distil labs

Trusted by

What distil labs does

Every Agent Type Supported

All supported out of the box.

Routing & classification
Function calling — single and multi-turn
Structured data extraction
Question answering

Browse tutorials →

Problem In, Model Out

Start training in 30 min from a prompt, 5–50 examples or production traces. Use the CLI or connect your observability platform directly — whatever fits your workflow.

Start training with minimal data
Automated data generation & training
LLM-level accuracy, 280x smaller

Get started →

Easy Integration

Side-by-side evaluation and hosted API endpoint out of the box. No infrastructure to provision, no GPU clusters to manage.

Managed inference endpoint included
Automated teacher evaluation & metrics
Integrate directly into your stack

Metrics & evaluation →

From Problem to Model

$ distil model create my-classifier
✔ Model created: my-classifier (mdl_8f3k2a)

$ distil model upload-data mdl_8f3k2a --data ./training-data.jsonl
Uploading ████████████████████ 100%
✔ Examples validated
✔ Dataset attached to mdl_8f3k2a

01

Upload Data

Create a model and upload your dataset in one go — 10 to 50 diverse examples is usually enough. Supports classification, QA, tool calling, multi-turn tool calling, and more.

$ distil model run-training mdl_8f3k2a

Training started...
✔ Teacher evaluation complete
✔ Training complete
✔ Model ready: mdl_8f3k2a

02

Train Model

Start training with a single command. Get feedback on task performance in minutes and model ready in a few hours. Trained SLMs consistently match frontier models 100x larger.

$ distil model deploy mdl_8f3k2a
✔ Endpoint live: https://api.distillabs.ai/v1/mdl_8f3k2a

$ distil model invoke mdl_8f3k2a --input "Classify: I want to return my order"
{
  "label": "return_request",
  "confidence": 0.97
}

03

Deploy & Invoke

Deploy your trained model to a hosted endpoint with one command, then invoke it immediately. No infrastructure to set up — just deploy and call.

from openai import OpenAI

# Just change the base URL — everything else stays the same
client = OpenAI(
    base_url="https://api.distillabs.ai/v1/mdl_8f3k2a",
    api_key="your-distil-api-key",
)

response = client.chat.completions.create(
    model="mdl_8f3k2a",
    messages=[{"role": "user", "content": "Classify: I want to return my order"}],
)
print(response.choices[0].message.content)
# → {"label": "return_request", "confidence": 0.97}

04

Integrate

Swap one URL in your existing code — that’s it. The distil labs endpoint is OpenAI-compatible, so any SDK or client that talks to OpenAI works out of the box.

Integration guide

What Our Customers Say

The distil labs platform accelerated the release of our cybersecurity-specialized language model, KINDI, enabling faster iterations with greater confidence. As a result, we ship InovaGuard improvements sooner and continuously boost investigation accuracy with every release.

Samir Bennacer

Co-Founder and CTO at Octodet

Read case study →

Using distil labs, we were able to spin up highly accurate custom small models tailored to our workflows in no time. Those models cut our inference costs by roughly 50% without sacrificing quality. The distil labs team was incredibly supportive as we got started and helped us get to production smoothly.

Lucas Hild

Co-Founder & CTO at Knowunity

Read case study →

With distil labs, we built a custom model using just ~100 datapoints in days. The self-service retraining has been especially valuable for our team-we can retrain the model ourselves with new data. The distil labs team was responsive and guided us through the entire process.

Sascha Bührle

Co-Founder & CEO at Uptime Industries

Read case study →