AIHubMix (free models)

Verified ✅ Truly Free

An OpenAI-compatible model gateway that lists about 35 zero-priced "-free" routes next to its paid catalog. Each free route's description sets per-account limits, usually 5 RPM, 100 requests/day and 1M tokens/day. AIHubMix also has an Anthropic-format endpoint for coding clients.

Free Account Renewable Allowance OpenAI-Compatible
Get API Key Suggest Edit
0

Overview

Provider Type

Proxy

API Endpoint

https://aihubmix.com/v1

Free Tier Highlights

5 RPM per account on most *-free routes

Why Choose AIHubMix (free models)?

AIHubMix (free models) 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

Create an account at aihubmix.com

2

create a key in console.aihubmix.com

3

set base URL https://aihubmix.com/v1 and use a "-free" model id

Available Models

Model Name ID Context Capabilities
Coding GLM 5.3 (free) Free
coding-glm-5.3-free
1 000 000 Context
-
Coding GLM 5.3 Flash (free) Free
coding-glm-5.3-flash-free
1 000 000 Context
-
Coding Kimi K3 (free) Free
coding-kimi-k3-free
1 000 000 Context
-
Coding MiniMax M3 (free) Free
coding-minimax-m3-free
1 000 000 Context
-
Xiaomi MiMo V2.6 Pro (free) Free
xiaomi-mimo-v2.6-pro-free
1 000 000 Context
-
Nemotron 3 Ultra 550B A55B (free) Free
nemotron-3-ultra-550b-a55b-free
1 000 000 Context
-
Gemma 4 31B IT (free) Free
gemma-4-31b-it-free
262 000 Context
-
GLM 4.7 Flash (free) Free
glm-4.7-flash-free
200 000 Context
-

Integration Examples

Ready-to-use code snippets for your applications.

main.py
from openai import OpenAI

client = OpenAI(
    api_key="YOUR_AIHUBMIX_KEY",
    base_url="https://aihubmix.com/v1"
)

response = client.chat.completions.create(
    model="coding-glm-5.3-free",
    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

5 Requests per minute per account on most *-free routes

Daily Quota

Requests per day

100 requests/day and 1 000 000 tokens/day per account (500 Requests per day on somee.g. glm-4.7-flash-freecoding-minimax-m3-free)

Use Cases

Free coding-agent backend (Claude Code or Codex through the gateway)

trying several frontier open models with one key

Limitations & Considerations

Strict per-account caps (5 RPM, 100 RPD, 1M tokens/day)

free routes come and go (e.g. qwen3.6-plus-preview-free has been removed)

the ":free" Llama/Mistral ids are not zero-priced (0.02 ratio), so use the "-free" suffixed ids

Community Hub

Live

Join the discussion, share tips, and rate AIHubMix (free models).

Quick Reactions

Add Discussion

Comments are moderated. Be helpful and respectful.

Recent Activity

0 comments

Ready to Get Started?

Join thousands of developers using AIHubMix (free models)

Start Building Now