Skip to main content
ClassAI operates on a Pay-As-You-Go (PAYG) billing model, ensuring you only pay for what you use. Our transparent pricing structure is designed to scale with your needs, from small experiments to enterprise deployments.

​
Billing Overview

Pay only for what you use — no plans, no tricks, no nonsense.
Our billing system tracks your usage in real-time and charges you based on the number of tokens processed by each model. Different models have different pricing tiers based on their capabilities and computational requirements.

​
Token-Based Pricing

​
What Are Tokens?

Tokens are the fundamental units of text processing in AI models. They represent pieces of text that can be:
  • Words or parts of words
  • Punctuation marks
  • Spaces and special characters
Quick estimation: On average, 1 token ≈ 4 characters or ≈ 0.75 words in English. A typical sentence contains 15-20 tokens.

​
Input vs Output Tokens

Our pricing distinguishes between two types of tokens:

Input Tokens

Text you send to the model (prompts, context, system messages)

Output Tokens

Text generated by the model in response
Why different pricing? Output tokens typically cost more because:
  • Generation requires more computational resources
  • Each output token depends on processing all previous tokens
  • Models must maintain context throughout generation

​
Pricing Structure

​
Example: DeepSeek V3 0324

Let’s break down the pricing for our popular DeepSeek: DeepSeek V3 0324 model: 
{
  "model": "deepseek-v3-0324",
  "pricing": {
    "input": {
      "unit": "1M tokens",
      "price_per_million_t": 0.22,
      "price_per_token_usd": "0.00000022"
    },
    "output": {
      "unit": "1M tokens",
      "price_per_million_t": 0.44,
      "price_per_token_usd": "0.00000044"
    }
  }
}

​
Know What You’re Paying For

Here’s how costs are calculated for a typical interaction:
1

Count Input Tokens

Your prompt: “Write a Python function to calculate fibonacci numbers”
  • Input tokens: ~8 tokens
  • Cost: 8 × 0.00000004=0.00000004 = 0.00000032
2

Count Output Tokens

Model response: Complete Python function with comments (~617 tokens)
  • Output tokens: ~617 tokens
  • Cost: 617 × 0.00000022=0.00000022 = 0.00013574
3

Total Cost

Total: 0.00000032+0.00000032 + 0.00013574 = $0.00013606
This example interaction costs approximately $0.00013606 - less than a fraction of a cent!

​
Viewing Current Pricing

You can always check the latest pricing for all available models:

API Endpoint

GET https://api.routeway.ai/v1/models
Returns pricing data for all models

Web Interface

View pricing in our web dashboard with interactive calculator

​
Cost Comparison: Routeway vs. DeepSeek AI

Let’s compare the cost of running the same task using the DeepSeek V3 0324 model on Routeway versus DeepSeek AI’s own platform. Task:
Prompt: “Write a Python function to calculate Fibonacci numbers” (~8 tokens)
Response: Complete Python function with comments (~617 tokens).

Routeway (DeepSeek V3 0324)

Input Tokens: 8 × 0.00000022=0.00000022 = 0.00000176
Output Tokens: 617 × 0.00000044=0.00000044 = 0.00027148
Total Cost: $0.00027324

DeepSeek AI (DeepSeek V3 0324)

Input Tokens: 8 × 0.00000027=0.00000027 = 0.00000216
Output Tokens: 617 × 0.00000055=0.00000055 = 0.00033935
Total Cost: $0.00034151
Note: Pricing is based on published rates as of July 2025.

​
Summary

For this example, running the DeepSeek V3 0324 model on Routeway costs $0.00027324 per interaction, while the same task on DeepSeek AI’s platform costs $0.00034151. This means DeepSeek AI’s own platform is approximately 25% more expensive than Routeway for this usage. In addition to lower cost, Routeway provides benefits like a unified API, real-time usage monitoring, and flexible billing options, making it a more versatile choice.

​
Payment Methods

We accept the following payment methods:

Crypto Payments

+ Bitcoin, Ethereum, USDC via Coinbase Commerce
+ Instant settlement
+ Low transaction fees

​
FAQs

If you’ve set up spending limits, your API access will be temporarily suspended once the limit is reached. You can increase the limit or wait for the next billing cycle.
Our Pay-As-You-Go model means you only pay for what you use - there are no pre-paid credits to refund. You’re only billed for actual token consumption.
⌘I