Get Seed Models by Provider

Used to retrieve all available models from the seed data for a specific AI provider. This endpoint returns detailed information about the models supported by a particular provider.

API Endpoint

Property	Value
Request Method	GET
Request URL	https://api.seliseblocks.com/models/seed/providers/{provider}

Request

Request Example

curl -X GET 'https://api.seliseblocks.com/models/seed/providers/openai' \
  -H 'accept: application/json'

Path Parameters

Field	Type	Required	Description
provider	string	Yes	Model provider name (case-insensitive). Examples: "openai", "anthropic", "azure", "google".

Request Headers

Field	Type	Required	Description
accept	string	Yes	Accepted response format. Use application/json

tip

When to use this endpoint:

• When building model selection UI for a specific provider
• To discover available model versions and their specifications
• Before creating a new AI model to verify model names
• To check supported features and parameters for provider models
• When migrating between model versions

Use cases:

• Provider exploration: Browse all models offered by OpenAI, Anthropic, etc.
• Model comparison: Compare specifications across models from the same provider
• Version discovery: Find the latest model versions available
• Configuration reference: Get default parameters and capabilities for each model
• Integration planning: Understand model requirements before implementation

Response

Success Response (200 OK)

Returns an array of model objects containing detailed information about each model from the specified provider.

[
  {
    "model_name": "gpt-4-turbo-preview",
    "version": "gpt-4",
    "display_name": "GPT-4 Turbo",
    "description": "Most capable GPT-4 model with 128K context window",
    "max_tokens": 4096,
    "context_window": 128000,
    "capabilities": ["chat", "completion", "vision"],
    "default_temperature": 0.7,
    "supported_features": ["streaming", "function_calling"],
    "pricing": {
      "input_per_1k_tokens": 0.01,
      "output_per_1k_tokens": 0.03
    }
  },
  {
    "model_name": "gpt-3.5-turbo",
    "version": "gpt-3.5",
    "display_name": "GPT-3.5 Turbo",
    "description": "Fast and efficient model for everyday tasks",
    "max_tokens": 4096,
    "context_window": 16385,
    "capabilities": ["chat", "completion"],
    "default_temperature": 0.7,
    "supported_features": ["streaming", "function_calling"],
    "pricing": {
      "input_per_1k_tokens": 0.0005,
      "output_per_1k_tokens": 0.0015
    }
  }
]

Response Fields

Field	Type	Description
-	array	Array of model objects with provider-specific details. Each object contains flexible properties based on the provider's model specifications.

note

Response Object Structure

The response returns an array of flexible objects (additionalProp1: {}) where each object represents a model. The exact structure varies by provider but typically includes:

Common Properties:

• model_name: Exact model identifier used in API calls
• version: Model version or family
• display_name: Human-readable model name
• description: Brief description of model capabilities
• max_tokens: Maximum output tokens
• context_window: Maximum input context size
• capabilities: Array of supported features
• default_temperature: Recommended temperature setting
• pricing: Cost information per token

Provider-Specific Properties:

• OpenAI: May include vision capabilities, function calling support
• Anthropic: May include Claude-specific features like extended context
• Azure: May include deployment-specific information
• Google: May include model variants and regional availability

Use this data to:

• Populate model selection dropdowns
• Display model capabilities to users
• Set appropriate default parameters
• Calculate cost estimates
• Validate model configurations

Error Response (422 Unprocessable Entity)

Returns validation error details when the provider parameter is invalid.

{
  "detail": [
    {
      "loc": [
        "path",
        "provider"
      ],
      "msg": "Provider not found or invalid provider name",
      "type": "value_error.notfound"
    }
  ]
}

Error Response Fields

Field	Type	Description
detail	array	Array of validation error objects.
loc	array	Location of the error in the request (e.g., path parameter).
msg	string	Human-readable error message.
type	string	Error type identifier.

Common Error Scenarios

Error Type	Description	Resolution
Provider Not Found	The specified provider doesn't exist	Use GET /models/seed/providers to get valid provider names
Invalid Provider Name	Provider name format is incorrect	Ensure provider name matches exactly (case-insensitive)
Empty Response	Provider exists but has no seed models	Contact support or check if provider is deprecated

Error Codes

Status Code	Description	Response Type
200	OK - Successfully retrieved models list	Success
404	Not Found - Provider doesn't exist	Not Found
422	Validation Error - Invalid provider parameter	Unprocessable Entity
500	Internal Server Error - Failed to fetch models	Internal Server Error

warning

Important Considerations

• Provider names are case-insensitive (both "OpenAI" and "openai" work)
• Seed data represents available models but doesn't guarantee all are accessible with your API keys
• Model specifications may change; seed data is periodically updated
• Not all models may be available in all regions or subscription tiers
• Pricing information in seed data is indicative; always verify with provider
• Some models may require special access or approval from the provider
• Cache responses appropriately to reduce unnecessary API calls