LLmHub API Models and Pricing
Official API documentation for LLmHub API (api.llmhub.dev)
LLMHub provides intelligent model routing between multiple leading AI models, automatically selecting the best model for your specific prompt. When you use model="automatic", our system analyzes your prompt and routes it to the most suitable model based on the task requirements.
Available Models
Our platform currently supports the following models:
| Feature | DeepSeek-R1 (Hosted in America) | GPT-4o-mini | Meta Llama-3.3-70B |
|---|---|---|---|
| 1 Million Input Tokens | $1.35 | $0.15 | $0.71 |
| 1 Million Output Tokens | $5.40 | $0.60 | $0.71 |
| Router Selection Criteria | Advanced Logic and Reasoning Tasks | Basic Logic and Coding Tasks | Conversational and regular prompts |
How Automatic Model Selection Works
LLMHub's intelligent routing system analyzes your prompt's intent and requirements to determine which model will provide the best results. Here's how different types of prompts are typically routed:
Example 1: Complex Reasoning
Prompt:
Analyze the logical fallacies in this argument: 'All birds can fly. Penguins are birds. Therefore, penguins can fly.'Selected Model: DeepSeek-R1 (Hosted in America)
Reason: This prompt requires Advanced Logic and Reasoning Tasks, making DeepSeek-R1 the optimal choice.
Example 2: Coding Task
Prompt:
Write a function in Python to find the largest number in a list without using max().Selected Model: GPT-4o-mini
Reason: This coding task involves Basic Logic and Coding Tasks, which GPT-4o-mini handles efficiently at a lower cost.
Example 3: General Knowledge
Prompt:
Summarize the key advantages of cloud computing for small businesses.Selected Model: Meta Llama-3.3-70B
Reason: This prompt requires Conversational and regular prompts, which Meta Llama-3.3-70B excels at.
Pricing Details
Our pricing is based on the number of tokens processed. When using model="automatic", you'll be charged based on the model your request is routed to.
Cost Optimization
The automatic routing not only selects the best model for your task but also helps optimize costs. For simpler tasks, the system routes to more cost-effective models, ensuring you get the best balance of performance and value.
Enterprise Options
For enterprise customers, we offer:
- Custom routing logic tailored to your specific use cases
- Dedicated infrastructure for improved performance
- Volume discounts on token pricing
- Priority support and SLAs
Contact our sales team to learn more about enterprise options.