Skip to content
Admin - Pricing
/
Get models pricing
Last updated

Get models pricing (Admin)

🔨 In Development — This section is still being developed and may change.
**GET** `/v1/pricing/models` - Retrieve detailed AI model pricing information with admin-specific financial data including markup percentages, actual costs, and profit margins.
GEThttps://api.freddy.aitronos.com/v1/pricing/models

Administrative endpoint that provides comprehensive pricing information for all AI models, including internal cost structure and profit margins. This endpoint is restricted to administrators only.

Authentication

This endpoint requires admin-level API keys.

Response

Returns a ModelsPricingResponse object containing detailed pricing for all models.

models array

Array of model pricing objects, each containing:

modelId string - Model identifier (e.g., gpt-4, claude-3-opus)

modelName string - Human-readable model name

provider string - Model provider (OpenAI, Anthropic, Aitronos)

inputCostPer1k number - Cost per 1,000 input tokens in USD

outputCostPer1k number - Cost per 1,000 output tokens in USD

currency string - Pricing currency (always USD)

ourMarkup number - Aitronos markup percentage (admin only)

costToUs number - Actual cost from provider (admin only)

profitMargin number - Profit per 1k tokens (admin only)

currency string

Base currency for all pricing (USD)

conversionRate number

Conversion rate from USD to CHF (base currency)

lastUpdated string

ISO 8601 timestamp of last pricing update

Bash
curl https://api.freddy.aitronos.com/v1/pricing/models \
  -H "api-key: $FREDDY_ADMIN_API_KEY"

Response

{
  "models": [
    {
      "modelId": "gpt-4",
      "modelName": "GPT-4",
      "provider": "OpenAI",
      "inputCostPer1k": 0.03,
      "outputCostPer1k": 0.06,
      "currency": "USD",
      "ourMarkup": 15,
      "costToUs": 0.03,
      "profitMargin": 0.0045
    },
    {
      "modelId": "gpt-3.5-turbo",
      "modelName": "GPT-3.5 Turbo",
      "provider": "OpenAI",
      "inputCostPer1k": 0.0015,
      "outputCostPer1k": 0.002,
      "currency": "USD",
      "ourMarkup": 20,
      "costToUs": 0.0015,
      "profitMargin": 0.0003
    },
    {
      "modelId": "claude-3-opus",
      "modelName": "Claude 3 Opus",
      "provider": "Anthropic",
      "inputCostPer1k": 0.015,
      "outputCostPer1k": 0.075,
      "currency": "USD",
      "ourMarkup": 10,
      "costToUs": 0.015,
      "profitMargin": 0.0015
    }
  ],
  "currency": "USD",
  "conversionRate": 0.9,
  "lastUpdated": "2025-10-16T10:30:00Z"
}

Understanding Admin Fields

Markup Percentage (ourMarkup)

The percentage markup applied to the provider's base cost. For example, a 15% markup on $0.03 means customers pay $0.0345.

Cost To Us (costToUs)

The actual cost charged by the AI provider (OpenAI, Anthropic, etc.) per 1,000 tokens. This is what Aitronos pays.

Profit Margin (profitMargin)

The profit Aitronos makes per 1,000 tokens after applying the markup:

profitMargin = (inputCostPer1k - costToUs)

Use Cases

Financial Reporting

import requests

response = requests.get(
    "https://api.freddy.aitronos.com/v1/pricing/models",
    headers={"api-key": admin_key}
)

pricing = response.json()

total_markup = sum(m['ourMarkup'] for m in pricing['models']) / len(pricing['models'])
print(f"Average markup across all models: {total_markup}%")

# Find most profitable model
most_profitable = max(pricing['models'], key=lambda m: m['profitMargin'])
print(f"Most profitable: {most_profitable['modelName']} (${most_profitable['profitMargin']}/1k)")

Pricing Analysis

# Compare pricing across providers
by_provider = {}
for model in pricing['models']:
    provider = model['provider']
    if provider not in by_provider:
        by_provider[provider] = []
    by_provider[provider].append(model)

for provider, models in by_provider.items():
    avg_input_cost = sum(m['inputCostPer1k'] for m in models) / len(models)
    avg_output_cost = sum(m['outputCostPer1k'] for m in models) / len(models)
    print(f"{provider}: Avg ${avg_input_cost:.4f}/1k input, ${avg_output_cost:.4f}/1k output")

Cost Monitoring

# Monitor cost changes over time
import json
from datetime import datetime

response = requests.get(
    "https://api.freddy.aitronos.com/v1/pricing/models",
    headers={"api-key": admin_key}
)

pricing = response.json()

# Save snapshot for historical tracking
snapshot = {
    "timestamp": datetime.now().isoformat(),
    "pricing": pricing
}

with open(f"pricing_snapshot_{datetime.now().date()}.json", "w") as f:
    json.dump(snapshot, f, indent=2)

Notes

  • Pricing data is cached and updated periodically
  • lastUpdated timestamp indicates when pricing was last refreshed from providers
  • Conversion rate applies when displaying prices in CHF
  • This endpoint is for internal administration only - do not expose to end users
  • Model availability may vary by organization tier

Admin API endpoints require administrator-level authentication and should not be exposed to regular users.

Previous page
Next page