BriefsToolAvailable now
Together AI launches Post-Training service for custom AI models with RL and SFT
Together Post-Training lets teams train custom open-weight AI models with RL or SFT on dedicated GPUs, with a reduced launch price of $9 per GPU-hour of B200 for eight weeks.
Summary
Together AI introduced Together Post-Training, a service for building custom models using reinforcement learning from environment rewards and supervised fine-tuning. You define the training loop, and Together runs the infrastructure. It launches with several open-weight models and supports LoRA and, for select models, full-weight training.
What changed
- New service for custom model training via RL and SFT, with the full training loop defined by the user
- Supports LoRA, including multiple adapters on shared GPUs, and full-weight runs for select models
- Launch models include Muse Spark Open, GLM 5.3, Kimi K3 and Qwen 3.8-27B, with more coming in the coming weeks
- Multi-LoRA adapter serving now supported in Dedicated Model Inference
- Tinker users can migrate by changing one import line
Availability
Available now“the feedback we received was invaluable in developing the product which now everyone can use.”
Pricing
| Plan | Price, as stated | Checked |
|---|---|---|
| Launch price for the first eight weeks | $9 per GPU-hour of B200 usage“For the first eight weeks, we are offering Together Post-Training at a reduced price of $9 per GPU-hour of B200 usage.” source |
Prices as stated by the company; we don’t convert or estimate.
Founder takeaway
If you have a narrow, repeated AI task and want a cheaper specialist model, the SDK and cookbooks are a low-effort way to test it, especially during the eight-week reduced price. Check the billing is per GPU-minute before scaling runs.
Source
Researched and drafted with AI from the official sources above, then checked automatically before publishing. Spotted a mistake? Tell us.
Related
More briefs
Vercel adds sandbox plugin support for running Paseo AI agents
Paseo now supports running AI agents in the cloud using the Vercel Sandbox plugin.
Vercel1 min read
Vercel introduces Virtual Models on AI Gateway for AI apps
Vercel released Virtual Models on AI Gateway to let developers manage model strings and fallbacks centrally.
Vercel1 min read
Vercel CLI allows AI agents to enable web analytics and observability
AI agents can now enable Web Analytics and Observability Plus for projects without requiring an interactive terminal.
Vercel1 min read
One email, every Monday
Briefs are published here through the day. Monday Heist is the email: one useful AI workflow, the files to use it, and the catch. The first issue is being prepared; subscribers get it first. Free, and you can leave in one click.
One email. Every Monday.