Fireworks AI (Pay-As-You-Go)

We use Fireworks AI as a powerful tool that helps us in building and scaling our customized AI application model for our business.

We wanted to create a customer base where our customers could interact with us through our chatbot, and Fireworks AI helped us in scaling through that by customizing the AI application model for our business to suit our customer's taste.

Fireworks AI helped us customize the application for our customers by creating strong platform leverage in the ecosystem around it, and that's what we leveraged by it providing us multiple model tiers, which we use in creating that customized AI application for our teams.

Fireworks AI has a very fast inference speed by providing minimal delay for our real-time applications.

The best feature Fireworks AI offers is the multiple model tiers; it has very vast model applications where it's more about grasping the infrastructure component quickly, and I think it helps our team balance quality and cost.

Having access to multiple model tiers helps our team balance quality and cost by giving us leverage where we can make options and look at what best suits our company and what we could use, which is beneficial because when you have multiple choices, you can tailor your approach and get what you actually need, so our options are not limited.

Fireworks AI has impacted us positively as it helps in offering us access to the open-source models by advancing fine-tuning options, a massive library where we can get information from the database that we can use in line with our company policy.

Fireworks AI helped us reduce costs, and it helps our team balance quality and improve customer satisfaction because interacting with us at that moment could provide them with easier access and quick answers and responses.

The only challenge is that Fireworks AI is not a ready-made business application; you have to customize it to suit your organization's taste, and it lacks a user-friendly dashboard, making it very difficult to grasp. You need to be very detailed to understand how the system works, so I think it could be improved in this aspect.

There is always room for improvement, and that's my fair view and overall scaling for them; as much as it has a fast inference speed, the platform could become more user-friendly. Making it more user-friendly is probably why I chose eight out of ten as my rating.

We have been using Fireworks AI for at least two years now.

Fireworks AI is very much stable.

The scalability of Fireworks AI is satisfactory to us.

Customer support for Fireworks AI is very friendly, active, and responsive.

We were using Groq before we switched to Fireworks AI.

My experience with pricing, setup cost, and licensing was a bit difficult, but the pricing was cost-effective for us, so we were able to get it done. I think it is renewable every year, so that's not a challenge for us.

There is a return on investment as Fireworks AI's accuracy helps us with our turnaround time, and I think that's a return on investment for us. It saves us cost as well.

Before choosing Fireworks AI, we evaluated other options, including Claude and Groq AI, but then we had to look at the options available to us, considering the cost-effectiveness and the license model.

I advise others looking into using Fireworks AI to use it because the ecosystem around Fireworks creates strong platform leverage and provides multiple model tiers that can let their team balance quality and cost.

Regarding Fireworks AI's AI capabilities, its governance and security policy is deeply rooted, following global standards, and I think that's a fair offering from them.

Regarding Fireworks AI's AI capabilities and the reliability of the output, this has not posed any challenge for us. It's good and satisfactory. I rated this review eight out of ten overall.

My main use case for Fireworks AI is typically for fine-tuning or choosing what models I want to use for my project. It is good for letting me use all the models, and it acts as a playground so I can even test them.

Recently, I used Fireworks AI to choose between models for a project. It was an assignment for one of the YC startups, and I wanted to see which model I should use for the audio transcript. I tested all of them using Fireworks AI, and I ended up choosing GPT 120B because of the help of Fireworks AI.

About my main use case for Fireworks AI, it is interesting that it lets me choose. There are so many models available. I think there were 300-plus models, which is really impressive.

The best features Fireworks AI offers are that the fine-tuning is really flexible and suitable. The customization is really good. I think it is providing so many models, which is the best part, and I do not need any GPU setup for using them. The number of models, which is very high, makes it very good.

The customization options in Fireworks AI are very good. I can adjust temperature there, or I can set a token limit there. That all helps me to customize my AI model and how I can use it better. That is really good.

Regarding the features of Fireworks AI, the integration in the back end and all is really good. Since I use it in my organization, the integration is pretty smooth.

Fireworks AI has positively impacted my organization by helping my productivity go up. It has saved me time. It has helped me to achieve more deadlines faster.

One of the things that could improve Fireworks AI is the cost, which I think is really expensive. It is very much more expensive than Groq, which I generally use. Also, there is no free tier, which is another issue. I only got around five to six credits when I signed up. A free tier would be advisable. Additionally, I think the number of models that were available for image generation and video was very less, which can be improved.

I would add that the image-video generation of Fireworks AI is pretty weak. As I have already mentioned, it supports fewer image models. I do not remember exactly, but it is very less compared to others. I think it has zero video generation capabilities, making it really hard for someone wanting to make a visual AI project. In my organization, I had to do one where I had to use image generation and its processing, and I could not use any model here. Additionally, it does not support the full ML cycle, such as data preparation and feature engineering. I cannot do it here and would need a separate tool or app for that.

I have been using Fireworks AI for one month, and it is pretty good.

Fireworks AI's scalability is good, but it might be slow sometimes, which could be an issue.

It was pretty easy to integrate Fireworks AI with my existing systems and workflows.

Fireworks AI has saved my team around half of what we used to take because initially, we had to manually research all the models. Now, we can just use it, which saves the time of searching and using each one and then deciding which one to go with.

My advice for others looking into using Fireworks AI is that if they are initially trying an AI model, I think it is a good option, but they can do more research and be better at security and all the other things we discussed. They have a huge library of all the open-source models. As I have already said, their fine-tuning features are very good. It is really good for a developer, but it is not that good for a businessman or someone who is non-technical.

Before we wrap up, I think Fireworks AI should have good build and integration so that a developer does not have to do a setup. I think it is similar to tools such as Zendesk.

I think Fireworks AI handles security and data privacy in my organization pretty well, but security can be a concern. It does have unusual traffic patterns, and it would be better if the vulnerabilities are properly monitored.

The performance of Fireworks AI in terms of speed and reliability was good. It is pretty reliable, and it makes me work faster.

My overall rating for this product is an eight out of ten.

Fireworks AI was my choice because, with keywords like low latency, enterprise automation, and corporate automation, it was able to provide expert-level insights. I built a system for memory, autonomous collaboration, and controlled generation in the projects where I applied Fireworks AI. After introducing Fireworks AI's high-speed inference engine, I found that communication speed between agents became about twice as fast compared to before. The function calling capability for agents to invoke external tools was very stable, and I confirmed that it was possible to perfectly implement complex workflows that query and reflect enterprise data in real time. This was the most decisive differentiator that allowed us to practically apply AI automation in enterprise environments.

A concrete example of how Fireworks AI helped would be a system with an access control system. By developing an agent, we built a system where, when people enter a factory inside a company, we receive their medical examination documents and, based on the information in those documents, we can determine whether to approve or deny their access registration or entry. By automating that, we quickly verify employees' health conditions and can impose entry restrictions.

The most satisfying feature of Fireworks AI was the combination of efficient inference speed and stable function calling. The core of an autonomous agent system is the model's ability to interact with external tools in real time. Fireworks AI is not just fast in plain text generation; it is innovative in that it reduces the latency that occurs in the process where agents perform complex tasks and, through that, choose and call tools.

Current LLM models have evolved from traditional foundation models into hybrid models, and while inference speed has improved, response time has become slower because they use things like Chain-of-Thought (CoT). To gain that inference speed, optimization of external function calling and similar aspects must be perfect; otherwise, the final answer will not come out quickly. By optimizing that through Fireworks, we were able to speed up the response time, which is a weakness of existing LLM models. A major advantage is that customers or business users can obtain answers quickly through text.

In terms of metrics, in the case of health checkup data, it is at least two to three pages of PDF files or scans, so when a human reads it, it takes at least about one to three minutes. Using LLMs and Fireworks, we built an integrated system that can make a determination in about thirty seconds to one minute and then pass that result on to other systems based on that.

In the current function calling, if Fireworks AI could be added as part of our RAG system not only with the function calling we are using now but also with a variety of other connections, then an even better situation would be possible. Fireworks is based on tool calling, so it needs to add more different kinds of connections to enable faster data retention and optimization.

Although multiple optimal optimization or measurement methodologies for using LLMs are being discussed, when using them inside enterprises, the main thing is actually measuring work handling capability or work processing speed. Based on that, and also through what might be called interviews with business-side staff, we measured the speed improvements in a somewhat indirect manner.

I have been using Fireworks AI for about two years.

The companies we usually work with are enterprise-level companies in Korea, so we cannot really provide actual company names or detailed data. However, in order to make decisions, when customers have certain requirements, we can quickly create agents for them, and in connecting those agents through connections like A2A and MCP, Fireworks has helped a lot. As a result, we experienced an innovative situation where time spent on simple repetitive tasks was reduced by over sixty percent. Additionally, task processing speed improved by about thirty percent. This naturally led to cost reduction or cost optimization. To be specific, if one person used to complete one unit of work before, it is now optimized so that they can do one point five or more units of work.

Based on my experience, I give Fireworks AI a rating of seven out of ten. Due to the fact that various connections are still somewhat lacking, I deducted about three points for this rating. Since we are basically a CSP partner, we use a public cloud as our base. However, depending on customer needs, enterprise-level customers want to apply it via their own in-house LLM or local LLM, so the hybrid concept is also under consideration. Our company fundamentally aims for a multi-cloud approach, so we use GCP, AWS, and Azure all together. Currently, I am mainly focused on the Azure side, so we deal only with Azure-based systems.

My main use case for Fireworks AI is to build a chatbot and recommendation engine to recommend products to users of my application. Since I work in a QSR-based domain, I want to give recommendations such as showing potato fries as an option if a burger is added to the cart, which is the type of automation I want to achieve with Fireworks AI.

I envision the chatbot working for my users by handling common queries and focusing on product suggestions. As a core technical person, I explore everything about AI products, and I am currently using Fireworks AI to understand what we can achieve with our chatbot for queries such as 'Where is my order?' or 'Give me the list of products under happy hour offers.'

I am focusing on the chatbot and recommendation engine, which are the major use cases I am exploring, including other AI options, not only Fireworks AI.

Based on my exploration so far, I find that Fireworks AI offers a platform where I can run and build my own AI models, which I consider to be the best feature. Fireworks AI has positively impacted my organization by fulfilling my use cases to some extent, and I definitely want to explore more as it is close to addressing my needs.

When exploring the flexibility or ease of use of Fireworks AI, I find that it is too early to say, but I can say that it is easy to understand and integrates easily by following the given steps.

Based on my exploration so far, I find that it is too early to judge any improvements or negative aspects of Fireworks AI, as I am still in the exploration phase.

I have been using Fireworks AI for a few days in the exploration phase only, and I have not implemented it yet.

Fireworks AI is stable from what I have seen so far, and based on my exploration, it is stable.

Regarding scalability, Fireworks AI is showing itself as a stable product based on my exploration.

I have not had the chance to contact or connect with Fireworks AI customer support.

My advice for others looking into using Fireworks AI is that if you have a use case where you need to build or run your pre-existing model or a model provided by Fireworks AI, then you should go with it. You can build your own chatbot and provide a personalized experience. For example, in the entertainment industry, similar to a Jio application, I can recommend videos as per user preferences, such as suggesting cartoon videos for children based on their age while ensuring the content is informative for both parents and children.

I rate Fireworks AI an eight out of ten based on my exploration. I chose eight out of ten because I explored it for the chatbot and recommendation engine, which align with my use case, and this rating may change in the future.

We primarily use Fireworks AI for text-to-image generation. We are developing a platform for artists to sell their art styles, where the system helps them tune a model and then sell images generated from their signature.

Fireworks AI has helped our organization by enabling us to create a platform for artists to sell their art styles. I am not the user of the solution. I'm the developer. It helps me do my job effectively.

Fireworks AI has a solid API and is quite easy to interact with. It has better documentation and logs, which are important for me as a developer. Additionally, it has a bigger infrastructure and provides nice support for fine-tuning the Flux AI model.

Returning the values charged for each event generation would improve Fireworks AI. When using the API, it does not return information about the charges for image generation, which would be useful for our solution.

I have been using Fireworks AI for about four months.

Fireworks AI is pretty stable, and I have not encountered any problems.

Fireworks AI offers a very complete API, and its scalability is impressive.

I previously used Okta. It was discontinued, so we opted for Fireworks AI.

The initial setup was fairly easy. It took about eight to ten days, including integrating it into our solution, testing, and moving from scratch to production.

I cannot comment on pricing or setup cost since others handle that aspect. As a developer, I primarily use the API.

I have evaluated SAL as an alternative solution.

I'd rate the solution ten out of ten.