Jan.ai

Verified ✅ Truly Free

Jan is an open-source, offline ChatGPT alternative for the desktop with an OpenAI-compatible local server and MCP tool support. Version 0.8.8 (October 2026) added Trusted Hosts origin checks for the local API, opt-in server-side MCP execution and a safer Claude Code integration, with a bundled llama.cpp engine.

Local AI Offline Privacy Desktop App
Get API Key Suggest Edit
1477

Overview

Provider Type

Local

API Endpoint

http://localhost:1337/v1

Free Tier Highlights

Hardware dependent

Why Choose Jan.ai?

Jan is an open-source, offline ChatGPT alternative for the desktop, with a local OpenAI-compatible server, MCP tool support and a bundled llama.cpp engine.

Best for: people who want a polished, private chat app that also serves an API to other tools.

Watch out: speed and model size depend entirely on your hardware.

Quick Start Guide

1

Download Jan from https://jan.ai/

2

Install and Open

3

Go to Hub -> Download Model

4

Start Chatting

5

Enable Local Server in settings

Available Models

9 free models
Model Name ID Context
GPT-OSS 20B (GGUF) Free
gpt-oss-20b
-
LFM3 1.7B (GGUF) Free
lfm3-1.7b
-
Flint 40B (GGUF) Free
flint-40b
-
Ternary Bonsai 2 27B (GGUF) Free
prism-ml/Ternary-Bonsai-2-27B-gguf
-
Gemma 4 12B Free
gemma-4-12b-it
-
Qwen3.8 27B (GGUF) Free
unsloth/Qwen3.8-27B-GGUF
-
Llama 3 (Local) Free
llama3-8b-instruct
System RAM dependent
Mistral (Local) Free
mistral-7b-instruct
System RAM dependent
Gemma 2 (Local) Free
gemma-2-9b-it
System RAM dependent

Integration Examples

Ready-to-use code snippets for your applications.

main.py
from openai import OpenAI

# Jan.ai local server (enable in Settings)
client = OpenAI(
    api_key="jan",
    base_url="http://localhost:1337/v1"
)

response = client.chat.completions.create(
    model="gpt-oss-20b",
    messages=[
        {"role": "user", "content": "Write a haiku about local AI"}
    ]
)

print(response.choices[0].message.content)

Free Tier Pricing & Limits

Rate Limit

Requests per minute

Hardware dependent

Daily Quota

Requests per day

Unlimited

Token Limit

Tokens per minute

Unlimited

Monthly Quota

Per month limit

Free Forever (Open Source)

Use Cases

Privacy-critical work

Offline coding/writing

Testing local models

Personal AI assistant

Limitations & Considerations

Requires decent hardware (RAM/GPU)

Battery drain on laptops

Local model quality vs GPT-4

Download sizes (GBs)

Community Hub

Live

Join the discussion, share tips, and rate Jan.ai.

Quick Reactions

Add Discussion

Comments are moderated. Be helpful and respectful.

Recent Activity

0 comments

Ready to Get Started?

Join thousands of developers using Jan.ai

Start Building Now