providers
Use when switching between LLM providers, accessing provider-specific features (Anthropic caching, OpenAI logprobs), or using raw SDK clients - covers multi-provider patterns and direct SDK access for OpenAI, Anthropic, Google, and Ollama
npx skills add majiayu000/claude-skill-registry --skill providers --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.
# Multi-Provider Patterns and Raw SDK Access ## Installation ```bash # With uv (recommended) uv add llmring # With pip pip install llmring ``` **Provider SDKs (install what you need):** ```bash uv add openai>=1.0 # OpenAI uv add anthropic>=0.67 # Anthropic uv add google-genai # Google Gemini uv add ollama>=0.4 # Ollama ``` ## API Overview This skill covers: - `get_provider()` method for raw SDK access - Provider initialization and configuration - Provider-specific features (caching, extra parameters) - Multi-provider patterns and switching - Fallback behavior ## Quick Start ```python from llmring import LLMRing, LLMRequest, Message async with LLMRing() as service: # Get raw provider client openai_client = service.get_provider("openai").client anthropic_client = service.get_provider("anthropic").client # Use provider SDK directly response = await openai_client.chat.completions.create( model="gpt-4o", messages=[{"role": "user", "content": "Hello"}], logprobs=True # Provider-specific feature ) ``` ## Complete API Documentation ### LLMRing.get_provider() Get raw provider client for direct SDK access. **Signature:** ```python def get_provider(provider_type: str) -> BaseLLMProvider ``` *
- Installation
- API Overview
- Quick Start
- Complete API Documentation
- LLMRing.getprovider()
- Provider Clients
- Provider Initialization
- Provider-Specific Features
- OpenAI: Logprobs and Advanced Parameters
- OpenAI: Reasoning Models (o1 series)
- Anthropic: Prompt Caching
- Anthropic: Extended Thinking
- Google: Large Context and Multimodal
- Ollama: Local Models and Custom Options
With uv (recommended) uv add llmring With pip pip install llmring uv add openai>=1.0 # OpenAI uv add anthropic>=0.67 # Anthropic uv add google-genai # Google Gemini uv add ollama>=0.4 # Ollama OpenAI Anthropic
What does the providers skill do?
Use when switching between LLM providers, accessing provider-specific features (Anthropic caching, OpenAI logprobs), or using raw SDK clients - covers multi-provider patterns and direct SDK access for OpenAI, Anthropic, Google, and Ollama
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill providers --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.