Product Overview

Two approaches, vastly different token costs. On the left, a coding query is sent directly to Claude. On the right, the same query is routed to a smaller, cheaper model, more appropriate for the query's complexity. The result is stark. This model just routed that coding request to a model a hundred times smaller. Same answer, ten times cheaper, running on hardware you already own. Routing everything through one big rented model is the expensive default. Every AI request you send to a Frontier API costs metered tokens and you break the feedback loop. But this doesn't have to be. Fine tuning platforms give you the option to ditch the Frontier for everything and use inference more intelligently. You still do the engineer's job: evals, test sets, data curation, failure analysis and iteration. Oumi automates that whole workflow. Think Claude code but for AI engineering. And in this video, I'll show you how. We'll build a coding model router from a single prompt. No data required. Let's log in to the Oumi platform. You can chat with Oumi just like you would chat with Claude Code. Only Oumi is specialized for AI development, and we call this agentic AI engineering. Let's enter our prompt, and the prompt is as follows. I want to build a model router specifically for deciding between coding models. Given a coding question, the router must analyze its complexity, category, and requirements, Then recommend the most cost effective open model. All called Sonnet and Opus for the most complex tasks to answer it. You must balance quality against cost. Use cheaper, smaller models for simple tasks and reserve expensive, larger models for complex ones. After we've entered the prompt, the Oumi agent is now going to ask clarifying questions, in this case about the output format. We'll choose JSON and specify two fields, model chosen and the rationale, and it also asks about which models the router needs to decide between. Now at this stage, the Oumi agent decides that it has enough information about the task, and it devises a plan. And the plan is as follows. So define the metric, synthesize test data, evaluate the baseline models, synthesize training data, then fine tune the model, and evaluate the model after fine tuning. Finally, doing a review and deciding on next steps. So you can see that the different steps ask additional clarifying questions and launch jobs on Oumi managed infrastructure. It walks us through the entire process of model development. Afterwards, we have the evaluation metrics from a single cycle of synthesized data, train, evaluate, and it shows that we're able to improve the routing accuracy over the base model by seventeen percent from eighty three percent to one hundred percent on this eval set of one hundred samples, and improve the cost efficiency by fifteen percent to ninety seven percent, and also achieve a valid output format in ninety nine percent of outputs. So fine tuning has clearly made a huge improvement. Let's compare the results of fine tuning to OPUS four point six. In this case, we see that the fine tuned model, which is a hundred times smaller than OPUS, is able to match its performance on accuracy and cost efficiency, and even improves on valid output formatting, which in this case, is because we didn't enumerate the values for each field in the system prompt, whereas the fine tuned model was able to learn this from the data. So we've turned requiring metered tokens from a Frontier model forever to a fixed cost of a few dollars to train a small language model. But we can do even better. Both before the model is put into production and afterwards, valuable feedback signals exist, if only they could be captured and utilized. Fortunately, Oumi has several features for doing just that, and we call this the self improvement loop. Let's examine the failure modes of the fine tuned model. What this means is the high level groupings of the types of prediction errors observed. Oumi takes those failure modes and curates a training set targeted at exactly those gaps. Oumi can continuously improve your models, performing the same steps as we've just shown after the model has been put into production to learn from failed predictions, detect distribution drift, and more. Stop throwing away valuable learning signals when you build with Anthropic or OpenAI and start owning the self improvement loop. Don't want to handle the inference infrastructure? That's okay. Oumi can handle it for you with one click deployments. And to use the model in your existing code, it's as simple as swapping out your endpoint address for Oumi's OpenAI compatible endpoint. A single line change. On the other hand, if you do need to fully manage inference, you have complete control over the model weights you can deploy to your on premise infrastructure or even directly to consumer devices. Oumi gives you model sovereignty and full deployment options, whether that's Oumi managed in your Cloud VPN, on premise or on edge devices. You brought a task and Oumi synthesized, evaluated, trained and deployed. Minutes of human time and now you own the results. We've built a calculator for your AI tasks total cost of ownership. Describe your use case and we'll estimate costs and start building a prototype just for you. You can book a time to meet with an Oumi AI expert and see your AI prototype in action. Until then, I hope to see you on the platform. We're offering free credits for new users, and may the AI vibes be with you.