跳到正文
TakoAPI
返回技能列表

litellm

由 ishaan-jaff 提供

Coding Agents & IDEs
1.3k下载量由 clawskills.sh 提供
1星标
0浏览量
0 个赞登录后即可为这个技能点赞
—暂无评分
你的评分

简介

Call 100+ LLM providers through LiteLLM's unified API.

描述

该技能的功能

LiteLLM provides a unified Python API to call 100+ LLM providers using the same interface. It handles routing, so you can switch between OpenAI, Anthropic, Google, and others without rewriting call logic. A proxy mode adds caching, rate limiting, and observability on top.

Instead of maintaining separate SDK integrations for each provider, one call signature works across all of them.

何时使用

  • Route code review tasks to GPT-4o while running on Claude
  • Compare outputs from three models on the same prompt
  • Switch to gpt-4o-mini for simple classification to cut costs
  • Access Gemini or Mistral from a runtime that only supports OpenAI format
  • Point all LLM calls through a shared proxy for usage tracking

示例工作流

输入

User asks: compare how GPT-4o and Claude answer 'What is the best sorting algorithm?'

智能体
  1. 1

    Import litellm and define the prompt as a messages list

  2. 2

    Loop over ["gpt-4o", "claude-sonnet-4-20250514"]

  3. 3

    Call litellm.completion(model=model, messages=prompt) for each

  4. 4

    Extract response.choices[0].message.content from each result

  5. 5

    Print each model name alongside its response

输出

Side-by-side text outputs from GPT-4o and Claude for the same question

前置要求

  • OPENAI_API_KEY environment variable (for OpenAI models)
  • ANTHROPIC_API_KEY environment variable (for Anthropic models)

安装

clawhub install ishaan-jaff/litellm

运行 CLI 命令,或把这段提示词粘贴到 Claude Code、Cursor、Codex 或你在用的任意编程智能体里。

链接