a2a-python VS openrouter-runner

A2A SDK - The underlying A2A protocol implementation

The official a2a-python SDK from Google has been frequently updated, and our tutorial needs to keep up. In this article, we'll implement a simple CurrencyAgent using version 0.2.3 of the a2a-python SDK.

from langchain_openai import ChatOpenAI from langchain_community.tools import DuckDuckGoSearchRun from langchain.tools import Tool from langchain.memory import ConversationBufferMemory from langchain.agents.agent_types import AgentType from langchain.agents import initialize_agent from dotenv import load_dotenv import os load_dotenv() def webSearchAgent(question): llm = ChatOpenAI( model = "deepseek/deepseek-chat-v3-0324:free", base_url = "https://openrouter.ai/api/v1", api_key = os.getenv("OPENROUTER_API_KEY"), ) search = DuckDuckGoSearchRun() tool = [ Tool ( name = "search", func = search.run, description = "When you want real time data use this", ) ] memory = ConversationBufferMemory(memory_key = "chat_history") agent = initialize_agent( llm = llm, tools = tool, agent = AgentType.CONVERSATIONAL_REACT_DESCRIPTION, memory = memory, verbose = True, handle_parsing_errors = True ) result = agent.run(question) print(f"Agent:\n\n {result}") webSearchAgent("Give me some latest news about Ai")

OpenRouter API Key → Create an account at OpenRouter and grab your key

OpenRouter (multi-model API wrapper) https://openrouter.ai

{ "Providers": [ { "name": "openrouter", "api_base_url": "https://openrouter.ai/api/v1/chat/completions", "api_key": "sk-xxx", "models": [ "anthropic/claude-sonnet-4" ], "transformer": { "use": ["openrouter"] } } ], "Router": { "default": "openrouter,anthropic/claude-sonnet-4" }, "LOG": true, "HOST": "127.0.0.1", + "PORT": 23456 }

OpenRouter - We love OpenRouter because it allows you to easily try out new models and load balance between models. We actually got an open source contribution for this one recently, so we should be supporting it ❤️

Link: Promptfoo Open Source Tool for Evaluation and Red Teaming Link: OpenRouterFor Moonshot Kimi K2 APIs Link: Kimi K2 Model Model Page

Then I discovered OpenRouter: "a unified API platform that provides access to a wide range of large language models with intelligent routing and automatic fallbacks." You can use whatever model you want with the same API key. But the feature I really needed was its provisionary API key system, which allowed me to generate one master key and programmatically:

What’s different is all the open weight models like Kimi-k2 or Qwen-3 Coder that are as good and, depending on the task, better than Anthropic’s Sonnet model for 80% less via openrouter [1] and other similar services.

You can use these models through Claude Code; I do it everyday.

Some developers are running smaller versions of these LLMs on their own hardware, paying no one.

So I don’t think Anthropic and the other companies can dramatically increase their prices without losing the customers that helped them go from $0 to $4 billion in revenue in 3 years.

Users can easily move between different AI platforms with no lock-in, which makes it harder to increase prices and proceed to enshitify their platforms.

[1]: https://openrouter.ai/