Models

List and retrieve information about available AI models.

List All Models

Endpoint

GET /api/v1/models

Request

curl http://localhost/api/v1/models \
  -H "Authorization: Bearer YOUR_API_KEY"

Response

{
  "object": "list",
  "data": [
    {
      "id": "gpt-4",
      "object": "model",
      "created": 1234567890,
      "owned_by": "system"
    },
    {
      "id": "gpt-3.5-turbo",
      "object": "model",
      "created": 1234567890,
      "owned_by": "system"
    },
    {
      "id": "text-embedding-ada-002",
      "object": "model",
      "created": 1234567890,
      "owned_by": "system"
    }
  ]
}

Python Example

import requests

response = requests.get(
    "http://localhost/api/v1/models",
    headers={"Authorization": "Bearer YOUR_API_KEY"}
)

models = response.json()["data"]
for model in models:
    print(f"Model ID: {model['id']}")
    print(f"Owned by: {model['owned_by']}")
    print("-" * 40)

JavaScript Example

const response = await fetch('http://localhost/api/v1/models', {
  headers: {
    'Authorization': 'Bearer YOUR_API_KEY'
  }
});

const data = await response.json();
data.data.forEach(model => {
  console.log(`Model ID: ${model.id}`);
  console.log(`Owned by: ${model.owned_by}`);
});

Get Model Details

Endpoint

GET /api/v1/models/{model_id}

Request

curl http://localhost/api/v1/models/gpt-4 \
  -H "Authorization: Bearer YOUR_API_KEY"

Response

{
  "id": "gpt-4",
  "object": "model",
  "created": 1234567890,
  "owned_by": "system"
}

Python Example

import requests

model_id = "gpt-4"
response = requests.get(
    f"http://localhost/api/v1/models/{model_id}",
    headers={"Authorization": "Bearer YOUR_API_KEY"}
)

model = response.json()
print(f"Model: {model['id']}")
print(f"Created: {model['created']}")
print(f"Owner: {model['owned_by']}")

Available Models

Chat Models

Model ID	Description	Max Tokens
gpt-4	Most capable model	8192
gpt-4-32k	GPT-4 with 32k context	32768
gpt-3.5-turbo	Fast, cost-effective	4096
gpt-3.5-turbo-16k	GPT-3.5 with 16k context	16384

Embedding Models

Model ID	Description	Dimensions
text-embedding-ada-002	General purpose text embeddings	1536

Model Selection Guide

Choose GPT-4 When:

• Complex reasoning tasks
• Code generation and debugging
• Creative writing requiring nuanced understanding
• Budget allows for higher costs

Choose GPT-3.5-Turbo When:

• Fast responses needed
• Cost efficiency is important
• Simple queries and responses
• High volume of requests

Choose 32k Context When:

• Long documents need processing
• Multi-part conversations
• Complex prompts with lots of context
• Maintaining conversation history

Error Handling

Model Not Found

{
  "error": {
    "message": "Model 'gpt-5' not found",
    "type": "invalid_request_error",
    "code": "model_not_found"
  }
}

Solution: Check available models with GET /api/v1/models

Authentication Error

{
  "error": {
    "message": "Invalid authentication credentials",
    "type": "authentication_error",
    "code": "invalid_api_key"
  }
}

Solution: Verify your API key is correct and active

Best Practices

1. Check Available Models - Query /api/v1/models before using a specific model
2. Handle Errors Gracefully - Model availability may change
3. Use Appropriate Models - Balance capability with cost
4. Cache Model List - Models don't change frequently, cache to reduce API calls

Next Steps

• Chat Completions - Use models to generate text
• Embeddings - Use embedding models
• Integration Examples - See how to use with clients