AI Horde (OpenAI-compatible front)

Verified ✅ Truly Free

A free, open-source, crowdsourced inference network where volunteers run the models. The oai.aihorde.net front puts an OpenAI-compatible chat completions API on top of the Horde's text workers. Requests without a key use the anonymous key 0000000000, at the lowest queue priority.

No Credit Card Free Tier OpenAI-Compatible
Get API Key Suggest Edit
0

Overview

Provider Type

API

API Endpoint

https://oai.aihorde.net/v1

Free Tier Highlights

Queue-based; anonymous requests have the lowest priorityregistered users earn kudos for priority

Why Choose AI Horde (OpenAI-compatible front)?

AI Horde (OpenAI-compatible front) stands out for its unique features and capabilities. With a developer-friendly API and comprehensive documentation, you can integrate AI capabilities into your applications within minutes.

Quick Start Guide

1

Optionally register at aihorde.net/register for a key

2

set base URL https://oai.aihorde.net/v1 with key 0000000000 or your own

3

pick a model from GET /v1/models

Available Models

Model Name ID Context Capabilities
Gemma 4 E4B IT Free
koboldcpp/gemma-4-E4B-it
65 000 Context
-
Qwen3 4B Free
koboldcpp/Qwen3-4B
8 000 Context
-
Llama 3.2 1B Instruct Free
koboldcpp/Llama-3.2-1B-Instruct
32 000 Context
-
L3 8B Stheno v3.2 Free
koboldcpp/L3-8B-Stheno-v3.2
8 000 Context
-
Rocinante XL 16B Free
koboldcpp/Rocinante-XL-16B-v1
16 000 Context
-

Integration Examples

Ready-to-use code snippets for your applications.

main.py
from openai import OpenAI

client = OpenAI(
    api_key="YOUR_AI_HORDE_KEY",
    base_url="https://oai.aihorde.net/v1"
)

response = client.chat.completions.create(
    model="koboldcpp/gemma-4-E4B-it",
    messages=[
        {"role": "user", "content": "Give me three tips for writing clean code."}
    ]
)

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

Free Tier Pricing & Limits

Rate Limit

Requests per minute

Queue-based; anonymous requests have the lowest priorityregistered users earn kudos for priority

Daily Quota

Requests per day

No fixed cap (volunteer capacity)

Use Cases

Zero-cost hobby and role-play chat

testing OpenAI clients without any account

Limitations & Considerations

Models and latency depend on which volunteers are online (queues can be long)

max_tokens 16-16384, default 512

mostly small or role-play fine-tunes, and volunteer workers can see prompts

Community Hub

Live

Join the discussion, share tips, and rate AI Horde (OpenAI-compatible front).

Quick Reactions

Add Discussion

Comments are moderated. Be helpful and respectful.

Recent Activity

0 comments

Ready to Get Started?

Join thousands of developers using AI Horde (OpenAI-compatible front)

Start Building Now