New

Distill a cheaper drop-in model from your agent traces with distil labs

Turn the agent traces you already collect into a training-ready dataset, then let distil labs fine-tune a cheaper drop-in model.

Put this blueprint to work

Talk it through with the dltHub team and we will help you ship it to production.

Your coding agent

Claude Code, Cursor or Codex

operates through

the agentic layer

dltHub AI harness

Agentic primitives to build, run and fix pipelines

dltHub context catalog

Lineage, schema, data quality, governance, run state

grounds and runs

Trace pipelines

Pydantic Logfire
Arize
Langfuse
LangChain

the managed infrastructure layer

Ingest and standardize traces into the OpenAI messages format as a training-ready dataset.

API

distil labs

Fine-tune a specialist model, served as a drop-in replacement via API to distil labs customers.

Four trace pipelines in. dltHub ingests and standardizes. distil labs turns it into a cheaper drop-in model.

How it works

This Blueprint gives distil labs customers a dltHub workspace that turns the agent traces they already collect into a training-ready dataset, ready to share with distil labs.

Point the workspace at your trace vendor (Pydantic, Arize, Langfuse, or LangChain). It ingests the traces, handles schema drift, and standardizes everything into the OpenAI messages format that distil labs trains on.

From the workspace you hand that dataset to distil labs, who fine-tune a specialist model and give you back a drop-in replacement served via API.

Key features

Your own dltHub workspace to collect and prepare agent traces
Ingests from Pydantic, Arize, Langfuse, and LangChain, standardized to the OpenAI messages format
One place to share trace data with distil labs, with no manual export or plumbing
distil labs fine-tunes a drop-in specialist model, served via API

How to get it

The trace pipelines and OpenAI-messages conversion are included in distil labs' dltHub. As a distil labs customer you get a dltHub workspace to collect and standardize your agent traces.
Contact distil labs to fine-tune the specialist model and get your drop-in replacement back.

Pricing

Standard: $1,190/month for dltHub Scale, the workspace and trace pipelines that make your traces training-ready.
Distillation: the fine-tuning step is priced by distil labs. Contact distil labs to scope it.

Built by

dltHub
distil labsTechnology partner

Put this blueprint to work

Talk it through with the dltHub team and we will help you ship it to production.

Find more blueprints