HelpingAI Logo

Models API

The models API allows you to list and retrieve information about the available models in HelpingAI. This is useful for discovering model capabilities and selecting the right model for your use case.

GET/v1/models

List all available models

List Models

Retrieve a list of all available models.

Examples

Python (using requests)

python
import requests

url = "https://api.helpingai.co/v1/models"
headers = {
    "Authorization": "Bearer YOUR_API_KEY"
}

response = requests.get(url, headers=headers)
print(response.json())

Python (using OpenAI SDK)

python
from openai import OpenAI

client = OpenAI(
    base_url="https://api.helpingai.co/v1",
    api_key="YOUR_API_KEY"
)

models = client.models.list()
for model in models.data:
    print(f"Model: {model.id}")
    print(f"Created: {model.created}")
    print(f"Owned by: {model.owned_by}")
    print("---")

Python (using HelpingAI SDK)

python
from helpingai import HelpingAI

client = HelpingAI(api_key="YOUR_API_KEY")

models = client.models.list()
for model in models.data:
    print(f"Model: {model.id}")
    print(f"Created: {model.created}")
    print(f"Owned by: {model.owned_by}")
    print("---")

JavaScript (using axios)

javascript
const axios = require('axios');

(async () => {
  const response = await axios.get(
    'https://api.helpingai.co/v1/models',
    {
      headers: {
        'Authorization': 'Bearer YOUR_API_KEY'
      }
    }
  );
  
  console.log(response.data);
})();

JavaScript (using OpenAI package)

javascript
import OpenAI from 'openai';

const openai = new OpenAI({
  baseURL: 'https://api.helpingai.co/v1',
  apiKey: 'YOUR_API_KEY'
});

async function main() {
  const models = await openai.models.list();
  
  for (const model of models.data) {
    console.log(`Model: ${model.id}`);
    console.log(`Created: ${model.created}`);
    console.log(`Owned by: ${model.owned_by}`);
    console.log('---');
  }
}

main();

JavaScript (using HelpingAI SDK)

javascript
import { HelpingAI } from 'helpingai';

const client = new HelpingAI({
  apiKey: 'YOUR_API_KEY'
});

async function main() {
  const models = await client.models.list();
  
  for (const model of models.data) {
    console.log(`Model: ${model.id}`);
    console.log(`Created: ${model.created}`);
    console.log(`Owned by: ${model.owned_by}`);
    console.log('---');
  }
}

main();

Response Format

json
{
  "object": "list",
  "data": [
    {
      "id": "Dhanishtha-2.0-preview",
      "object": "model",
      "created": 1677610602,
      "owned_by": "helpingai",
      "permission": [
        {
          "id": "modelperm-abc123",
          "object": "model_permission",
          "created": 1677610602,
          "allow_create_engine": false,
          "allow_sampling": true,
          "allow_logprobs": false,
          "allow_search_indices": false,
          "allow_view": true,
          "allow_fine_tuning": false,
          "organization": "*",
          "group": null,
          "is_blocking": false
        }
      ],
      "root": "Dhanishtha-2.0-preview",
      "parent": null
    }
  ]
}

Retrieve Model

GET/v1/models/{model_id}

Retrieve information about a specific model

Get detailed information about a specific model.

Path Parameters

ParameterTypeDescription
model_idstringThe ID of the model to retrieve

Examples

Python (using requests)

python
import requests

model_id = "Dhanishtha-2.0-preview"
url = f"https://api.helpingai.co/v1/models/{model_id}"
headers = {
    "Authorization": "Bearer YOUR_API_KEY"
}

response = requests.get(url, headers=headers)
print(response.json())

Python (using OpenAI SDK)

python
from openai import OpenAI

client = OpenAI(
    base_url="https://api.helpingai.co/v1",
    api_key="YOUR_API_KEY"
)

model = client.models.retrieve("Dhanishtha-2.0-preview")
print(f"Model ID: {model.id}")
print(f"Created: {model.created}")
print(f"Owned by: {model.owned_by}")

Python (using HelpingAI SDK)

python
from helpingai import HelpingAI

client = HelpingAI(api_key="YOUR_API_KEY")

model = client.models.retrieve("Dhanishtha-2.0-preview")
print(f"Model ID: {model.id}")
print(f"Created: {model.created}")
print(f"Owned by: {model.owned_by}")

JavaScript (using axios)

javascript
const axios = require('axios');

(async () => {
  const modelId = 'Dhanishtha-2.0-preview';
  const response = await axios.get(
    `https://api.helpingai.co/v1/models/${modelId}`,
    {
      headers: {
        'Authorization': 'Bearer YOUR_API_KEY'
      }
    }
  );
  
  console.log(response.data);
})();

JavaScript (using OpenAI package)

javascript
import OpenAI from 'openai';

const openai = new OpenAI({
  baseURL: 'https://api.helpingai.co/v1',
  apiKey: 'YOUR_API_KEY'
});

async function main() {
  const model = await openai.models.retrieve('Dhanishtha-2.0-preview');
  
  console.log(`Model ID: ${model.id}`);
  console.log(`Created: ${model.created}`);
  console.log(`Owned by: ${model.owned_by}`);
}

main();

JavaScript (using HelpingAI SDK)

javascript
import { HelpingAI } from 'helpingai';

const client = new HelpingAI({
  apiKey: 'YOUR_API_KEY'
});

async function main() {
  const model = await client.models.retrieve('Dhanishtha-2.0-preview');
  
  console.log(`Model ID: ${model.id}`);
  console.log(`Created: ${model.created}`);
  console.log(`Owned by: ${model.owned_by}`);
}

main();

Available Models

Dhanishtha-2.0-preview

Our flagship model with emotional intelligence and Chain of Recursive Thoughts capabilities.

Key Features:

  • Emotional Intelligence: 98 EQ score with natural empathetic responses
  • Chain of Recursive Thoughts: Thinks during response generation
  • Token Efficiency: 5x fewer tokens than GPT-4 for similar quality
  • OpenAI Compatibility: Drop-in replacement for OpenAI API
  • Tool Calling: Advanced function calling capabilities
  • Streaming: Real-time response generation

Specifications:

  • Context Length: 32,768 tokens
  • Training Data: Up to April 2024
  • Languages: Optimized for English, supports 50+ languages
  • Use Cases: General conversation, emotional support, reasoning tasks, creative writing

Pricing:

  • Input: $0.50 per 1M tokens
  • Output: $1.50 per 1M tokens

Model Comparison

FeatureDhanishtha-2.0-previewTraditional Models
Emotional Intelligence✅ Built-in❌ Limited
Chain of Recursive Thoughts✅ Real-time❌ Pre-processing only
Token Efficiency✅ 5x better❌ Standard
Context Length32K tokensVaries
Streaming✅ Yes✅ Yes
Tool Calling✅ Advanced✅ Basic
hideThink Parameter✅ Unique❌ Not available

Choosing the Right Model

For Emotional Support Applications

  • Recommended: Dhanishtha-2.0-preview
  • Why: Built-in emotional intelligence and empathetic responses

For Complex Reasoning Tasks

  • Recommended: Dhanishtha-2.0-preview with hideThink=false
  • Why: Chain of Recursive Thoughts engine shows thought process

For Cost-Sensitive Applications

  • Recommended: Dhanishtha-2.0-preview
  • Why: 5x more token-efficient than comparable models

For Real-time Applications

  • Recommended: Dhanishtha-2.0-preview with streaming
  • Why: 4x faster inference with streaming support

Next Steps