Skip to main content
The Models API provides information about available LLM models from all configured providers, including capabilities, pricing, and context limits.

​
List models

Retrieve all available models from configured providers.

​
Endpoint

GET /api/models

​
Parameters

​
provider
string
Filter models by provider (openai, anthropic, gemini, bedrock)
​
capability
string
Filter by model capability (chat, embedding, image_generation)

​
Response

​
models
array
Array of model objects

​
Example

cURL
curl http://localhost:9090/api/models
Python
import requests

response = requests.get('http://localhost:9090/api/models')
models = response.json()

# List all chat models
chat_models = [m for m in models['models'] if 'chat' in m['capabilities']]
for model in chat_models:
    print(f"{model['id']} - {model['provider']}")
    print(f"  Context: {model['context_window']} tokens")
    print(f"  Price: ${model['pricing']['input']}/1M input, ${model['pricing']['output']}/1M output")

​
Filter by provider

Get models from a specific provider: 
curl "http://localhost:9090/api/models?provider=anthropic"
Returns only Anthropic Claude models.

​
Filter by capability

Get models with specific capabilities: 
# Chat models only
curl "http://localhost:9090/api/models?capability=chat"

# Embedding models
curl "http://localhost:9090/api/models?capability=embedding"

# Image generation models
curl "http://localhost:9090/api/models?capability=image_generation"

​
Using models in requests

Use the model ID from the API in your requests: 
curl http://localhost:9090/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o",
    "messages": [{"role": "user", "content": "Hello"}]
  }'
vLLora automatically routes to the correct provider based on the model ID.

​
Model capabilities

​
Chat models

Models with chat capabilities support:
  • Conversational interfaces
  • Multi-turn dialogues
  • System prompts
  • Tool/function calling (if supported)
Example chat models:
  • gpt-4o, gpt-4o-mini (OpenAI)
  • claude-3-5-sonnet-20241022, claude-3-5-haiku-20241022 (Anthropic)
  • gemini-2.0-flash-exp, gemini-1.5-pro (Google)
  • anthropic.claude-3-5-sonnet-20241022-v2:0 (AWS Bedrock)

​
Embedding models

Models that generate vector embeddings:
  • text-embedding-3-small, text-embedding-3-large (OpenAI)
  • text-embedding-004 (Google)

​
Image generation models

Models that generate images from text:
  • dall-e-3, dall-e-2 (OpenAI)

​
Pricing information

The pricing field shows costs per 1 million tokens: 
{
  "id": "gpt-4o",
  "pricing": {
    "input": 2.50,   // $2.50 per 1M input tokens
    "output": 10.00  // $10.00 per 1M output tokens
  }
}
Use this to estimate costs before making requests.

​
Context windows

The context_window field indicates the maximum total tokens (input + output):
  • gpt-4o: 128,000 tokens
  • claude-3-5-sonnet-20241022: 200,000 tokens
  • gemini-2.0-flash-exp: 1,000,000 tokens
Ensure your requests fit within the model’s context window.

​
CLI command

List models from the command line: 
vllora list
This displays all available models in a formatted table.

​
Sync models

Update the model database from provider APIs: 
# Sync all models
vllora sync --models

# Sync specific provider
vllora sync --models --providers
Model information is embedded in vLLora at build time for fast startup. Use sync to update with the latest models from provider APIs.

​
Best practices

  • Use smaller/faster models (gpt-4o-mini, claude-3-5-haiku) for simple tasks
  • Use larger models (gpt-4o, claude-3-5-sonnet) for complex reasoning
  • Check context window if you have long conversations
Check model pricing before deploying. Cost differences can be significant:
  • gpt-4o-mini: 0.15/0.15/0.60 per 1M tokens
  • gpt-4o: 2.50/2.50/10.00 per 1M tokens
Not all models support all features. Check the features array:
  • Tool calling support varies by model
  • Vision capabilities are model-specific
  • JSON mode isn’t universal
Run vllora sync --models periodically to get new models and updated pricing.

​
Next steps

Chat Completions

Use models in chat completion requests

Embeddings

Generate embeddings with embedding models

Image Generation

Create images with DALL-E models

Providers

Learn about provider support

Build docs developers (and LLMs) love

Get started for freeTalk to us