Latest
Together AI ships a $17 recipe for custom support-ticket classifiers
Together AI released together/Tev1-4B-experimental, a Qwen3.5 4B-based classifier, and published a guide showing how to fine-tune a similar model for roughly $17 using 38,000 labeled examples. The resulting model takes a customer message plus multiple-choice options and returns a single label in JSON, suited to support intent routing.
What changes for operators — For a support team fielding a few hundred tickets a day, this is a concrete blueprint for a first-line triage bot: feed in the customer message plus your existing intent list, get back a single label in under a token's worth of output, and route accordingly. The training cost (~$17) and time (~25 minutes) make it cheap enough to iterate on your own historical tickets rather than rely on a general-purpose LLM call for every classification, and the fixed temperature=0, max_tokens=8 setup makes outputs predictable enough to feed directly into a routing rule or CRM webhook without a human review step for high-confidence cases.