Refuel

Refuel is an AI data-labeling and data-enrichment platform that uses LLMs to label, clean, structure, and enrich enterprise datasets. Refuel Cloud exposes a REST API where datasets, tasks, and deployed applications transform new data in realtime, and the open-source autolabel library lets teams run the same LLM labeling workflows in their own environment.

6 APIs 0 Features

AILLMData LabelingData EnrichmentAutolabel

APIs

Refuel Applications API

Deployed applications are versioned snapshots of a Task served behind a REST API. Call POST /applications/{application-name}/label with a JSON array of rows to transform new dat...

Refuel Tasks API

A Task is a set of LLM guidelines defining the transformation to perform on a dataset (classification, extraction, structured output). Tasks support structured outputs, batch pr...

Refuel Datasets API

A dataset is a collection of structured / semi-structured rows you want to transform with LLMs. Datasets can be uploaded directly or imported from cloud storage (S3, GCS) and da...

Refuel Labeling and Predict API

Submit rows to a deployed application to run LLM labeling / prediction in realtime via the label endpoint, returning enriched output values plus confidence and explanations for ...

Refuel Models API

Refuel hosts and finetunes LLMs purpose-built for data labeling. Tasks can use Refuel-hosted base models or custom finetuned models, with finetuning runs tracked and finetuned m...

Refuel Autolabel (Open Source)

Autolabel is the open-source Python library (pip install refuel-autolabel) to label, clean, and enrich text datasets with any LLM (OpenAI, Anthropic, Google, HuggingFace, vLLM, ...

Collections

Refuel Cloud API

OPEN

Pricing Plans

Refuel Ai Plans Pricing

3 plans

PLANS

Rate Limits

Refuel Ai Rate Limits

2 limits

RATE LIMITS

FinOps

Refuel Ai Finops

FINOPS

Resources

👥

GitHubOrganization

Sources

opencollection: 1.0.0
info:
  name: Refuel Cloud API
  version: '1.0'
request:
  auth:
    type: bearer
    token: '{{apiKey}}'
items:
- info:
    name: Applications
    type: folder
  items:
  - info:
      name: Transform rows with a deployed application
      type: http
    http:
      method: POST
      url: https://cloud-api.refuel.ai/applications/{{applicationName}}/label
      headers:
      - key: Content-Type
        value: application/json
      - key: Accept
        value: application/json
      body:
        type: json
        data: "[{\n  \"resume_link\": \"https://path/to/resume.pdf\"\n}]"
    docs: Submit a JSON array of input rows to a deployed application to run LLM labeling / prediction in realtime. Each row
      is an object whose keys match the application's expected input fields. Subject to 300 requests/min and up to 100 concurrent
      requests.