Mercury 2 Integrations

OpenAI’s mission is to ensure that artificial general intelligence (AGI)—by which we mean highly autonomous systems that outperform humans at most economically valuable work—benefits all of humanity. We will attempt to directly build safe and beneficial AGI, but will also consider our mission fulfilled if our work aids others to achieve this outcome. Apply our API to any language task — semantic search, summarization, sentiment analysis, content generation, translation, and more — with only a few examples or by specifying your task in English. One simple integration gives you access to our constantly-improving AI technology. Explore how you integrate with the API with these sample completions.

GPT-4.1 is an advanced AI model from OpenAI, designed to enhance performance across key tasks such as coding, instruction following, and long-context comprehension. With a large context window of up to 1 million tokens, GPT-4.1 can process and understand extensive datasets, making it ideal for tasks like software development, document analysis, and AI agent workflows. Available through the API, GPT-4.1 offers significant improvements over previous models, excelling at real-world applications where efficiency and accuracy are crucial.

LiveKit is a real-time platform that enables developers to build video, voice, and data capabilities into their applications. Building on WebRTC, it supports a broad range of frontend and backend platforms. LiveKit's network is optimized for ultra-low latency, extreme resiliency, and massive scale. Our team is distributed across the world, and our infrastructure delivers billions of minutes of audio and video every month. LiveKit provides SDK support across all major platforms, allowing you to code your application with a LiveKit client natively designed for your platform of choice. You can self-host LiveKit for free without changing a line of code, as the entire ecosystem of tools and services is Apache 2.0 open source. LiveKit offers a feature-rich platform, including SSO and RBAC for teams, enterprise-grade security with end-to-end encryption, noise and echo cancellation, session recording, stream ingestion, and moderation tools.

Pipecat is an open source framework and ecosystem for building real-time voice and multimodal conversational AI agents. It gives developers everything they need to create, deploy, and scale AI applications that can see, hear, and speak, while orchestrating audio, video, AI services, transports, and conversation pipelines with ultra-low latency. The core Pipecat framework is a Python-based system for building voice and multimodal AI pipelines, helping teams connect components such as speech-to-text, LLMs, text-to-speech, vision, video, transports, and business logic without manually wiring every service from scratch. Pipecat is designed to be vendor-neutral and composable, supporting more than 100 AI services so developers can choose the models and providers that fit each use case. Its ecosystem includes Pipecat Subagents for coordinating specialized agents with handoff, task dispatch, and distributed deployment.

GroqCloud is a high-performance AI inference platform built specifically for developers who need speed, scale, and predictable costs. It delivers ultra-fast responses for leading generative AI models across text, audio, and vision workloads. Powered by Groq’s purpose-built LPU (Language Processing Unit), the platform is designed for inference from the ground up, not adapted from training hardware. GroqCloud supports popular LLMs, speech-to-text, text-to-speech, and image-to-text models through industry-standard APIs. Developers can start for free and scale seamlessly as usage grows, with clear usage-based pricing. The platform is available in public, private, or co-cloud deployments to match different security and performance needs. GroqCloud combines consistent low latency with enterprise-grade reliability.

Inception Labs is pioneering the next generation of AI with diffusion-based large language models (dLLMs), a breakthrough in AI that offers 10x faster performance and 5-10x lower cost than traditional autoregressive models. Inspired by the success of diffusion models in image and video generation, Inception’s dLLMs introduce enhanced reasoning, error correction, and multimodal capabilities, allowing for more structured and accurate text generation. With applications spanning enterprise AI, research, and content generation, Inception’s approach sets a new standard for speed, efficiency, and control in AI-driven workflows.

We’ve built the fastest AI accelerator, based on the largest processor in the industry, and made it easy to use. With Cerebras, blazing fast training, ultra low latency inference, and record-breaking time-to-solution enable you to achieve your most ambitious AI goals. How ambitious? We make it not just possible, but easy to continuously train language models with billions or even trillions of parameters – with near-perfect scaling from a single CS-2 system to massive Cerebras Wafer-Scale Clusters such as Andromeda, one of the largest AI supercomputers ever built.

Retell AI is an advanced platform that enables businesses to build, test, deploy, and monitor AI-powered voice agents for seamless customer interactions. With features like call transfer, appointment scheduling, and knowledge base synchronization, it allows for the creation of lifelike conversations with minimal latency. The platform supports integration with various telephony systems and offers multilingual capabilities, making it suitable for global operations. Retell AI's scalable infrastructure ensures reliable performance, handling high call volumes efficiently. Additionally, it provides robust monitoring tools to analyze call performance and user sentiment, facilitating continuous improvement of voice agents.

Voice AI for any application. Vapi lets developers build, test and deploy voicebots in minutes rather than months. Solutions for everything. Customer support, front desk, outbound sales, lead generation, telehealth, food ordering, transportation logistics, employee training, roleplay, or whatever else you want to build. We’re making voice AI’s as simple, reliable, and accessible as any other API in your stack. All the power with all the customizability. Plug in any model or voice, and talk to it everywhere.