groq-inference
Fast LLM inference with Groq API - chat, vision, audio STT/TTS, tool use. Use when: groq, fast inference, low latency, whisper, PlayAI TTS, Llama, vision API, tool calling, voice agents, real-time AI.
npx skills add majiayu000/claude-skill-registry --skill groq-inference-skill --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# GROQ Inference Skill Ultra-fast LLM inference for real-time applications. GROQ delivers 10-100x faster inference than standard providers. ## Quick Reference: Model Selection | Use Case | Model ID | Context | Notes | |----------|----------|---------|-------| | **General Chat** | `llama-3.3-70b-versatile` | 128K | Best all-around | | **Fast Chat** | `llama-3.1-8b-instant` | 128K | Simple tasks, fastest | | **Vision/OCR** | `meta-llama/llama-4-scout-17b-16e-instruct` | 128K | Up to 5 images | | **STT** | `whisper-large-v3` | 448 | GROQ-hosted (NOT OpenAI API) | | **TTS** | `playai-tts` | - | Fritz-PlayAI voice | | **Reasoning** | `meta-llama/llama-4-maverick-17b-128e-instruct` | 128K | Thinking models | | **Tool Use** | `compound-beta` | - | Built-in web search, code exec | ## Core Patterns ### 1. Chat Completion (Basic + Streaming) ```python import os from groq import Groq, AsyncGroq client = Groq(api_key=os.environ.get("GROQ_API_KEY")) def chat(prompt: str, system: str = "You are helpful.") -> str: response = client.chat.completions.create( model="llama-3.3-70b-versatile", messages=[ {"role": "system", "content": system}, {"role": "user", "content": prompt} ], temperature=0.7, max
- Quick Reference: Model Selection
- Core Patterns
- 1. Chat Completion (Basic + Streaming)
- 2. Vision / Multimodal
- 3. Audio: Speech-to-Text (GROQ-Hosted Whisper)
- 4. Audio: Text-to-Speech (PlayAI)
- 5. Tool Use / Function Calling
- 6. Compound Beta (Built-in Web Search + Code Exec)
- 7. Reasoning Models
- 8. Async Patterns
- Rate Limits
- Integration Notes
- Environment Variables
- Reference Files
Optional multi-provider
What does the groq-inference skill do?
Fast LLM inference with Groq API - chat, vision, audio STT/TTS, tool use. Use when: groq, fast inference, low latency, whisper, PlayAI TTS, Llama, vision API, tool calling, voice agents, real-time AI.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill groq-inference-skill --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.