Right now, we’re excited to announce two main enhancements to mannequin fine-tuning in Azure AI Foundry—Reinforcement High quality-Tuning (RFT) with o4-mini, coming quickly, and Supervised High quality-Tuning (SFT) for the 4.1-nano mannequin, accessible now.
Right now, we’re excited to announce three main enhancements to mannequin fine-tuning in Azure AI Foundry—Reinforcement High quality-Tuning (RFT) with o4-mini (coming quickly), Supervised High quality-Tuning (SFT) for the GPT-4.1-nano and Llama 4 Scout mannequin (accessible now). These updates replicate our continued dedication to empowering organizations with instruments to construct extremely personalized, domain-adapted AI techniques for real-world affect.
With these new fashions, we’re unblocking two main avenues of LLM customization: GPT-4.1-nano is a robust small mannequin, excellent for distillation, whereas o4-mini is the primary reasoning mannequin you’ll be able to fine-tune, and Llama 4 Scout is a best-in-class open supply mannequin.
Reinforcement High quality-Tuning with o4-mini
Reinforcement High quality-Tuning introduces a brand new degree of management for aligning mannequin conduct with complicated enterprise logic. By rewarding correct reasoning and penalizing undesirable outputs, RFT improves mannequin decision-making in dynamic or high-stakes environments.
Coming quickly for the o4-mini mannequin, RFT unlocks new prospects to be used instances requiring adaptive reasoning, contextual consciousness, and domain-specific logic—all whereas sustaining quick inference efficiency.
Actual world affect: DraftWise
DraftWise, a authorized tech startup, used reinforcement fine-tuning (RFT) in Azure AI Foundry Fashions to boost the efficiency of reasoning fashions tailor-made for contract technology and overview. Confronted with the problem of delivering extremely contextual, legally sound recommendations to legal professionals, DraftWise fine-tuned Azure OpenAI fashions utilizing proprietary authorized knowledge to enhance response accuracy and adapt to nuanced person prompts. This led to a 30% enchancment in search outcome high quality, enabling legal professionals to draft contracts sooner and concentrate on high-value advisory work.
Reinforcement fine-tuning on reasoning fashions is a possible sport changer for us. It’s serving to our fashions perceive the nuance of authorized language and reply extra intelligently to complicated drafting directions, which guarantees to make our product considerably extra helpful to legal professionals in actual time.
—James Ding, founder and CEO of DraftWise.
When do you have to use Reinforcement High quality-Tuning?
Reinforcement High quality-Tuning is finest fitted to use instances the place adaptability, iterative studying, and domain-specific conduct are important. You must take into account RFT in case your state of affairs entails:
- Customized Rule Implementation: RFT thrives in environments the place choice logic is very particular to your group and can’t be simply captured via static prompts or conventional coaching knowledge. It allows fashions to study versatile, evolving guidelines that replicate real-world complexity.
- Area-Particular Operational Requirements: Ideally suited for situations the place inner procedures diverge from business norms—and the place success relies on adhering to these bespoke requirements. RFT can successfully encode procedural variations, comparable to prolonged timelines or modified compliance thresholds, into the mannequin’s conduct.
- Excessive Determination-Making Complexity: RFT excels in domains with layered logic and variable-rich choice bushes. When outcomes depend upon navigating quite a few subcases or dynamically weighing a number of inputs, RFT helps fashions generalize throughout complexity and ship extra constant, correct selections.
Instance: Wealth advisory at Contoso Wellness
To showcase the potential of RFT, take into account Contoso Wellness, a fictitious wealth advisory agency. Utilizing RFT, the o4-mini mannequin discovered to adapt to distinctive enterprise guidelines, comparable to figuring out optimum consumer interactions primarily based on nuanced patterns just like the ratio of a consumer’s web price to accessible funds. This enabled Contoso to streamline their onboarding processes and make extra knowledgeable selections sooner.
Supervised High quality-Tuning now accessible for GPT-4.1-nano
We’re additionally bringing Supervised High quality-Tuning (SFT) to the GPT-4.1-nano mannequin—a small however highly effective basis mannequin optimized for high-throughput, cost-sensitive workloads. With SFT, you’ll be able to instill your mannequin with company-specific tone, terminology, workflows, and structured outputs—all tailor-made to your area. This mannequin might be accessible for fine-tuning within the coming days.
Why High quality-tune GPT-4.1-nano?
- Precision at Scale: Tailor the mannequin’s responses whereas sustaining pace and effectivity.
- Enterprise-Grade Output: Guarantee alignment with enterprise processes and tone-of-voice.
- Light-weight and Deployable: Good for situations the place latency and price matter—comparable to customer support bots, on-device processing, or high-volume doc parsing.
In comparison with bigger fashions, 4.1-nano delivers sooner inference and decrease compute prices, making it properly fitted to large-scale workloads like:
- Buyer assist automation, the place fashions should deal with 1000’s of tickets per hour with constant tone and accuracy.
- Inside information assistants that comply with firm type and protocol in summarizing documentation or responding to FAQs.
As a small, quick, however extremely succesful mannequin, GPT-4.1-nano makes an incredible candidate for distillation as properly. You should utilize fashions like GPT-4.1 or o4 to generate coaching knowledge—or seize manufacturing visitors with saved completions—and educate 4.1-nano to be simply as good!
Llama 4 High quality-Tuning now accessible
We’re additionally excited to announce assist for fine-tuning Meta’s Llama 4 Scout—a innovative,17 billion energetic parameter mannequin which gives an business main context window of 10M tokens whereas becoming on a single H100 GPU for inferencing. It’s a best-in-class mannequin, and extra highly effective than all earlier technology llama fashions.
Llama 4 fine-tuning is accessible in our managed compute providing, permitting you to fine-tune and inference utilizing your individual GPU quota. Out there in each Azure AI Foundry and as Azure Machine Studying parts, you could have entry to extra hyperparameters for deeper customization in comparison with our serverless expertise.
Get began with Azure AI Foundry at present
Azure AI Foundry is your basis for enterprise-grade AI tuning. These fine-tuning enhancements unlock new frontiers in mannequin customization, serving to you construct clever techniques that suppose and reply in ways in which replicate your online business DNA.
- Use Reinforcement High quality-tuning with o4-mini to construct reasoning engines that study from expertise and evolve over time. Coming quickly in Azure AI Foundry, with regional availability for East US2 and Sweden Central.
- Use Supervised High quality-Tuning with 4.1-nano to scale dependable, cost-efficient, and extremely personalized mannequin behaviors throughout your group. Out there now in Azure AI Foundry in North Central US and Sweden Central.
- Strive Llama 4 scout advantageous tuning to customise a best-in-class open supply mannequin. Out there now in Azure AI Foundry mannequin catalog and Azure Machine Studying.
With Azure AI Foundry, fine-tuning isn’t nearly accuracy—it’s about belief, effectivity, and flexibility at each layer of your stack.
Discover additional:
We’re simply getting began. Keep tuned for extra mannequin assist, superior tuning strategies, and instruments that will help you construct AI that’s smarter, safer, and uniquely yours.