
    "display_name": "My Custom GPT-4",
    "custom_provider_id": "my-azure-provider",
    "input_cost": 0.025,
    "output_cost": 0.075
}

response = requests.post(url, headers=headers, json=payload)
print(response.json())