Unsloth

Unsloth is an open-source framework for fine-tuning, reinforcement learning, and running large language models locally. Its Python library trains 500+ models (text, vision, audio, embeddings) roughly 2x faster with up to 70-80% less VRAM via custom Triton kernels and dynamic quantization, and Unsloth Studio provides a local, browser-based GUI for no-code training and chat. Models loaded in Unsloth are exposed through an authenticated, OpenAI-compatible local API endpoint (llama-server) so agents like Claude Code, Codex, and standard OpenAI/Anthropic SDKs can use them; there is no hosted SaaS API. Backed by Lightspeed Venture Partners.

Unsloth is profiled on the APIs.io network. Tagged areas include Company, Artificial Intelligence, LLM Fine-Tuning, Machine Learning, and Open Source.

Unsloth’s developer surface includes documentation, getting-started guide, engineering blog, support, pricing, changelog, CLI, and 16 more developer resources.

🌐 Visit website 📡 Source on GitHub
25.8/100 emerging ▬ flat Agent 14/100 human only Full breakdown ↓
scored 2026-07-27 · rubric v0.5
AccessSelf serve
0 APIs
CompanyArtificial IntelligenceLLM Fine-TuningMachine LearningOpen SourceReinforcement LearningQuantizationLocal AIDeveloper Tools

Kin Score

Kin Score Kin Score How this is scored →
scored 2026-07-27 · rubric v0.5
Composite quality — 25.8/100 · emerging
Contract Quality 0.0 / 25
Developer Ergonomics 10.0 / 20
Commercial Clarity 6.3 / 20
Operational Transparency 2.7 / 13
Governance 0.0 / 12
Discoverability 6.8 / 10
Agent readiness — 14/100 · human only
Machine-Readable Contract 0 / 18
Agentic Access Contract 0 / 15
MCP Server 0 / 12
Machine-Readable Auth 10 / 10
Idempotency 0 / 9
Stable Error Semantics 0 / 8
Request/Response Examples 0 / 7
Rate-Limit Signaling 0 / 7
Typed Event Surface 0 / 6
Agent Skills 0 / 5
Well-Known Catalog 4 / 4
Consent & Bot Identity 0 / 3
Improve this rating by publishing the missing artifacts — every area above can be raised, and the full rubric is at apis.io/rating/. This rating is computed from github.com/api-evangelist/unsloth: open an issue to ask a question, or submit a pull request to add artifacts. Want it done for you? Prioritized profiling — $2,500 →

Security Posture 2

Authentication, domain security, vulnerability disclosure, and trust-center signals.

Unsloth Authentication

apiKey · 1 scheme

SECURITY

Unsloth Domain Security

TLSv1.3 · HSTS · DMARC

SECURITY

Resources

Get Started 1

Portal, sign-up, and the first successful call

GettingStarted
GettingStarted

Documentation 1

Reference material describing how the API behaves

Documentation
Documentation

Agent Surfaces 2

MCP servers, agent skills, and machine-readable catalogs

LLMsTxt
LLMsTxt
 WellKnown
WellKnown

Design & Contract 2

Pagination, idempotency, versioning, errors, and events

Conformance
Conformance
 Lifecycle
Lifecycle

Build 4

SDKs, sample code, and the tooling you integrate with

GitHubOrganization
GitHubOrganization
 Packages
Packages
 SDKs
SDKs
 CLI
CLI

Access & Security 2

Authentication, authorization, and security posture

DomainSecurity
DomainSecurity
 Authentication
Authentication

Operate 4

Status, limits, changes, and where to get help

Support
Support
 Contact
Contact
 ChangeLog
ChangeLog
 ChangeLog
ChangeLog

Commercial 3

Pricing, plans, and the legal terms of use

Pricing
Pricing
 TermsOfService
TermsOfService
 PrivacyPolicy
PrivacyPolicy

Company 3

The organization behind the API

Website
Website
 Blog
Blog
 Newsletter
Newsletter

Other 1

Properties that don't map to a standard resource type

ModelHub
ModelHub

Source (apis.yml)

apis.yml Raw ↑ 
aid: unsloth
name: Unsloth
description: Unsloth is an open-source framework for fine-tuning, reinforcement learning, and running large language models
  locally. Its Python library trains 500+ models (text, vision, audio, embeddings) roughly 2x faster with up to 70-80% less
  VRAM via custom Triton kernels and dynamic quantization, and Unsloth Studio provides a local, browser-based GUI for no-code
  training and chat. Models loaded in Unsloth are exposed through an authenticated, OpenAI-compatible local API endpoint (llama-server)
  so agents like Claude Code, Codex, and standard OpenAI/Anthropic SDKs can use them; there is no hosted SaaS API. Backed
  by Lightspeed Venture Partners.
url: https://raw.githubusercontent.com/api-evangelist/unsloth/refs/heads/main/apis.yml
x-type: company
x-source: vc-portfolio
x-backed-by:
- lightspeed-venture-partners
x-tier: profile
x-tier-reason: enriched-2026-07-21
accessModel:
  pricing: unknown
  onboarding: self-serve
  trial: false
  try_now: false
  public: false
  label: Self-serve signup
  confidence: medium
  source:
  - authentication
  generated: '2026-07-22'
  method: derived
specificationVersion: '0.20'
created: '2026-07-17'
modified: '2026-07-21'
tags:
- Company
- Artificial Intelligence
- LLM Fine-Tuning
- Machine Learning
- Open Source
- Reinforcement Learning
- Quantization
- Local AI
- Developer Tools
image: https://unsloth.ai/cgi/image/unsloth_logo_no_shadow_KgfOV6keeBZnffQsKUny3.png
apis: []
common:
- type: DomainSecurity
  url: security/unsloth-domain-security.yml
- name: Website
  type: Website
  url: https://unsloth.ai
- name: Documentation
  type: Documentation
  url: https://unsloth.ai/docs
- name: Getting Started
  type: GettingStarted
  url: https://unsloth.ai/docs/get-started/fine-tuning-for-beginners
- name: Blog
  type: Blog
  url: https://unsloth.ai/blog
- name: GitHub Organization
  type: GitHubOrganization
  url: https://github.com/unslothai
- name: Support (Discord Community)
  type: Support
  url: https://discord.com/invite/unsloth
- name: Contact
  type: Contact
  url: https://unsloth.ai/contact
- name: Pricing
  type: Pricing
  url: https://unsloth.ai/pricing
- name: Terms of Service
  type: TermsOfService
  url: https://unsloth.ai/terms
- name: Privacy Policy
  type: PrivacyPolicy
  url: https://unsloth.ai/privacy
- name: Newsletter
  type: Newsletter
  url: https://unslothai.substack.com/
- name: Hugging Face Organization
  type: ModelHub
  url: https://huggingface.co/unsloth
- name: Release Notes (GitHub Releases)
  type: ChangeLog
  url: https://github.com/unslothai/unsloth/releases
- name: Changelog Artifact
  type: ChangeLog
  url: changelog/unsloth-changelog.yml
- name: Packages
  type: Packages
  url: packages/unsloth-packages.yml
- name: SDKs
  type: SDKs
  url: packages/unsloth-packages.yml
- name: LLMs.txt
  type: LLMsTxt
  url: llms/unsloth-llms.txt
- name: Well-Known Index
  type: WellKnown
  url: well-known/unsloth-well-known.yml
- name: Conformance
  type: Conformance
  url: conformance/unsloth-conformance.yml
- name: CLI
  type: CLI
  url: cli/unsloth-cli.yml
- name: Authentication
  type: Authentication
  url: authentication/unsloth-authentication.yml
- name: Lifecycle
  type: Lifecycle
  url: lifecycle/unsloth-lifecycle.yml
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com
- FN: APIs.json
  email: info@apis.io
x-enrichment:
  date: '2026-07-21'
  status: enriched
  artifacts_added: 9
  pass: local-v1