Fireworks AI 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.

AptlyStar.ai, powered by Aptly Technology Corporation, is an AI platform providing innovative solutions to enhance customer support and enhance workflow automation. With its intuitive tools, AptlyStar empowers businesses to build and deploy AI-powered agents, driving efficiency and productivity across teams.

Mixtral 8x7B is a high-quality sparse mixture of experts model (SMoE) with open weights. Licensed under Apache 2.0. Mixtral outperforms Llama 2 70B on most benchmarks with 6x faster inference. It is the strongest open-weight model with a permissive license and the best model overall regarding cost/performance trade-offs. In particular, it matches or outperforms GPT-3.5 on most standard benchmarks.

APIPark is an open-source, all-in-one AI gateway and API developer portal, that helps developers and enterprises easily manage, integrate, and deploy AI services. No matter which AI model you use, APIPark provides a one-stop integration solution. It unifies the management of all authentication information and tracks the costs of API calls. Standardize the request data format for all AI models. When switching AI models or modifying prompts, it won’t affect your app or microservices, simplifying your AI usage and reducing maintenance costs. You can quickly combine AI models and prompts into new APIs. For example, using OpenAI GPT-4 and custom prompts, you can create sentiment analysis APIs, translation APIs, or data analysis APIs. API lifecycle management helps standardize the process of managing APIs, including traffic forwarding, load balancing, and managing different versions of publicly accessible APIs. This improves API quality and maintainability.

E2B is an open source runtime designed to securely execute AI-generated code within isolated cloud sandboxes. It enables developers to integrate code interpretation capabilities into their AI applications and agents, facilitating the execution of dynamic code snippets in a controlled environment. The platform supports multiple programming languages, including Python and JavaScript, and offers SDKs for seamless integration. E2B utilizes Firecracker microVMs to ensure robust security and isolation for code execution. Developers can deploy E2B within their own infrastructure or utilize the provided cloud service. The platform is designed to be LLM-agnostic, allowing compatibility with various large language models such as OpenAI, Llama, Anthropic, and Mistral. E2B's features include rapid sandbox initialization, customizable execution environments, and support for long-running sessions up to 24 hours.

​LiteLLM is a versatile platform designed to streamline interactions with over 100 Large Language Models (LLMs) through a unified interface. It offers both a Proxy Server (LLM Gateway) and a Python SDK, enabling developers to integrate various LLMs seamlessly into their applications. The Proxy Server facilitates centralized management, allowing for load balancing, cost tracking across projects, and consistent input/output formatting compatible with OpenAI standards. This setup supports multiple providers. It ensures robust observability by generating unique call IDs for each request, aiding in precise tracking and logging across systems. Developers can leverage pre-defined callbacks to log data using various tools. For enterprise users, LiteLLM offers advanced features like Single Sign-On (SSO), user management, and professional support through dedicated channels like Discord and Slack.

Qwen3, the latest iteration of the Qwen family of large language models, introduces groundbreaking features that enhance performance across coding, math, and general capabilities. With models like the Qwen3-235B-A22B and Qwen3-30B-A3B, Qwen3 achieves impressive results compared to top-tier models, thanks to its hybrid thinking modes that allow users to control the balance between deep reasoning and quick responses. The platform supports 119 languages and dialects, making it an ideal choice for global applications. Its pre-training process, which uses 36 trillion tokens, enables robust performance, and advanced reinforcement learning (RL) techniques continue to refine its capabilities. Available on platforms like Hugging Face and ModelScope, Qwen3 offers a powerful tool for developers and researchers working in diverse fields.

BotDojo is an enterprise-grade AI enablement platform that empowers organizations to design, deploy, monitor, and scale intelligent agents across chat, voice, email, and web channels using a low-code visual workflow builder, while integrating deeply with enterprise data sources and systems. It provides over 100 ready-made templates to accelerate common use-cases (such as support automation, knowledge search, sales insights, and internal ops), supports branching logic, memory, tool orchestration (code, RPA, web browse), and connects to CRMs, ticketing systems, and databases. BotDojo also delivers human-feedback loops and continuous agent learning by enabling employees to coach agents via feedback queues, codifying corrections into memory and prompts, and evaluating performance through robust observability (audit trails, metrics such as deflection, first-contact resolution, and cost per interaction).

MiniMax-M2.1 is an open-source, agentic large language model designed for advanced coding, tool use, and long-horizon planning. It was released to the community to make high-performance AI agents more transparent, controllable, and accessible. The model is optimized for robustness in software engineering, instruction following, and complex multi-step workflows. MiniMax-M2.1 supports multilingual development and performs strongly across real-world coding scenarios. It is suitable for building autonomous applications that require reasoning, planning, and execution. The model weights are fully open, enabling local deployment and customization. MiniMax-M2.1 represents a major step toward democratizing top-tier agent capabilities.

MiniMax M2.5 is a frontier AI model engineered for real-world productivity across coding, agentic workflows, search, and office tasks. Extensively trained with reinforcement learning in hundreds of thousands of real-world environments, it achieves state-of-the-art performance in benchmarks such as SWE-Bench Verified and BrowseComp. The model demonstrates strong architectural thinking, decomposing complex problems before generating code across more than ten programming languages. M2.5 operates at high throughput speeds of up to 100 tokens per second, enabling faster completion of multi-step tasks. It is optimized for efficient reasoning, reducing token usage and execution time compared to previous versions. With dramatically lower pricing than competing frontier models, it delivers powerful performance at minimal cost. Integrated into MiniMax Agent, M2.5 supports professional-grade office workflows, financial modeling, and autonomous task execution.

MiniMax M2.7 is an advanced AI model designed to enhance real-world productivity across coding, search, and office workflows. It is trained with reinforcement learning across numerous real-world environments, enabling it to handle complex, multi-step tasks effectively. The model excels in problem-solving by breaking down challenges before generating solutions across multiple programming languages. It delivers high-speed performance with rapid token generation, allowing tasks to be completed efficiently. With optimized reasoning and cost-effective pricing, it provides powerful capabilities while minimizing resource usage. It also achieves strong performance in software engineering benchmarks, reducing incident response time and improving development efficiency. Additionally, it supports advanced agentic workflows and professional-grade office tasks, making it highly versatile for modern work environments.

The next generation of our open source large language model. This release includes model weights and starting code for pretrained and fine-tuned Llama language models — ranging from 7B to 70B parameters. Llama 2 pretrained models are trained on 2 trillion tokens, and have double the context length than Llama 1. Its fine-tuned models have been trained on over 1 million human annotations. Llama 2 outperforms other open source language models on many external benchmarks, including reasoning, coding, proficiency, and knowledge tests. Llama 2 was pretrained on publicly available online data sources. The fine-tuned model, Llama-2-chat, leverages publicly available instruction datasets and over 1 million human annotations. We have a broad range of supporters around the world who believe in our open approach to today’s AI — companies that have given early feedback and are excited to build with Llama 2.

Assembly brings your entire development context into focus, starting each day with clarity. It is designed to revolutionize software development by integrating understanding, planning, coding, reviewing, and documentation into a cohesive system. Serving as the command center for development teams, Factory offers personalized dashboards that highlight relevant tasks and streamline workflows, ensuring clarity and efficiency from the start of each day. The platform facilitates collaborative design and planning, allowing teams to craft architectures, draft requirements, and outline technical roadmaps with ease. Its codebase Q&A feature accelerates onboarding and knowledge sharing by capturing context and decisions, simplifying the comprehension of complex systems. Factory's AI-driven code review system delves deep into codebases, identifying subtle issues and assisting in implementing feedback effectively.

Inworld TTS is a state-of-the-art text-to-speech platform designed to deliver ultra-realistic, context-aware speech synthesis and precise voice-cloning capabilities at a radically accessible price. The flagship model, TTS-1, is optimized for real-time applications and supports low-latency streaming (first audio chunk in ≈200 ms) as well as multiple languages (including English, Spanish, French, Korean, Chinese, and more). Developers can use instant zero-shot voice cloning (5-15 seconds of audio) or professional fine-tuned cloning, add voice-tags for emotion, style, and non-verbal sounds, and switch languages while preserving voice identity. The larger TTS-1-Max model (in preview) offers even more expressive speech and multilingual strength. The platform supports both API and portal access, streaming or batch mode, and is designed for everything from interactive voice agents and gaming characters to branded audio experiences.

Outspeed provides networking and inference infrastructure to build fast, real-time voice and video AI apps. AI-powered speech recognition, natural language processing, and text-to-speech for intelligent voice assistants, automated transcription, and voice-controlled systems. Create interactive digital characters for virtual hosts, AI tutors, or customer service. Enable real-time animation and natural conversations for engaging digital interactions. Real-time visual AI for quality control, surveillance, touchless interactions, and medical imaging analysis. Process and analyze video streams and images with high speed and accuracy. AI-driven content generation for creating vast, detailed digital worlds efficiently. Ideal for game environments, architectural visualizations, and virtual reality experiences. Create custom multimodal AI solutions with Adapt's flexible SDK and infrastructure. Combine AI models, data sources, and interaction modes for innovative applications.

FireWorks is a complete solution with built in workflow, enabling you to manage all the needs of your department. FireWorks is a complete software solution for Fire Stations and EMS, it includes a built in workflow, enabling you to manage all the needs of your department. Our integrated Pre-Plan and Inspection system ties together both essential functions of a Fire Rescue Department: Suppression + Prevention. Crews can conduct pre-plan surveys while the Fire inspectors conduct their periodic inspections. Critical data such as emergency contact information, knox box locations, FACP locations, etc as well as last known inspection violations are accessible from a mobile device. Data that is updated during the Prevention activity of inspection and Suppression pre-plan activity is updated instantly and available to all users of the system. FireWorks the most innovative public safety solution available on the market today.