Interfaze

Beta

pricing

docs

blog

Get Started

Introduction

Examples

Vision

OCR (Image & Document)

Object Detection

GUI Detection

Web

Scraping

Audio

Speech-to-Text (STT)

Speaker Diarization

Translation

Code Sandboxing

Guardrails

Concepts

Precontext

Run Tasks

Structured Outputs

Reasoning

Streaming

Function Calling

Handling Files

Resources

Lowering costs & improving speed

Limits

Security

Supported Languages

FAQs

Projects

Interfaze as tools

Postgres LLM

Integrations

OpenAI SDK

Vercel AI SDK

Langchain SDK

n8n Integration

API Reference

Chat Completion API

Web search

copy markdown

The best web search index built on top of SERP and our growing web index which includes niche research indexes in all fields like:

Research indexes - biology, finance, medicine, law, arxiv, and many more
Social platforms - Linkedin, X, Personal sites, Private contact database
Financial data - stocks, forex, crypto, commodities, SEC filings, and more
General search - news, events, products, company information, and more

Basic web search

OpenAI SDK

Vercel AI SDK

LangChain SDK

const response = await interfaze.chat.completions.create({
	model: "interfaze-beta",
	messages: [{ role: "user", content: "Latest news on Nvidia" }],
});

console.log(response.choices[0].message.content);

//@ts-expect-error precontext is not typed
const precontext = response.precontext;
console.log("Web Search Results:", precontext[0]?.result);

Text output

**Strategic Partnerships and AI Factories:**

- Nvidia and Emerald AI are collaborating with major energy companies (AES, Constellation, Invenergy, NextEra Energy, Nscale Energy & Power, and Vistra) to develop "power-flexible AI factories." These factories aim to connect to the grid faster and generate valuable AI resources while potentially stabilizing the global energy grid.
- Nvidia's AI ecosystem is expanding with Marvell joining forces through NVLink Fusion, connecting Marvell to Nvidia's AI factory and AI-RAN.
- Roche is scaling Nvidia AI factories globally to accelerate drug discovery, diagnostic solutions, and manufacturing breakthroughs.
- Nvidia is also working with telecom leaders to build AI grids for optimizing inference on distributed networks and with T-Mobile and partners to integrate physical AI applications on AI-RAN-Ready infrastructure.
- Adobe and Nvidia have announced a strategic partnership to deliver the next generation of Firefly models and creative, marketing, and agentic workflows.
- Hyundai Motor, Kia, BYD, Geely, Isuzu, and Nissan are adopting NVIDIA DRIVE Hyperion for Level 4 autonomous vehicles.
- Mistral, a leading European AI provider, recently raised $830 million in new debt specifically to purchase 13,800 Nvidia chips.

**Key Initiatives and Technologies:**

- Nvidia is accelerating power-flexible AI factories to fortify the grid, focusing on efficiency at scale.
- The company is advancing open-source AI, donating its Dynamic Resource Allocation Driver for GPUs to the Kubernetes Community.
- Nvidia has announced an Open Physical AI Data Factory Blueprint to accelerate robotics, vision AI agents, and autonomous vehicle development.
- Nvidia has entered production with Dynamo, an inference operating system for AI factories.
- GTC 2026 showcased virtual worlds powering the physical AI era and highlighted NVIDIA RTX PCs and DGX Sparks running the latest open models and AI agents locally.
- 90 frames-per-second virtual reality is now available on GeForce NOW.
- Nvidia RTX-accelerated computers now connect directly to Apple Vision Pro.

**Market and Financial News:**

- Nvidia's CEO projects $1 trillion in AI chip sales as a new computing era begins.
- Nvidia reported record sales of $68 billion in the fourth quarter, beating back "bubble fears."
- Despite some market challenges, with the stock dipping below a critical trading range, analysts remain bullish on Nvidia.
- The company's latest reported earnings date is May 20, 2026.

**Other News:**

- Iran has reportedly threatened Nvidia, Apple, and other tech giants with attacks.
- Nvidia's CEO, Jensen Huang, emphasized the company's energy-efficient architecture.

JSON output

Web search result array can be found in the precontext property of the response.

Structured web search

OpenAI SDK

Vercel AI SDK

LangChain SDK

import { z } from "zod";
import { zodResponseFormat } from "openai/helpers/zod";

const NvidiaNewsSchema = z.object({
	summary: z.string(),
	current_stock_price: z.number(),
	links: z.array(z.string()),
});

const response = await interfaze.chat.completions.create({
	model: "interfaze-beta",
	messages: [{ role: "user", content: "Latest news on Nvidia" }],
	response_format: zodResponseFormat(NvidiaNewsSchema, "nvidia_news_schema"),
});

console.log(response.choices[0].message.content);

//@ts-expect-error precontext is not typed
const precontext = response.precontext;
console.log("Web Search Results:", precontext[0]?.result);

If you look through precontext you will be able to see that a web scrape was performed to get higher quality results from each page after the search results were returned.

Learn more about web scraping here.

JSON output (as of 2026-04-01)

People enrichment search

OpenAI SDK

Vercel AI SDK

LangChain SDK

import { z } from "zod";
import { zodResponseFormat } from "openai/helpers/zod";

const PersonSchema = z.object({
	summary: z.string(),
	company: z.string().optional(),
	emails: z.array(z.string()).describe("all unmasked email addresses").optional(),
	location: z.string().describe("City and country").optional(),
});

const response = await interfaze.chat.completions.create({
	model: "interfaze-beta",
	messages: [
		{
			role: "user",
			content: "Who is Yoeven D Khemlani, his company, his email and where is he based now?",
		},
	],
	response_format: zodResponseFormat(PersonSchema, "person_schema"),
});

console.log(response.choices[0].message.content);

//@ts-expect-error precontext is not typed
const precontext = response.precontext;
console.log("Web Search Results:", precontext[0]?.result);

JSON output

Web search raw outputs

Running Web search as a tasks with <task>web_search</task> in the system message make it faster and cheaper with a fixed structured output that's pre-defined.

Learn more about running a task.

OpenAI SDK

Vercel AI SDK

LangChain SDK

import { z } from "zod";
import { zodResponseFormat } from "openai/helpers/zod";

const response = await interfaze.chat.completions.create({
	model: "interfaze-beta",
	messages: [
		{ role: "system", content: "<task>web_search</task>" },
		{ role: "user", content: "GLP-1 research paper" },
	],
	response_format: zodResponseFormat(z.any(), "web_search_schema"),
});

console.log(response.choices[0].message.content);

//@ts-expect-error precontext is not typed
const precontext = response.precontext;
console.log("Web Search Results:", precontext[0]?.result);

JSON output

{
  "object": {
    "name": "web_search",
    "result": [
      {
        "title": "Glucagon-like peptide 1 (GLP-1) - PubMed",
        "description": "23 German Center for Diabetes Research (DZD), Neuherberg, Germany; Division of Metabolic Diseases, Department of Medicine, Technische Universität München, Munich, Germany; Helmholtz Zentrum München, German Research Center for Environmental Health (GmbH), Neuherberg, Germany. ... Background: The glucagon-like peptide-1 (GLP-1) is a multifaceted hormone with broad pharmacological potential.",
        "content": "23 German Center for Diabetes Research (DZD), Neuherberg, Germany; Division of Metabolic Diseases, Department of Medicine, Technische Universität München, Munich, Germany; Helmholtz Zentrum München, German Research Center for Environmental Health (GmbH), Neuherberg, Germany. ... Background: The glucagon-like peptide-1 (GLP-1) is a multifaceted hormone with broad pharmacological potential.",
        "url": "https://pubmed.ncbi.nlm.nih.gov/31767182/"
      },
      {
        "title": "Mapping the effectiveness and risks of GLP-1 receptor agonists - PubMed",
        "description": "<strong>Glucagon-like peptide 1 receptor agonists (GLP-1RAs) are increasingly being used to treat diabetes and obesity</strong>. However, their effectiveness and risks have not yet been systematically evaluated in a comprehensive set of possible health outcomes.",
        "content": "<strong>Glucagon-like peptide 1 receptor agonists (GLP-1RAs) are increasingly being used to treat diabetes and obesity</strong>. However, their effectiveness and risks have not yet been systematically evaluated in a comprehensive set of possible health outcomes.",
        "url": "https://pubmed.ncbi.nlm.nih.gov/39833406/"
      },
      {
        "title": "Pharmacogenomics of GLP-1 receptor agonists: a genome-wide analysis of observational data and large randomised controlled trials - PubMed",
        "description": "<strong>Predicting the response to GLP-1 receptor agonists: an unexpected role for β-arrestin-1.</strong> Sladek R. Sladek R. Lancet Diabetes Endocrinol. 2023 Jan;11(1):3-4. doi: 10.1016/S2213-8587(22)00357-6. Lancet Diabetes Endocrinol.",
        "content": "<strong>Predicting the response to GLP-1 receptor agonists: an unexpected role for β-arrestin-1.</strong> Sladek R. Sladek R. Lancet Diabetes Endocrinol. 2023 Jan;11(1):3-4. doi: 10.1016/S2213-8587(22)00357-6. Lancet Diabetes Endocrinol.",
        "url": "https://pubmed.ncbi.nlm.nih.gov/36528349/"
      },
      {
        "title": "GLP-1 physiology informs the pharmacotherapy of obesity - PubMed",
        "description": "Scope of review: <strong>Here I discuss the physiology of Glucagon-like peptide-1 (GLP-1) action in the control of food intake in animals and humans</strong>, highlighting the importance of gut vs. brain-derived GLP-1 for the control of feeding and body weight.",
        "content": "Scope of review: <strong>Here I discuss the physiology of Glucagon-like peptide-1 (GLP-1) action in the control of food intake in animals and humans</strong>, highlighting the importance of gut vs. brain-derived GLP-1 for the control of feeding and body weight.",
        "url": "https://pubmed.ncbi.nlm.nih.gov/34626851/"
      },
      {
        "title": "A review of GLP-1 receptor agonists: Evolution and advancement, through the lens of randomised controlled trials - PubMed",
        "description": "Aims: <strong>To review the evolution and advancement of GLP-1</strong> receptor agonist (GLP-1RA) therapy, through the lens of randomised controlled trials, from differentiating characteristics, efficacy, safety, tolerability, and cardiovascular outcomes, to ...",
        "content": null,
        "url": "https://pubmed.ncbi.nlm.nih.gov/29364586/"
      }
    ]
  },
  "finishReason": "stop",
  "usage": {
    "inputTokens": 2362,
    "outputTokens": 7030,
    "totalTokens": 9392
  },
  "response": {
    "id": "interfaze-1775115604419",
    "modelId": "interfaze-beta",
    "body": {
      "id": "interfaze-1775115604419",
      "object": "chat.completion",
      "model": "interfaze-beta",
      "usage": {
        "prompt_tokens": 2362,
        "completion_tokens": 7030,
        "total_tokens": 9392
      }
    }
  }
}

GUI Detection

Scraping