Interfaze · Launch Video Breakdown: Hook, Pacing & Motion Design

Scene-by-scene timeline & spoken transcript

1. 0:00 – 0:50

   The Hook

   Unified Gateway for Web Search

   “Hey everyone, I'm excited to introduce Open Web Search, a unified gateway for web search. It's one API key, one structured format, and high availability. We've integrated with a bunch of different indexes, including Exa, Parallel, Brave, Perplexity, and more. Let's take a look at how it works. You can search for anything, like 'latest open source LLMs', and it will give you results from all the different providers. You can also specify a particular provider, like Perplexity, and it will give you results from just that provider. We also support JSON output, which is great for programmatic access. You can also search for things like 'Garry Tan's LinkedIn' and it will give you results from different providers like Brave, Parallel, and Exa. This is really powerful because it allows you to get a comprehensive view of the web without having to integrate with multiple APIs.”

   On screen

   OpenWebSearch The unified gateway for web search All search indexes, one API key, one structured format and high availability. Get API key -> Read the docs -> Exa Tavily Brave Bing Perplexity Parallel Apify Serp Valyu Octen + more Perplexity latest open source LLMs TRY browser automation updates latest open source LLMs AI infrastructure funding Garry Tan's LinkedIn retrieval augmented generation papers NVIDIA earnings highlights Results JSON Best Open Source LLMs 2026 - Telyrx DeepSeek V4, GLM K2, Kimi K2.6, Kimi K3, MiniMax M3, Qwen M3, and Gemma 4. Compare the best open-source LLMs of 2026 by benchmarks, context window, and use case. ... The best open-source LLMs in 2026 are DeepSeek V4, GLM K2, Kimi K2.6, Kimi K3, MiniMax M3, Qwen M3, 235B, and Google Gemma 4 31B - Kimi K2 posts the highest QPGH Diamond score of any open model at 93.5% per the Onyx Leaderboard. Open Source LLM Leaderboard 2026 - Vellum updated 24 Jul 2026 # Open Source LLM Leaderboard This open source LLM leaderboard displays the latest public benchmark performance for open-weight and open-source models released after April 2024. The data comes from model providers as well as independently run evaluations by Vellum or the open-source community. We feature results from non-saturated benchmarks, excluding outdated benchmarks. Best Open Source LLMs in 2026: We Reviewed 7 Models DeepSeek-VR-Pro-8B13 available now on Fireworks Blog ... The open-source model landscape is moving fast in 2026. GLM K2, Kimi K3 (described by Kimi as open source, though its full weights pending, scheduled for release by July 27, 2026), Kimi K2.7 Code, MiniMax Citation-backed, real-time answers This is a limited preview Demo. Create a free account for the full response, every provider, and control over each request. Get an API key -> Read the docs -> Get started with an agent Merge multiple providers Fallbacks for high uptime Switch search without switching code Switch search without switching code Brave Garry Tan's LinkedIn TRY browser automation updates latest open source LLMs AI infrastructure funding Garry Tan's LinkedIn retrieval augmented generation papers NVIDIA earnings highlights Results JSON Garry Tan - President & CEO, Y Combinator | LinkedIn linkedin.com/in/garrytan Garry Tan is a designer, PM & engineer turned investor and helper to startups. Subscribe to my YouTube channel at youtube.com/garrytan Founder, board partner and advisor at Initialized Capital, an early stage venture capital fund that was started by me. Garry Tan - Career Hacker | LinkedIn Experience: Career Hacker Location: Chester. View Garry Tan's profile on LinkedIn, a professional community of 1 million members. Garry Tan | LinkedIn Check out professional insights posted by Garry Tan, President & CEO, Y Combinator. We cannot provide a description for this page right now. Independent broad-web and media search normalized response Parallel Garry Tan's LinkedIn id: req-4f80a28-eb31-43c1-a9f1-e9fa6cf37e0e, provider: "parallel", query: "Garry Tan's LinkedIn", results: [ { "title": "Garry Tan", "url": "https://linkedin.com/in/garry-tan-7b751367", "snippet": "Position: A \nExperience: KLA \nSource": "linkedin.co", "published_date": null, "score": null } ] Exa Garry Tan's LinkedIn id: req-866572b0-9707-432b-9022-c931f0b58c", "provider": "exa", "query": "Garry Tan's LinkedIn", "results": [ { "title": "President & CEO, Y Combinator - Garry Tan", "url": "https://www.linkedin.com/in/garrytan", "snippet": "FirstName": "Garry", "LastName": "Tan", "Headline": "President & CEO, Y Combinator", "Location": "San Francisco, California, United States", "Source": "linkedin.com", "published_date": "2020-08-09", "score": null } ] usage: { "cost": 0.007, "result_count": 5 }

   Camera

   Static wide shot of a desktop browser window, with a picture-in-picture of the presenter in the bottom right.

   Motion

   Screen recording with live cursor interaction, showcasing product functionality. Text highlights and scrolling are the primary motion elements.

2. 0:50 – 1:50

   Product Reveal

   API Integration and Documentation

   “So how do you get started with Open Web Search? It's super simple. You can sign in to your account, and then you'll get an API key. We have comprehensive documentation that shows you how to make requests, what parameters are available, and what the unified response format looks like. You can see here an example of a TypeScript fetch request, where you can specify the provider, the query, and the number of results. We also have support for coding agents, so you can easily integrate Open Web Search into your AI applications. The authentication is straightforward, just a bearer token. And we have clear endpoints for search requests, including support for fallbacks and multiple providers.”

   On screen

   OpenWebSearch Sign in to your account Continue with Google By using this service, you agree to our Terms of Service and Privacy Policy. Run your first search fetch typescript const response = await fetch('https://api.openwebsearch.ai/v1/search', { method: 'POST', headers: { Authorization: `Bearer ${process.env.OPENWEBSEARCH_API_KEY}`, 'Content-Type': 'application/json', }, body: JSON.stringify({ provider: "exa", query: "What changed in browser automation this week", max_results: 10, }), }); const { results, provider, usage } = await response.json(); Use with a coding agent This reference is also published as an agent skill, so an agent can integrate OpenWebSearch without being walked through the API. npx skills add https://openwebsearch.ai Authentication Send your API key as a bearer token with every API request. Authorization: Bearer YOUR_API_KEY Authentication failures return a standard 401 error envelope. Endpoints Method Path Description POST /v1/search Search through one provider or an ordered fallback list. GET /v1/providers Discover providers, result limits, and parameter support. provider string Yes, unless provider is set One provider slug. providers string[] Yes, unless provider is set Ordered provider fallback list. Takes precedence over provider. allow_fallbacks boolean No Enables fallback through providers. Defaults to true for lists with multiple entries. strict_params boolean No Reject unsupported parameters instead of dropping them with a warning. Defaults to false. max_results integer No Number of results. Defaults to 10 and is capped per provider. country string No Two-letter ISO country code, such as "us". include_domains string[] No Restrict results to these domains. exclude_domains string[] No Exclude results from these domains. start_date string No Earliest publication date in YYYY-MM-DD format. end_date string No Latest publication date in YYYY-MM-DD format. recency string No One of hour, day, week, month, or year safe_search string No One of off, moderate, or strict. provider_options object No Provider-native options keyed by provider slug. You must provide either provider or a non-empty providers list. Query GET /v1/providers to discover the live provider slugs and supported parameters. Unified response Every successful request returns the same top-level shape. The provider field identifies the provider that actually served the request, including when a fallback was used.

   Camera

   Static wide shot of a desktop browser window, with a picture-in-picture of the presenter in the bottom right.

   Motion

   Screen recording with live cursor interaction, showcasing product documentation and code examples. Smooth scrolling and text highlighting.

3. 1:50 – 2:50

   Feature Teaser

   Diverse Indexes and Web Scraping

   “Open Web Search supports different indexes with different strengths. For people and companies, we have Exa and Valyu. For specialized datasets, we have Valyu. For agent-ready content, we have Parallel and Tavily. For broad web coverage, we have Brave and Bing. For real-time answers, Perplexity and Octen. And for SERP intelligence, Apify Serp. We also have a powerful feature to extract full webpages. You can provide a URL, and it will return structured JSON or markdown, bypassing bot detection. This is incredibly useful for real-time web scraping and data extraction. For example, you can extract information about Patrick Collison from his LinkedIn profile.”

   On screen

   Different indexes. Different strengths. There is no universally best search provider. Historical depth, people data, freshness, media coverage, and ranking quality vary by index. Choose the provider that fits the job without changing your integration. People & companies Exa Specialized datasets Valyu Specialized indexes and structured fields for professional profiles and company discovery. Research, financial, academic, and proprietary sources beyond the general web. Agent-ready content Parallel Tavily Broad web coverage Brave Bing Relevant excerpts and search nodes designed to feed research agents and AI applications. General web indexes with strong coverage across web pages, news, images, video, and local results. Real-time answers Perplexity Octen SERP intelligence Apify Serp Fresh web content for grounded answers, live information, and multi-step research workflows. Localized organic results, ads, rich result blocks, related queries, and rankings. Extract full webpage Extract full webpage content in structured JSON or markdown using Interfaze Al to bypass bot detection for real-time web scraping. linkedin.com/in/patrickcollison { "firstName": "Patrick", "lastName": "Collison", "headline": "Stripe CEO", "openToWork": false, "hiring": false, "about": "Dynamically communicate prospective opportunities and proactive technologies. Efficiently aggregate interactive materials before state of the art collaboration and idea-sharing. Credibly supply cross-media metrics via leading-edge solutions.\nSeamlessly embrace world-class imperatives and technically sound best practices. Black belt parallelization of prospective relationships via tactical leadership skills. Enthusiastically productive Patrick Collison 2nd Stripe CEO San Francisco Bay Area Contact info https://patrickcollison.com 82,886 followers Try on Interfaze ->

   Camera

   Static wide shot of a desktop browser window, with a picture-in-picture of the presenter in the bottom right.

   Motion

   Screen recording with live cursor interaction, highlighting different index categories and demonstrating web scraping functionality. Smooth scrolling.

4. 2:50 – 3:58

   Call to Action

   Pricing, Fallbacks, and Future

   “Now let's talk about pricing. We have a transparent pricing model where you buy credits and spend them on any provider. Each provider has its own pricing, for example, Apify Serp is $3.50-$6 per 1K requests, Brave is $5 per 1K requests, and so on. We also have built-in fallbacks for high uptime. If one provider fails, we automatically route to the next one. This ensures that your applications remain resilient. We're constantly adding new providers and features, so stay tuned for updates. We'd love to hear your feedback and see what you build with Open Web Search. Get started today!”

   On screen

   Pricing by provider Buy credits once and spend them on any provider below. Apify Serp Localized SERP features and rankings Brave Independent broad-web and media search Perplexity Citation-backed, real-time answers Parallel Token-dense excerpts for Al agents Exa People, companies, and semantic discovery Valyu Academic, financial, and proprietary data Tavily Fresh news and agent-ready research Bing Broad web, local, news, and image coverage Octen Real-time and multimodal web search $3.50-$6 / 1K requests $5 / 1K requests $5 / 1K requests $5-$15 / 1K requests $7-$37 / 1K requests $1.50-$30 / 1K requests Coming soon Coming soon Coming soon Method Path Description POST /v1/search Search through one provider or an ordered fallback list. GET /v1/providers Discover providers, result limits, and parameter support. Search request Send a JSON body to POST /v1/search. Parameter Type Required Description query string Yes A non-empty search query. provider string Yes, unless provider is set One provider slug. providers string[] Yes, unless provider is set Ordered provider fallback list. Takes precedence over provider. allow_fallbacks boolean No Enables fallback through providers. Defaults to true for lists with multiple entries. strict_params boolean No Reject unsupported parameters instead of dropping them with a warning. Defaults to true. max_results integer No Number of results. Defaults to 10 and is capped per provider. country string No Two-letter ISO country code, such as "us". include_domains string[] No Restrict results to these domains. exclude_domains string[] No Exclude results from these domains. start_date string No Earliest publication date in YYYY-MM-DD format. end_date string No Latest publication date in YYYY-MM-DD format. recency string No One of hour, day, week, month, or year safe_search string No One of off, moderate, or strict. provider_options object No Provider-native options keyed by provider slug. You must provide either provider or a non-empty providers list. Query GET /v1/providers to discover the live provider slugs and supported parameters. Unified response Every successful request returns the same top-level shape. The provider field identifies the provider that actually served the request, including when a fallback was used.

   Camera

   Static wide shot of a desktop browser window, with a picture-in-picture of the presenter in the bottom right.

   Motion

   Screen recording with live cursor interaction, highlighting pricing details and reiterating key features like fallbacks. Smooth scrolling.