Skip to main content

Documentation Index

Fetch the complete documentation index at: https://mintlify.com/helicone/helicone/llms.txt

Use this file to discover all available pages before exploring further.

​
Overview

The Models endpoint returns a comprehensive list of all AI models supported by Helicone AI Gateway. This includes models from providers like OpenAI, Anthropic, Google, Meta, Mistral, and many others. The response follows the OpenAI API format for compatibility with existing tools and libraries.

​
Endpoint

GET https://ai-gateway.helicone.ai/v1/models

​
Authentication

No authentication is required for this endpoint. It’s publicly accessible to help you discover available models.

​
Request

This endpoint accepts no parameters. Simply make a GET request: 
curl https://ai-gateway.helicone.ai/v1/models

​
Response Format

​
object
string
Object type, always "list"
​
data
array
Array of model objects. Each model contains:

​
Model Object

​
id
string
The model identifier that can be used in API requests.Examples:
  • "gpt-4"
  • "claude-3-5-sonnet-20241022"
  • "gemini-2.0-flash-exp"
​
object
string
Object type, always "model"
​
created
integer
Unix timestamp of when the model was released
​
owned_by
string
The organization that owns/created the model.Examples:
  • "openai"
  • "anthropic"
  • "google"
  • "meta"

​
Example Request

curl https://ai-gateway.helicone.ai/v1/models

​
Example Response

{
  "object": "list",
  "data": [
    {
      "id": "gpt-4",
      "object": "model",
      "created": 1687882411,
      "owned_by": "openai"
    },
    {
      "id": "gpt-4-turbo",
      "object": "model",
      "created": 1704067200,
      "owned_by": "openai"
    },
    {
      "id": "gpt-3.5-turbo",
      "object": "model",
      "created": 1677649963,
      "owned_by": "openai"
    },
    {
      "id": "claude-3-5-sonnet-20241022",
      "object": "model",
      "created": 1729555200,
      "owned_by": "anthropic"
    },
    {
      "id": "claude-3-opus-20240229",
      "object": "model",
      "created": 1709251200,
      "owned_by": "anthropic"
    },
    {
      "id": "gemini-2.0-flash-exp",
      "object": "model",
      "created": 1704067200,
      "owned_by": "google"
    },
    {
      "id": "gemini-1.5-pro",
      "object": "model",
      "created": 1704067200,
      "owned_by": "google"
    },
    {
      "id": "llama-3.3-70b-instruct",
      "object": "model",
      "created": 1733011200,
      "owned_by": "meta"
    },
    {
      "id": "mistral-large-latest",
      "object": "model",
      "created": 1704067200,
      "owned_by": "mistralai"
    },
    {
      "id": "deepseek-chat",
      "object": "model",
      "created": 1704067200,
      "owned_by": "deepseek"
    }
  ]
}

​
Model Categories

The endpoint returns models across multiple categories:

​
Chat Models

  • OpenAI GPT models (GPT-4, GPT-3.5, etc.)
  • Anthropic Claude models
  • Google Gemini models
  • Meta Llama models
  • Mistral models
  • DeepSeek models
  • And many more

​
Multimodal Models

Models that support multiple input/output types (text, images, audio):
  • GPT-4 Vision
  • Claude 3 Opus/Sonnet
  • Gemini Pro Vision

​
Specialized Models

  • Reasoning models (o1, o3-mini)
  • Fast inference models (GPT-4 Turbo, Gemini Flash)
  • Cost-effective models (GPT-3.5, Claude Haiku)

​
Filtering Models

The API returns all publicly available models that don’t require explicit routing. Some enterprise or specialized models may require additional configuration and won’t appear in this list. Models requiring explicit routing (via requireExplicitRouting flag) are excluded from the response to avoid confusion.

​
Usage with Chat Completions

Once you have the model ID from this endpoint, use it directly in the Chat Completions endpoint: 
curl https://ai-gateway.helicone.ai/v1/chat/completions \
  -H "Authorization: Bearer YOUR_HELICONE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-3-5-sonnet-20241022",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

​
Model Information

For detailed information about each model including:
  • Pricing
  • Context length
  • Capabilities
  • Provider documentation
Visit the Helicone Models page.

​
Programmatic Access

You can programmatically fetch and filter models in your application: 
import requests

response = requests.get("https://ai-gateway.helicone.ai/v1/models")
models = response.json()["data"]

# Filter by provider
openai_models = [m for m in models if m["owned_by"] == "openai"]

# Get model IDs
model_ids = [m["id"] for m in models]

print(f"Total models available: {len(models)}")
print(f"OpenAI models: {len(openai_models)}")

const response = await fetch("https://ai-gateway.helicone.ai/v1/models");
const data = await response.json();
const models = data.data;

// Filter by provider
const anthropicModels = models.filter(m => m.owned_by === "anthropic");

// Get model IDs
const modelIds = models.map(m => m.id);

console.log(`Total models available: ${models.length}`);
console.log(`Anthropic models: ${anthropicModels.length}`);

​
Notes

  • This endpoint is unauthenticated and rate-limited per IP address
  • The list of models is updated automatically as new providers and models are added
  • Some models may require specific authentication or configuration to use
  • Model availability may vary by region or account type
  • The created timestamp uses Unix epoch time (seconds since January 1, 1970)