llm-inference
Use when wanting to interact with any LLM - Explains available inference endpoints so the agent selects suitable models.
When & Why to Use This Skill
This Claude skill enables seamless interaction with multiple Large Language Models (LLMs) through OpenAI-compatible inference endpoints. It empowers agents to intelligently select the most appropriate model—ranging from high-speed options like Llama 3.1 to powerful reasoning models like GLM-4—based on specific task requirements, context window constraints, and performance needs.
Use Cases
- Dynamic Model Selection: Automatically routing simple text processing tasks to fast, efficient models like Llama-3.1-8b while reserving complex reasoning or creative tasks for high-parameter models like GPT-OSS-120B.
- Large-Scale Document Processing: Utilizing models with 65,536 token context windows to analyze extensive datasets, long-form reports, or entire codebases without losing context.
- Cross-Model Format Standardization: Leveraging diverse inference providers to transform arbitrary strings into structured formats (JSON, Markdown) by applying explicit system prompts across different model architectures.
- Performance Optimization: Balancing request-per-minute limits and token throughput by switching between available endpoints to maintain agent responsiveness during high-load periods.
| name | llm-inference |
|---|---|
| description | "Use when wanting to interact with any LLM - Explains available inference endpoints so the agent selects suitable models." |
LLM Inference
The Cloudflare Pages function functions/cerebras-chat.ts provides OpenAI-compatible LLM inference. See tools/cerebras-llm-inference/index.html for a working example.
Available models
| Model | Max context tokens | Requests / minute | Tokens / minute |
|---|---|---|---|
| gpt-oss-120b | 65,536 | 30 | 64,000 |
| llama-3.3-70b | 65,536 | 30 | 64,000 |
| llama3.1-8b | 8,192 | 30 | 60,000 |
| qwen-3-235b-a22b-instruct-2507 | 65,536 | 30 | 64,000 |
| qwen-3-235b-a22b-thinking-2507 | 65,536 | 30 | 60,000 |
| qwen-3-32b | 65,536 | 30 | 64,000 |
| zai-glm-4.6 | 64,000 | 10 | 150,000 |
llama3.1-8bis the fastest option.zai-glm-4.6is the most powerful option.gpt-oss-120bremains the best all rounder.
LLMs are not just for chat: they can be used to process any string in any arbitrary way. If making a tool that requires the LLM to respond in a specific way or format then be very clear and explicit in its system prompt; eg what to include/exclude, plain/markdown formatting, length, etc.