API Endpoints

Arvae provides two main API endpoints for chat completions, each serving a specific purpose to help you interact with different AI models.

V1 Endpoint

https://arvae.ai/api/v1/chat/completions

Purpose

Use this endpoint for accessing all third-party models from providers like OpenAI, Anthropic, Google, Meta, etc.

Available Models

OpenAI models (GPT-4, GPT-3.5, etc.)
Anthropic models (Claude 3 Opus, Sonnet, etc.)
Google models (Gemini Pro, etc.)
Meta models (Llama 3, etc.)
And many more

See all available models →

V2 Endpoint

https://arvae.ai/api/v2/chat/completions

Purpose

Use this endpoint exclusively for Hanooman models.

Available Models

hanooman/hanooman-everest

The Hanooman model offers specialized capabilities optimized for certain tasks. See the Hanooman model documentation for details.

Request Format

Both endpoints follow the same request format, making it easy to switch between them by just changing the URL and model name.

Example Request

1POST /api/v1/chat/completions
2Content-Type: application/json
3Authorization: Bearer YOUR_API_KEY
4
5{
6  "model": "openai/chatgpt-4o-latest",
7  "messages": [
8    {"role": "system", "content": "You are a helpful assistant."}, 
9    {"role": "user", "content": "Hello, who are you?"}
10  ],
11  "temperature": 0.7,
12  "max_tokens": 500,
13  "stream": false
14}

Response Format

Each endpoint returns responses in a consistent format, similar to the OpenAI API format that many developers are already familiar with.

V1 Endpoint Response Example

1{
2    "id": "arvae-1745773067-1VSEv2b7Nzk8wAZfMJst",
3    "model": "openai/chatgpt-4o-latest",
4    "choices": [
5        {
6            "finish_reason": "stop",
7            "index": 0,
8            "message": {
9                "role": "assistant",
10                "content": "Hello! I'm here and ready to help. How are you?"
11            }
12        }
13    ],
14    "token_metrics": {
15        "input_tokens": 12,
16        "output_tokens": 14,
17        "total_tokens": 26
18    }
19}

V2 Endpoint Response Example

1{
2    "model": "hanooman/hanooman-everest",
3    "id": "arvae-id_yNwd8EyBzJJO1W2nV",
4    "conversation_id": null,
5    "choices": [
6        {
7            "index": 0,
8            "finish_reason": "stop",
9            "message": {
10                "role": "assistant",
11                "content": "Hello! I'm functioning optimally today, thank you for asking. How can I assist you?"
12            }
13        }
14    ],
15    "token_metrics": {
16        "input_tokens": 125,
17        "output_tokens": 21,
18        "total_tokens": 146
19    }
20}

For more details on the response format and how to parse it, see the Response Format documentation.

Next Steps

Continue exploring the Arvae API by learning about authentication and making your first API request.

Next: Authentication →Browse Available Models