For years, SaaS companies cruised on easy per-seat pricing and almost-free scaling. Enter AI: every query burns power, every model costs cash, and suddenly startups are in a pricing puzzle.
In his talk Pricing for AI Agents at the How to Web Conference 2025 in Bucharest, Emanuel Martonca (Founder, Pricing Strategist at Soft Fight) dives into why traditional SaaS pricing no longer works – and what it takes to build sustainable business models in the AI era.
Emanuel opens his talk with a simple story:
Imagine you’re an angel investor having lunch with a founder who’s built an AI platform that helps large companies map their employees’ skills.
The founder explains that the tool lets sales teams quickly find experts in niche technologies across the organization, making it easier to sell IT services.
In a company of 10.000 people, sales representatives are often far removed from the engineers doing the actual work. So, when a client in New York asks about a specific technology, the salesperson might have no idea whether anyone in the company has that expertise – or even where to find them.
The founder claims his AI solves this problem in days, not months, and points out the lucrative potential. After all, some companies currently pay almost $400.000 annually for software solving the same problem.
However, Emanuel warns – there are couple of critical considerations when thinking about AI pricing.
AI is fundamentally different from traditional SaaS, explains Martonca. While SaaS benefits from near-zero marginal costs for additional users and high gross margins, AI is computationally expensive:
A single AI query can consume ten times more energy than a Google search. Such costs must be considered in pricing, along with other factors like marketing, positioning, differentiation, and risk
Unlike SaaS, where the main concern might be looking like a glorified spreadsheet, AI introduces far more complex risks.
Traditional SaaS frameworks and mental models don’t translate to AI startups – they require a different approach. In particular, common SaaS seat-based subscription models often fail in the AI context.
As Martonca highlights, AI frequently replaces the very people you might charge for, making seat-based pricing impractical.
Moreover, many AI projects, proofs of concept, pilots, or experiments never reach production:
Every AI pilot that doesn’t go to production represents lost revenue for software vendors, and AI accelerates development, reducing the need for large teams – further impacting legacy software revenues.
Currently, there is no standard model for AI pricing.
Unlike SaaS, where “good-better-best” packages and per-seat subscriptions were well-established, AI pricing is complex and still experimental:
You can price by input, output, outcome, or performance. The choice depends heavily on the problem being solved and the client’s perceived value, rather than purely on technological complexity.
Many founders get caught up in explaining how their AI works so they talk about the models, the architecture, the agents, but clients care most about solving a business problem.
A central lesson is to price the problem, not the technology, Emanuel points out.
In the skills-matching example, instead of charging for the software or the AI engine, the vendor could charge for each successful match of employee to project. This approach shifts risk to the vendor, but aligns price with the value delivered to the client.
Emanuel also highlights the blurring line between products and services in AI. Traditionally, companies were either product-focused or service-focused. AI challenges this distinction.
OpenAI, for example, sells consulting services alongside its technology platform. Delivering outcomes and real business results has become the primary source of value, not just providing access to software.
AI budgets also differ from traditional IT budgets:
SaaS historically took money from IT departments. AI often taps into HR or services budgets, which are significantly larger.
For both startups and established companies, Emanuel’s advice is clear: start with the customer and the problem they need solved. Identify what they value and what they’re willing to pay for – only then design a solution and assess its economic viability.
Most AI vendors currently use a hybrid model: a flat base price for platform access, some included usage, and additional charges based on usage or tokens. It’s a pragmatic – if temporary – solution in an environment full of unknowns. Yet the fundamental principles of pricing still apply:
Understand the value delivered, choose the right metric for your model, and price according to the problem solved, not just the technology deployed.
This is important beacuse getting pricing wrong can be fatal. Companies that adapt their models to reflect value and outcomes, rather than legacy SaaS logic, will be best positioned to succeed in this new era.
