Skip to main content
GET
/
models
List Models
curl --request GET \
  --url https://api.kakiyo.com/v1/models \
  --header 'Authorization: Bearer <token>'
{
  "models": [
    {
      "id": "680321c8001e2f527d82",
      "name": "GPT 5 Mini",
      "pricing": {
        "input": 0.25,
        "output": 2,
        "cached": 0.1
      },
      "status": "active"
    }
  ],
  "total": 8
}

​
Overview

Get a list of all available AI models with their pricing information. This endpoint returns active models that can be used for prompt configuration and campaign creation.

​
Use Cases

  • Prompt Configuration: Discover available models for AI prompt setup
  • Cost Estimation: Calculate expected costs based on model pricing
  • Model Selection: Choose appropriate models for different use cases
  • Integration Planning: Plan model usage across campaigns and workflows

​
Response Structure

The response includes an array of available models with pricing details: 
{
  "models": [
    {
      "id": "67fcab2e0032f8b20363",
      "name": "Claude 4 Sonnet",
      "pricing": {
        "input": 3,
        "output": 15,
        "cached": 3.75
      },
      "status": "active"
    },
    {
      "id": "67fccf2900258424236f",
      "name": "Claude OPUS 4.1",
      "pricing": {
        "input": 15,
        "output": 75,
        "cached": 7.5
      },
      "status": "active"
    },
    {
      "id": "680321e500318611796d",
      "name": "Gemini 2.5 Flash",
      "pricing": {
        "input": 0.3,
        "output": 2.5,
        "cached": 0.15
      },
      "status": "active"
    },
    {
      "id": "682c0dfc0036ded6b90b",
      "name": "Gemini 2.5 Pro",
      "pricing": {
        "input": 1.25,
        "output": 10,
        "cached": null
      },
      "status": "active"
    },
    {
      "id": "680321aa001300a6673d",
      "name": "GPT 4.1",
      "pricing": {
        "input": 2,
        "output": 8,
        "cached": 0.5
      },
      "status": "active"
    },
    {
      "id": "689f6adb001e16e22378",
      "name": "GPT 5",
      "pricing": {
        "input": 1.25,
        "output": 10,
        "cached": 3
      },
      "status": "active"
    },
    {
      "id": "680321c8001e2f527d82",
      "name": "GPT 5 Mini",
      "pricing": {
        "input": 0.25,
        "output": 2,
        "cached": 0.1
      },
      "status": "active"
    },
    {
      "id": "689f1e61000b7da834bf",
      "name": "Grok 4",
      "pricing": {
        "input": 3,
        "output": 15,
        "cached": null
      },
      "status": "active"
    }
  ],
  "total": 8
}

​
Testing Example

curl -X GET "https://api.kakiyo.com/v1/models" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json"

// JavaScript/Node.js
const getModels = async () => {
  const response = await fetch('https://api.kakiyo.com/v1/models', {
    method: 'GET',
    headers: {
      'Authorization': 'Bearer YOUR_API_KEY',
      'Content-Type': 'application/json'
    }
  });

  return await response.json();
};

// Usage example
const models = await getModels();
console.log('Available Models:', models);

// Find most cost-effective model
const cheapestModel = models.models.reduce((prev, current) => 
  (prev.pricing.input + prev.pricing.output) < (current.pricing.input + current.pricing.output) ? prev : current
);
console.log('Most cost-effective model:', cheapestModel.name);

# Python
import requests

def get_models():
    """Get list of available AI models"""
    response = requests.get(
        'https://api.kakiyo.com/v1/models',
        headers={
            'Authorization': 'Bearer YOUR_API_KEY',
            'Content-Type': 'application/json'
        }
    )
    
    return response.json()

# Usage example
models = get_models()
print('Available Models:', models)

# Filter models by pricing
budget_models = [
    model for model in models['models'] 
    if model['pricing']['input'] <= 1.0
]
print(f'Budget-friendly models: {len(budget_models)}')

​
Pricing Information

​
Pricing Structure

  • Input: Cost per 1,000 input tokens
  • Output: Cost per 1,000 output tokens
  • Cached: Cost per 1,000 cached tokens (if supported, otherwise null)

​
Model Categories by Cost

Budget Models (Input ≤ $1.00):
  • GPT 5 Mini: 0.25input/0.25 input / 2.00 output
  • Gemini 2.5 Flash: 0.30input/0.30 input / 2.50 output
Standard Models (1.00<Input≤1.00 < Input ≤ 3.00):
  • GPT 4.1: 2.00input/2.00 input / 8.00 output
  • GPT 5: 1.25input/1.25 input / 10.00 output
  • Gemini 2.5 Pro: 1.25input/1.25 input / 10.00 output
  • Claude 4 Sonnet: 3.00input/3.00 input / 15.00 output
  • Grok 4: 3.00input/3.00 input / 15.00 output
Premium Models (Input > $3.00):
  • Claude OPUS 4.1: 15.00input/15.00 input / 75.00 output

​
Integration Examples

​
Model Selection for Prompts

const selectModelForPrompt = async (maxBudget) => {
  const models = await getModels();
  
  // Filter models within budget
  const affordableModels = models.models.filter(model => 
    model.pricing.input <= maxBudget
  );
  
  // Sort by performance/cost ratio (assuming higher price = better performance)
  return affordableModels.sort((a, b) => b.pricing.input - a.pricing.input)[0];
};

// Usage
const bestModel = await selectModelForPrompt(2.0);
console.log('Selected model:', bestModel.name);

​
Cost Calculation

const calculateCost = (model, inputTokens, outputTokens) => {
  const inputCost = (inputTokens / 1000) * model.pricing.input;
  const outputCost = (outputTokens / 1000) * model.pricing.output;
  
  return {
    input: inputCost,
    output: outputCost,
    total: inputCost + outputCost
  };
};

// Usage
const cost = calculateCost(
  models.models.find(m => m.name === 'GPT 5 Mini'),
  5000, // 5K input tokens
  2000  // 2K output tokens
);
console.log('Estimated cost:', cost);

​
Best Practices

  1. Cost Optimization: Choose models based on your use case requirements
  2. Performance vs Cost: Balance model capabilities with budget constraints
  3. Caching: Utilize cached pricing when available for repeated content
  4. Model Monitoring: Regularly check for new models and pricing updates
  5. Budget Planning: Use pricing information for accurate cost forecasting

​
Common Use Cases

​
Campaign Planning

Use model pricing to estimate campaign costs based on expected message volume and complexity.

​
Prompt Optimization

Select appropriate models for different prompt types - use budget models for simple tasks, premium models for complex reasoning.

​
Cost Management

Monitor and control AI usage costs by selecting models that fit your budget requirements.

​
Error Responses

​
Authentication Failed

{
  "error": "unauthorized",
  "message": "Invalid or missing API key"
}

​
Internal Server Error

{
  "error": "internal_error",
  "message": "An internal error occurred while fetching models"
}

Authorizations

​
Authorization
string
header
required

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

Response

Models retrieved successfully

​
models
object[]
​
total
integer
Example:

8