At Reka, we are committed to building the next generation of multimodal agents. As summer draws to a close, we're excited to share a summary of our latest releases and enhancements! Our team has been hard at work bringing you new features designed to improve your experience.

APIs Free tier

We're excited to announce our free tier as part of our September release! Starting this month, we're introducing automatic monthly credit refreshes. Every start of the month, users will receive $10 in free credits that can be used for any API feature. This means you'll have consistent access to explore and utilize our platform's capabilities without interruption.

What can you get with 10$ you may ask? Here some ideas:

• Make 400 research requests about turtles, to finish your big project in time.

• Analyze 250 images for a marketing campaign showcasing the versatility of AI in various industries.

• Translate 1000 minutes of audio content into a different language, perhaps to create a funny dubbed version of a classic movie scene.

Each of these examples demonstrates the versatility and potential of Reka's products, whether you're looking to add a touch of humor to your day or enhance your professional projects with engaging visuals and audio content.

Reka Vision API

We announced in July Reka Vison designed for physical world understanding and search. Today, we are proud to share that the API, of Reka Vision, is now available. Paired with this API is documentation and code samples to help you get started and experiment with our Vision API.

Reka Vision is your next-generation multimodal AI platform built to interpret, search, and reason across video and image content at scale and with unprecedented accuracy.

Create your own of multimodal agents with the following capabilities:

• Video Management (Watch): upload an image or a video and let our model analyze the scenes, process audio, and interpret textual cues to create internal representations of the uploaded data. This is a one time process. Reka Vision will always remember until it is instructed to delete the memory.

• Video Search: Find exact moments in videos with natural language. Search for "delivery truck" or more complex activities and receive the exact timestamps when it appears.

• Video QA (Chat): Get comprehensive, detailed descriptions of any photo or video content. Engage in conversations with your visual content using everyday language. Ask questions like "What products are displayed on the shelf?" or "How many people entered the building between 2-4 PM?"

From content moderation to security monitoring, from media analysis to automated cataloging, Reka Vision empowers you to extract meaningful insights from visual data at scale. The era of truly intelligent visual processing has arrived!

You get 2 hours of free video upload and unlimited search and QA. Contact us to unlock a higher upload limit, we have an extensive startup partnership program.

Reka Research Updates

Reka Research is your gateway to the world's most comprehensive and intelligent web research capabilities, and it just got even more powerful! Whether you're conducting market analysis, competitive research, or exploring emerging trends, Reka Research doesn't just find information, it discovers the most valuable, accurate, and contextually relevant data the internet has to offer. Use this API to discover, analyze, and synthesize information from across the digital landscape.

MCP Server

We now have a Model Context Protocol (MCP) server providing AI-powered fact-checking and similarity search using Reka Research API. This server is hosted remotely and ready to use—no local installation required! Connect your agent with our MCP server to give it the power to perform certain kinds of research.

The Reka Research MCP server is accessible at reka-research-mcp.vercel.app/mcp. To use it, simply configure your MCP client to connect to this endpoint. It integrates seamlessly with various tools, including VS Code and Claude Desktop.

For comprehensive details or instructions on local deployment, please refer to our open-source GitHub repository.

New API Parameter

user_location

We're proud to unveil our User Location feature! Now you can harness the power of location-aware research by simply including the user_location parameter in your API calls. Instead of having the user enter the location when looking for the weather forecast or for a nearby restaurant, you could pass the location from the device or browser to the API and provide personalized responses.

We can't wait to share our demo using this feature (spoiler: check out our YouTube channel tomorrow), meanwhile learn more about it here. 

Open Community

Join our Discord community with all the best community members, would it be to share, help, or ask questions. 

It’s time!

We're thrilled about these updates and can't wait for you to explore them!

Looking ahead, our team will be present at several upcoming events where we'll be showcasing live demos and providing samples of these new features. Make sure to mark your calendars!

• Agentic AI Conference: 15-19 September online. Register now!

• IBC Show: 15-19 September at Amsterdam Come see us!

• Tech Week: 6-12 October at San Francisco. Register now!

Stay tuned in the coming days for more detailed demonstrations and samples of all these exciting new features! We'll be sharing more information on our social media channels and through our newsletter.