providers

What problem does it solve?

Managing multiple LLM providers (OpenAI, Anthropic, Google, Ollama) often means dealing with different APIs and SDKs, hindering flexibility and access to unique features. This Skill unifies access and enables provider-specific optimizations, saving you integration effort.

Core Features & Use Cases

• Unified Provider Access: Switch between LLM providers with minimal code changes, leveraging a consistent interface for core functionalities.
• Raw SDK Access: Directly access underlying provider SDKs (e.g., openai.AsyncOpenAI) for advanced, provider-specific features like OpenAI's logprobs or Anthropic's prompt caching.
• Multi-Provider Fallbacks: Configure automatic failover to alternative providers in case of outages or rate limits, ensuring application resilience and continuous operation.
• Use Case: Optimize costs by trying a cheaper provider first, then falling back to a more expensive but reliable one, or use Anthropic's prompt caching for long system prompts to save up to 90% on token costs.

Quick Start

Use the providers skill to get the raw OpenAI client and make a chat completion request to 'gpt-4o' with 'logprobs' enabled.