OpenAI, Anthropic cut AI model costs as price-performance race intensifies

Enterprises can now buy frontier AI for far less per token after OpenAI and Anthropic cut prices on their newest models on Tuesday.

OpenAI released GPT-6 Sol and GPT-6 Luna with per-token costs half those of their GPT-5.6 predecessors.

“These models help distribute the benefits of that intelligence by advancing the frontier on cost efficiency,” OpenAI said in a blog post about the launch. “Improvements in caching and inference let us serve these models at lower cost, and we’re passing those savings directly on… by reducing API prices for Sol and Luna by 50%,” it said.

Anthropic, meanwhile, launched Claude Opus 5.5 with token prices 20% below those of Opus 5, and claimed that this, with the model’s lower compute requirements and reduced token usage, meant additional savings for enterprises: “It performs at the level of Claude Fable 5.1 on most work and costs 40% less to run than Opus 5,” the company announced on Opus 5.5’s web page.

Focus shifts to cost-performance

Rather than touting raw performance, as they did with the launch of their flagship models GPT 6 Astra and Claude Fable 5.1, the companies emphasized the value for money of their new models.

But analysts say the moves are about more than the lower prices.

AI vendors are increasingly competing on efficiency, said Forrester VP and principal analyst Charlie Dai.

“Frontier AI is entering a prolonged price-performance race driven primarily by inference efficiency gains, better caching, and model optimization, and it’s also intensified by competitive pressure as capabilities converge,” Dai said.

Providers are lowering costs to “expand enterprise adoption and stimulate higher-volume production usage.”

The economics of on-premises AI in question

Lower API costs improve the economics of consuming AI via cloud platforms, particularly for workloads such as coding agents and enterprise automation.

However, there’s still a case for private or hybrid deployments, Dai said, citing data sovereignty, security, and intellectual property requirements.

“Lower inference costs improve the economics of API consumption, but they do not eliminate demand for private and hybrid AI,” he said; enterprises are maintaining “optionality through hybrid architectures and selective infrastructure ownership.”

Sanchit Vir Gogia, chief analyst at Greyhound Research, said that as usage-based costs decline, organizations evaluating on-premises deployments need to assess utilization levels, data requirements, and operational constraints.

He sees more price cuts to come. “This is sustained price compression, and calling it a conventional price war misses the point. It is a land grab for the default route through which enterprises buy intelligence,” Gogia said.

Evaluating cost beyond tokens

While vendors highlight lower token pricing and benchmark-driven cost metrics, analysts said enterprises need to assess broader measures.

“CIOs should evaluate cost per business outcome, not cost per token,” Dai said, pointing to factors such as reliability, latency, and task completion rates.

Gogia said pricing needs to be evaluated against successful outcomes rather than attempts. “The only defensible measure is total cost per accepted, policy-compliant outcome,” he said.

Both analysts said enterprises should validate vendor claims using their own workloads rather than relying on benchmark comparisons.

The pricing changes are also affecting the broader AI ecosystem, including hyperscalers and infrastructure providers, they said.

Hyperscalers may need to shift toward higher-value services such as orchestration, governance, and AI platforms as pricing pressure increases on raw compute, Dai said.

Gogia added that the changes point to “margin migration rather than margin collapse,” with lower revenue per token offset in part by lower serving costs and higher demand.

The latest releases also reflect increasing competition among frontier model providers.

Anushree Verma, senior director analyst at Gartner, said enterprises are beginning to view general-purpose models as interchangeable.

“Models are increasingly becoming commoditized,” Verma said, adding that providers are “aggressively trying to grab market share,” often supported by hyperscale infrastructure and capital. This is contributing to direct price competition and a “race to the bottom” for standard inference, she said.

For enterprises, the changes introduce both opportunities and trade-offs, as lower pricing expands access to AI while increasing the need to evaluate performance, cost, and deployment options across providers.

This article first appeared on InfoWorld.