Tavily

If you already use the OpenAI Python SDK, you already know how to call a model: from openai import OpenAI client = OpenAI( api_key="sk-or-...", base_url="https://api.openai.com/v1" ) response = client.chat.completions.create( model="gpt-4o", messages=[{"role": "user", "content": "What changed in EU AI regulation this week?"}] ) print(response.choices[0].message.content) Now add one thing: live web search. With most OpenAI-compatible gateways, you don’t need tools, a search key, or an agent loop. You only change the base_url. ...

Tavily is the default answer to “how do I give my agent web search?” It has a clean API, good retrieval quality, and a free tier. But it also has a separate account, a separate API key, and a separate dollar-denominated bill. The friction is not the dollar part. It is the second of everything: a second signup, a second key, a second dashboard, a second line on your statement. This post compares the realistic alternatives — what they replace, how they bill, and where each one fits. ...

If you’re building with DeepSeek, Qwen, or GLM outside China, you’ve probably wondered: does using a Chinese open-weight model mean my users get Chinese search results? Short answer: no — but only if the search source is separate from the model. The confusion is understandable. Most developers assume “the model” and “the search” come from the same place. They don’t. Here’s what’s actually happening, and how to control it. The model does reasoning. The search source decides what it reads. An open-weight model — whether DeepSeek V4, Qwen3.8, or GLM-5.3 — is a set of weights. It doesn’t “search the internet” on its own. When a response includes web results, those results were fetched by a separate search layer and injected into the model’s context window before it generates text. ...