Meta introduced at the moment a partnership with Cerebras Programs to energy its new Llama API, providing builders entry to inference speeds as much as 18 occasions sooner than conventional GPU-based options.
The announcement, made at Meta’s inaugural LlamaCon developer convention in Menlo Park, positions the corporate to compete instantly with OpenAI, Anthropic, and Google within the quickly rising AI inference service market, the place builders buy tokens by the billions to energy their purposes.
“Meta has selected Cerebras to collaborate to deliver the ultra-fast inference that they need to serve developers through their new Llama API,” mentioned Julie Shin Choi, chief advertising and marketing officer at Cerebras, throughout a press briefing. “We at Cerebras are really, really excited to announce our first CSP hyperscaler partnership to deliver ultra-fast inference to all developers.”
The partnership marks Meta’s formal entry into the enterprise of promoting AI computation, reworking its in style open-source Llama fashions right into a industrial service. Whereas Meta’s Llama fashions have accrued over one billion downloads, till now the corporate had not supplied a first-party cloud infrastructure for builders to construct purposes with them.
“This is very exciting, even without talking about Cerebras specifically,” mentioned James Wang, a senior government at Cerebras. “OpenAI, Anthropic, Google — they’ve built an entire new AI business from scratch, which is the AI inference business. Developers who are building AI apps will buy tokens by the millions, by the billions sometimes. And these are just like the new compute instructions that people need to build AI applications.”
A benchmark chart exhibits Cerebras processing Llama 4 at 2,648 tokens per second, dramatically outpacing opponents SambaNova (747), Groq (600) and GPU-based companies from Google and others — explaining Meta’s {hardware} alternative for its new API. (Credit score: Cerebras)
Breaking the pace barrier: How Cerebras supercharges Llama fashions
What units Meta’s providing aside is the dramatic pace enhance supplied by Cerebras’ specialised AI chips. The Cerebras system delivers over 2,600 tokens per second for Llama 4 Scout, in comparison with roughly 130 tokens per second for ChatGPT and round 25 tokens per second for DeepSeek, in line with benchmarks from Synthetic Evaluation.
“If you just compare on API-to-API basis, Gemini and GPT, they’re all great models, but they all run at GPU speeds, which is roughly about 100 tokens per second,” Wang defined. “And 100 tokens per second is okay for chat, but it’s very slow for reasoning. It’s very slow for agents. And people are struggling with that today.”
This pace benefit permits totally new classes of purposes that have been beforehand impractical, together with real-time brokers, conversational low-latency voice programs, interactive code technology, and on the spot multi-step reasoning — all of which require chaining a number of massive language mannequin calls that may now be accomplished in seconds quite than minutes.
The Llama API represents a major shift in Meta’s AI technique, transitioning from primarily being a mannequin supplier to turning into a full-service AI infrastructure firm. By providing an API service, Meta is making a income stream from its AI investments whereas sustaining its dedication to open fashions.
“Meta is now in the business of selling tokens, and it’s great for the American kind of AI ecosystem,” Wang famous in the course of the press convention. “They bring a lot to the table.”
The API will supply instruments for fine-tuning and analysis, beginning with Llama 3.3 8B mannequin, permitting builders to generate knowledge, prepare on it, and take a look at the standard of their customized fashions. Meta emphasizes that it received’t use buyer knowledge to coach its personal fashions, and fashions constructed utilizing the Llama API will be transferred to different hosts—a transparent differentiation from some opponents’ extra closed approaches.
Cerebras will energy Meta’s new service by way of its community of knowledge facilities situated all through North America, together with amenities in Dallas, Oklahoma, Minnesota, Montreal, and California.
“All of our data centers that serve inference are in North America at this time,” Choi defined. “We will be serving Meta with the full capacity of Cerebras. The workload will be balanced across all of these different data centers.”
The enterprise association follows what Choi described as “the classic compute provider to a hyperscaler” mannequin, much like how Nvidia offers {hardware} to main cloud suppliers. “They are reserving blocks of our compute that they can serve their developer population,” she mentioned.
Past Cerebras, Meta has additionally introduced a partnership with Groq to supply quick inference choices, giving builders a number of high-performance alternate options past conventional GPU-based inference.
Meta’s entry into the inference API market with superior efficiency metrics might probably disrupt the established order dominated by OpenAI, Google, and Anthropic. By combining the recognition of its open-source fashions with dramatically sooner inference capabilities, Meta is positioning itself as a formidable competitor within the industrial AI area.
“Meta is in a unique position with 3 billion users, hyper-scale datacenters, and a huge developer ecosystem,” in line with Cerebras’ presentation supplies. The mixing of Cerebras expertise “helps Meta leapfrog OpenAI and Google in performance by approximately 20x.”
For Cerebras, this partnership represents a significant milestone and validation of its specialised AI {hardware} method. “We have been building this wafer-scale engine for years, and we always knew that the technology’s first rate, but ultimately it has to end up as part of someone else’s hyperscale cloud. That was the final target from a commercial strategy perspective, and we have finally reached that milestone,” Wang mentioned.
The Llama API is presently obtainable as a restricted preview, with Meta planning a broader rollout within the coming weeks and months. Builders involved in accessing the ultra-fast Llama 4 inference can request early entry by deciding on Cerebras from the mannequin choices inside the Llama API.
“If you imagine a developer who doesn’t know anything about Cerebras because we’re a relatively small company, they can just click two buttons on Meta’s standard software SDK, generate an API key, select the Cerebras flag, and then all of a sudden, their tokens are being processed on a giant wafer-scale engine,” Wang defined. “That kind of having us be on the back end of Meta’s whole developer ecosystem is just tremendous for us.”
Meta’s alternative of specialised silicon alerts one thing profound: within the subsequent section of AI, it’s not simply what your fashions know, however how rapidly they will suppose it. In that future, pace isn’t only a function—it’s the entire level.
Day by day insights on enterprise use circumstances with VB Day by day
If you wish to impress your boss, VB Day by day has you coated. We provide the inside scoop on what firms are doing with generative AI, from regulatory shifts to sensible deployments, so you may share insights for max ROI.
An error occured.
