compound-beta-mini
Preview
Compound-beta-mini is a compound AI system powered by an openly available model already supported in GroqCloud to intelligently and selectively use tools to answer user queries, starting first with web search and code execution.
Rate limits for compound-beta and compound-beta-mini are determined by the rate limits of the individual models that comprise them.
Key Technical Specifications
Model Architecture
Compound-beta-mini leverages Llama 3.3 70B to automatically use tools. Unlike compound-beta, it can only use one tool per request.
Performance Metrics
Groq developed a new evaluation benchmark for measuring search capabilities called RealtimeEval. This benchmark is designed to evaluate tool-using systems on current events and live data. On the benchmark, Compound Beta Mini outperformed GPT-4o-search-preview and GPT-4o-mini-search-preview significantly.
Learn More About Agentic Tooling
Discover how to build powerful applications with real-time web search and code execution
Technical Details
| FEATURE | VALUE |
|---|---|
| Context Window (Tokens) | 128K |
| Max Output Tokens | 8,192 |
| Max File Size | N/A |
| Token Generation Speed | 275 tokens per second |
| Input Token Price | Varies. Pricing is based on input tokens to underlying models (while in preview) |
| Output Token Price | Varies. Pricing is based on output tokens from underlying models (while in preview) |
| Tool Use |  |
| Agentic Tooling |  |
| JSON Mode | |
| Image Support | |
Use Cases
Realtime Web Search
Automatically access up-to-date information from the web using the built-in web search tool powered by Tavily.
Code Execution
Execute Python code automatically using the code execution tool powered by E2B.
Code Generation and Technical Tasks
Create AI tools for code generation, debugging, and technical problem-solving with high-quality multilingual support.
Best Practices
- Use system prompts to improve steerability and reduce false refusals. Compound-beta-mini is designed to be highly steerable with appropriate system prompts.
- Consider implementing system-level protections like Llama Guard for input filtering and response validation.
- Deploy with appropriate safeguards when working in specialized domains or with critical content.
- Compound-beta-mini should not be used by customers for processing protected health information. It is not a HIPAA Covered Cloud Service under Groq's Business Associate Addendum for customers at this time.
Quick Start
Experience the capabilities of compound-beta-mini on Groq:
pip install groq1from groq import Groq
2client = Groq()
3completion = client.chat.completions.create(
4 model="compound-beta-mini",
5 messages=[
6 {
7 "role": "user",
8 "content": "Explain why fast inference is critical for reasoning models"
9 }
10 ]
11)
12print(completion.choices[0].message.content)