LLM Inference Pricing Research Server
In this project, you are going to make a chatbot to scrape LLM Inference Serving websites to research costs of serving various LLMs. You will do this by writing an MCP Server that hooks up to Firecrawl's API and saving the data in a SQLite Database. You should use the following websites to scrape:
- "cloudrift": "https://www.cloudrift.ai/inference"
- "deepinfra": "https://deepinfra.com/pricing"
- "fireworks": "https://fireworks.ai/pricing#serverless-pricing"
- "groq": "https://groq.com/pricing"
1. Make a venv with uv
2. Sync venv with pyproject.toml (`uv sync`)
3. Make an API Key on Anthropic and Firecrawl
4. Complete the 2 tool calls in `starter_server.py`
5. Change the `server_config.json` to point to your server file
6. Complete any section in `starter_client.py` that has "#complete".
7. Test using any methods taught in the course
8. Use the following prompts in your chatbot but play around with all the LLM providers in the list above:
- "How much does cloudrift ai (https://www.cloudrift.ai/inference) charge for deepseek v3?"
- "How much does deepinfra (https://deepinfra.com/pricing) charge for deepseek v3"
- "Compare cloudrift ai and deepinfra's costs for deepseek v3"
TDQS
Scored across 2 tools
The two tools have clearly distinct purposes: 'scrape_websites' performs the scraping operation to gather data, while 'extract_scraped_info' retrieves and formats previously scraped information. There is no overlap in functionality - one creates data, the other queries it.
Both tools use snake_case naming which is consistent, but they follow different verb patterns: 'scrape_websites' uses a verb_noun format while 'extract_scraped_info' uses verb_adjective_noun. This minor deviation prevents a perfect score, but the naming is still clear and readable.
With only 2 tools for a 'LLM Inference Pricing Research Server', the surface feels severely underpowered. The server's name suggests comprehensive pricing research capabilities, but the tools only cover basic website scraping and data extraction - missing essential operations like price comparison, model benchmarking, cost analysis, or API integration that would be expected for this domain.
The toolset is severely incomplete for the stated purpose of 'LLM Inference Pricing Research'. While scraping and extraction are useful first steps, there are no tools for analyzing pricing data, comparing providers, calculating costs, or generating research reports. The server provides only data collection capabilities without the analysis tools needed to fulfill its research purpose.