{"version":1,"type":"story","url":"https://digestai.news/story/baseten-releases-serverless-loops-for-open-model-fine-tuning-with-per","json":"https://digestai.news/story/baseten-releases-serverless-loops-for-open-model-fine-tuning-with-per.json","markdown":"https://digestai.news/story/baseten-releases-serverless-loops-for-open-model-fine-tuning-with-per.md","slug":"baseten-releases-serverless-loops-for-open-model-fine-tuning-with-per","headline":"Baseten releases Serverless Loops for open-model fine-tuning with per-token billing","summary":"Baseten made its **Serverless Loops** SDK generally available on November 6, 2026, enabling users to fine-tune open models for supervised learning and reinforcement tasks without managing infrastructure. The service bills by token—only for training and sampling, not idle time—and abstracts away GPU allocation, kernels, and distributed training, leaving users to define training signals, base models, and hyperparameters like LoRA rank or loss functions.\n\nThe **serverless catalog** currently supports three models: **Qwen/Qwen3.6-35B-A3B**, **zai-org/GLM-5.3-Flash** (text + vision), and **zai-org/GLM-5.3** (text only), each with a 262,144-token limit. Users can deploy trained checkpoints as OpenAI-compatible endpoints, with GPU costs tied to inference runtime. Baseten highlights improvements in error handling, startup speed, and weight transfers, citing daily handling of **15 billion requests** across its production inference stack. Early adopters like **Datadog**, **Ambience Healthcare**, and **LangChain Labs** used the service for RL-based agent training, clinical transcription correction, and GitHub issue diagnosis, respectively.","keyPoints":["Serverless Loops bills by token for training/sampling only, excluding idle time or result review","Supports three open models (Qwen/GLM variants) with 262,144-token context; deployment requires Hugging Face access","Checkpoints persist post-run and can be deployed as OpenAI-compatible endpoints with live GPU billing"],"whyItMatters":"This lowers the barrier for teams to experiment with fine-tuning open models without GPU expertise or upfront costs, accelerating adoption of specialized agents for niche tasks like clinical transcription or SRE workflows.","category":{"slug":"research","name":"Research","url":"https://digestai.news/category/research"},"entities":{"companies":["Baseten","NVIDIA","Datadog","Ambience Healthcare","LangChain Labs"],"models":["Qwen/Qwen3.6-35B-A3B","zai-org/GLM-5.3-Flash","zai-org/GLM-5.3","Nemotron Super 3.5 VL"],"people":[]},"firstPublishedAt":"2026-11-06T16:53:03Z","updatedAt":"2026-11-06T16:53:03Z","sourceCount":1,"hasPrimarySource":false,"sources":[{"outlet":"Unite.AI","title":"Baseten Makes Serverless Loops Generally Available for Post-Training","url":"https://unite.ai/baseten-makes-serverless-loops-generally-available-for-post-training","publishedAt":"2026-11-06T16:53:03Z","type":"press","primary":false,"lead":true}],"sourceNotes":null,"discussions":[],"thread":{"title":"Baseten Builds Enterprise AI Infrastructure","url":"https://digestai.news/thread/baseten-launches-grid-to-route-and-govern-enterprise-ai-coding","storyCount":2},"cite":{"text":"Digest AI, \"Baseten releases Serverless Loops for open-model fine-tuning with per-token billing\", 6 November 2026, https://digestai.news/story/baseten-releases-serverless-loops-for-open-model-fine-tuning-with-per","publisher":"Digest AI","title":"Baseten releases Serverless Loops for open-model fine-tuning with per-token billing","datePublished":"2026-11-06T16:53:03Z","url":"https://digestai.news/story/baseten-releases-serverless-loops-for-open-model-fine-tuning-with-per"},"generatedBy":"Written by Digest AI's editorial model from the linked sources; the sources are the record.","license":"Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse"}