Skip to main content

​
Models

ClassAI provides access to a diverse range of state-of-the-art AI models from leading providers including OpenAI, Meta, Anthropic, and others. Our model catalog includes both free and premium options to suit different use cases and budgets.

​
Model Types

​
Free Models

Free models are identified by the :free suffix in their model ID. These models offer:
  • Rate Limits: 20 requests per minute (RPM) and 200 requests per day (RPD)
  • Cost: No charges for usage
  • Perfect for: Testing, prototyping, and low-volume applications
For detailed information about rate limits and how they work, see our Rate Limits guide.

​
Premium Models

Premium models offer enhanced capabilities and higher rate limits:
  • Cost: Usage-based pricing per million tokens
  • Perfect for: Production applications, high-volume workloads, and enterprise use cases

​
Available Models

You can explore all available models, their technical specifications, code examples, and real-time status at https://routeway.ai/models. You can also retrieve the complete list of available models programmatically: 
curl -X GET "https://api.routeway.ai/v1/models"

​
Model Response Format

Each model in the response includes comprehensive information: 
{
  "object": "list",
  "data": [
    {
      "id": "llama-4-scout-17b-16e-instruct",
      "name": "Meta: Llama 4 Scout",
      "short_name": "Llama 4 Scout",
      "description": "Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model...",
      "created": 1743881519,
      "owned_by": "meta",
      "type": "chat.completions",
      "hallucination_rate": 1.62,
      "available": true,
      "pricing": {
        "input": {
          "unit": "1M tokens",
          "price_per_million_t": 0.1,
          "price_per_token_usd": "0.00000004"
        },
        "output": {
          "unit": "1M tokens",
          "price_per_million_t": 0.225,
          "price_per_token_usd": "0.00000022"
        }
      }
    }
  ]
}

​
Model Properties

​
id
string
required
Unique identifier for the model. Use this ID when making API requests.
​
name
string
Full display name of the model including the provider.
​
short_name
string
Abbreviated name for the model.
​
description
string
Detailed description of the model’s capabilities, training data, and use cases.
​
created
integer
Unix timestamp when the model was added to ClassAI.
​
owned_by
string
The organization that developed the model (e.g., “openai”, “meta”, “anthropic”).
​
type
string
The type of model, typically “chat.completions” for conversational models.
​
hallucination_rate
number
Benchmark score indicating the model’s tendency to generate factually incorrect information. Lower values indicate better factual accuracy.
​
available
boolean
Whether the model is currently available for use.
​
pricing
object
Pricing information for the model, including input and output token costs.

​
Choosing the Right Model

  • Development & Testing
  • Production
For prototyping and testing, start with free models (:free suffix):
  • No cost to experiment
  • Perfect for proof-of-concepts
  • 20 RPM / 200 RPD limits
Monitor your usage and costs through the Routeway dashboard. Free models are perfect for getting started, but premium models offer significantly better performance for production use cases.

​
Rate Limits

All models are subject to rate limits to ensure fair usage and system stability. Free models have stricter limits, while premium models offer more generous allowances.

Learn More

For comprehensive information about rate limits, including how to handle them and increase your limits, visit our Rate Limits documentation.

​
FAQs

No, you don’t need to set rate limits manually. Free models automatically enforce 20 requests per minute (RPM) and 200 requests per day (RPD). These limits are applied by the system.
Use free models (marked with :free) for testing, prototyping, or low-volume applications. For production workloads or advanced capabilities, paid models offer better performance, higher limits, and priority availability.
No, usage is aggregated at the account level. All model usage under the same API key is counted toward your overall request and token limits.
⌘I