Pricing

Model Pricing

Endpoint: /api/pricing

Description: Retrieves pricing information for all models or a specific model if provided. Pricing is based on model tiers and includes input and output token prices per million tokens.

Authentication: Required (JWT token or Api Key)

HTTP Method: GET

Request Parameters:

Parameter	Type	Required	Description
model_id	string	No	ID of the model to retrieve pricing for. If not provided,
			pricing for all available models will be returned.

Response Format:

{
  "data": [
    {
      "model_id": "llama3.1-8b",
      "tier": "TIER_1",
      "pricing": {
        "input_token_price": 0.003,
        "output_token_price": 0.008
      }
    },
    {
      "model_id": "phi4:14b",
      "tier": "TIER_2",
      "pricing": {
        "input_token_price": 0.23,
        "output_token_price": 0.67
      }
    }
  ]
}

Key Response Fields:

Field	Type	Description
model_id	string	Identifier for the model
tier	string	Pricing tier category for the model
pricing.input_token_price	number	Price per million tokens for input/prompt tokens
pricing.output_token_price	number	Price per million tokens for output/completion tokens

Response Codes:

• 200: Successfully retrieved pricing information

• 401: Not authenticated

• 404: Model not found (if a specific model_id was requested)