Web Search API Quickstart: Integrate in Minutes

llmwebsearchapi.com›authentication-base-url

Authentication & Base URL

To use the API, you need an API key. Sign up on the Get API key page with just an email and password. Your key appears immediately. No credit card is required for the trial credit. Use the base URL https://api.llmwebsearchapi.com/v1 with any OpenAI-compatible client. The model ID is uncensored. This model is open-weight and tuned to answer without refusals for lawful adult, fictional, or controversial topics. It is not GPT, Claude, or another vendor's model.

llmwebsearchapi.com›basic-chat-completion-request

Basic Chat Completion Request

Send a standard chat completion request to extract text from search results. The API accepts messages and returns a completion. Use the model uncensored to ensure no content filters block your data. The request body supports up to 8 MB. Below is a cURL example for a basic extraction task.

Copycurl https://api.llmwebsearchapi.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Write a blunt product review of a cheap VPN."}]
  }'

The response includes the generated text, which you can then pass to your agent's memory or summary layer.

llmwebsearchapi.com›sdk-examples-for-python-and-javascript

SDK Examples for Python and JavaScript

Use the official OpenAI SDKs for Python and Node.js. Set the base_url to our endpoint and provide your API key. The Python SDK handles streaming and JSON parsing automatically. The Node SDK works similarly. Below is a Python example showing how to initialize the client and send a request.

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.llmwebsearchapi.com/v1", api_key="YOUR_KEY")

resp = client.chat.completions.create(
    model="uncensored",
    messages=[{"role": "user", "content": "Summarise this thread without softening it."}],
)
print(resp.choices[0].message.content)

For JavaScript, the setup is nearly identical. Set the environment variable or pass the key directly. The model ID remains uncensored.

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.llmwebsearchapi.com/v1", apiKey: process.env.API_KEY });

const resp = await client.chat.completions.create({
  model: "uncensored",
  messages: [{ role: "user", content: "Draft a villain monologue for my game." }],
});
console.log(resp.choices[0].message.content);

llmwebsearchapi.com›streaming-responses-for-real-time-processing

Streaming Responses for Real-Time Processing

Enable streaming by setting stream: true in your request. The API returns Server-Sent Events (SSE) tokens. This is useful for real-time processing of long search results. You can display tokens as they arrive or accumulate them for later use. The streaming response format matches the OpenAI standard. Below is a streaming example using cURL.

Copystream = client.chat.completions.create(
    model="uncensored",
    messages=[{"role": "user", "content": "Tell the story in second person."}],
    stream=True,
)
for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)

Parse the data field in each SSE message to get the partial text.

llmwebsearchapi.com›tool-calling-for-search-result-structuring

Tool Calling for Search Result Structuring

Use tool calling to structure extracted data. Define a schema for your desired output, such as a list of URLs or a summary object. The API returns structured JSON that matches your schema. This is ideal for populating AI agent memory with clean, typed data. Define the tool in the tools parameter and specify the function name. The model will respond with a function call object. You can then execute the function or store the result directly.

llmwebsearchapi.com›handling-context-windows-for-long-searches

Handling Context Windows for Long Searches

The context window is 64,000 tokens for prompt plus completion. If your search results exceed this, you must truncate or summarize them before sending. The API does not automatically handle long contexts. Send only the relevant text to stay within limits. If you exceed the limit, you will receive an error. Monitor your token usage to avoid unexpected costs. The price is $0.25 per 1M input tokens and $1.00 per 1M output tokens.

llmwebsearchapi.com›rate-limits-and-error-codes

Rate Limits and Error Codes

Rate limit is 300 requests per minute per key. The request body limit is 8 MB. If you send an invalid key, you get a 401 error. If you have no credit, you get a 402 error. If you exceed the rate limit, you get a 429 error. Regenerate your key at any time to revoke the old one. Each account has one key. The trial credit expires after 7 days. Top-up starts at $10 with bonus credit options.