Fireworks

““Working with RADPAIR— and through their partnership with Fireworks — has been key to pushing this forward. Now, radiologists can dictate naturally and have AI keep up in real time, which is a major leap forward,””

““The intelligence core is super important, but the gap from that core to delivering value is where the hard problem is. Talk to more users, think about product experience, do the data integrations with your customers. Offload model inference to a trustworthy provider. That’s a much better choice than managing your own hosted models, and it’s not a good use of your time when you’re building a startup.””

““We are investing in model training, fine-tuning and RL. We have the internal talent and capability to do that work, and we plan to collaborate with Fireworks on compute and training frameworks.””

““For our customers in the science community, the model-agnostic strategy is a super important factor. They don’t want model lock-in, and they want to make sure they can use state-of-the-art models.””

““We feel like Fireworks is part of our internal team, especially part of our engineering team. This inference service is very critical to our product experience, so having a trustworthy partner on both the business side and the engineering side was a huge factor in the decision.””

““We started using more proprietary models in the beginning. We wanted to bring Biomni Lab to as many scientists as we could at the same frontier quality while driving cost efficiencies. At the same time, our users really want the flexibility of choosing models. There are so many good open source models out there, so we wanted to give users that control.””

“On Fireworks, combining open-source worker models with frontier tool use and post-training closes much of the gap to frontier performance on Legal Agent Benchmark, while improving cost efficiency and system controllability.”

“We’re not just building for today’s use cases. Fireworks helps us stay ahead by enabling fast iteration, reliable scaling, and the flexibility to adapt as AI agents evolve.”

“That improvement is a game changer for delivering reliable, enterprise-scale AI powered by Fireworks.”

“By partnering with Fireworks to fine-tune models, we reduced latency from about 2 seconds to 350 milliseconds , significantly improving performance and enabling us to launch AI features at scale,”

“By fine-tuning models, we reduced latency from about 2 seconds to 350 milliseconds, significantly improving performance and enabling us to launch AI features at scale,”

“We’re spending a ton of time around the unit economics of multi-agent systems. Fireworks has given us the flexibility to update, improve, and evolve our pricing models for our customers as new agentic capabilities come to market.”

“Fireworks won simply because it worked consistently. Whenever we deploy any model, it works the first time. No tuning, no fiddling. That mattered to us, because we change models all the time. What I don’t want is to get stuck in a 3-week development cycle trying to make a model work.”

“Most clinical AI sits on a closed model behind someone else’s API. We post-trained a 550B open model on synthetic data, with a reward that treats clinical safety and faithfulness as hard gates, and it now beats the frontier model in live clinician comparisons. Owning the weights means we can pin a version, inspect every change and run the same checkpoint on-premises. Fireworks and NVIDIA made that possible for a team of twelve.”

“The biggest benefit has been reliability. We tried other providers, but we’ve seen Fireworks lead in this sense, as well as respond to our requests and queries very fast.”

“The aha moment was when we were deciding whether to roll out GLM-5.2 as one of our recommended model options. We felt Fireworks gave us the confidence to do this without reliability concerns. We have a main agent that has access to all of our data that everyone across the company interacts with and asks questions. When we moved this agent from Opus 4.8 to GLM-5.2, nobody noticed a difference in the experience. The outputs were consistent with what we expected, which gave us the confidence to make GLM-5.2 a recommended model option.”

“We are excited to be partnering with Fireworks to deploy our Deep Research Agents using Fireworks. Outstanding work! We’ve achieved fantastic results with the post-training on Kimi-K2. We conducted a series of systematic benchmarks for the deep_research task, and the conclusions are really positive. It performed comparably to SOTA closed source models in detailed human evaluations. It uses tools more frequently and skillfully, which we are excited to see.”

“We are really excited to see what we were able to achieve partnering with Fireworks. Fireworks enabled us to own our AI journey, and unlock better quality in just four weeks. This resulted in a better user experience for our customers.”

““Open-weight models are going to be the main way engineering teams keep automating more while managing cost in a sustainable way. Fireworks is what enables us to deliver on that mission.””

““The choice of all the models has been one of the key differentiators helping Factory gain rapid adoption among enterprises. We’ve had almost 2x month-over-month growth for the last several months, and that speaks to how much having the choice of models really matters.””

““Fireworks supports us by having these models available on basically day zero, typically well ahead of most other inference providers.””

““We have finite engineers like everybody else. We would prefer to have engineers make training more efficient and more precise rather than spin up an inference effort.””

“Being able to serve the best models with cutting-edge latency provides us with an enormous competitive advantage”

“Fireworks’ Multi-LoRA capabilities align with Cresta’s strategy to deploy custom AI through fine-tuning cutting-edge base models. It helps unleash the potential of AI on private enterprise data.”

“We have received tremendous support from the amazing Fireworks team. From troubleshooting and quick incident responses to insightful explanations of metrics, their engagement has been exceptional. The low-latency, high-throughput serving of LLMs has been particularly valuable, as latency is crucial for our real-time applications.”