A AIHubMix
activeUnified OpenAI-compatible API aggregating OpenAI, Claude, Gemini, DeepSeek, GLM, Qwen and more — with load balancing and high concurrency support.
https://aihubmix.com/v1
Avg Latency
—
90-day Uptime
—%
Rate Limits
5 RPM / 500 RPD
Sign-up Required
Yes
Info
Models (19)
gpt-4.1-free
CTX: 1M · 5 RPM
gpt-4.1-mini-free
CTX: 1M · 5 RPM
gpt-4.1-nano-free
CTX: 1M · 5 RPM
gpt-4o-free
CTX: 1M · 5 RPM
gemini-3-flash-preview-free
CTX: 1M · 5 RPM
gemini-2.0-flash-free
CTX: 1M · 5 RPM
coding-glm-5.1-free
CTX: 128K · 5 RPM
coding-glm-5-free
CTX: 128K · 5 RPM
coding-glm-5-turbo-free
CTX: 128K · 5 RPM
coding-glm-4.7-free
CTX: 128K · 5 RPM
glm-4.7-flash-free
CTX: 128K · 5 RPM
coding-glm-4.6-free
CTX: 200K · 5 RPM
coding-minimax-m2.7-free
CTX: 200K · 5 RPM
coding-minimax-m2.5-free
CTX: 200K · 5 RPM
coding-minimax-m2.1-free
CTX: 200K · 5 RPM
coding-minimax-m2-free
CTX: 200K · 5 RPM
step-3.5-flash-free
CTX: 256K · 5 RPM
kimi-for-coding-free
CTX: 256K · 5 RPM
mimo-v2-flash-free
CTX: 256K · 5 RPM
Quick Start
export API_KEY="your_api_key_here"
curl https://aihubmix.com/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $API_KEY" \
-d '{
"model": "gpt-4.1-mini-free",
"messages": [
{"role": "user", "content": "Hello! How are you?"}
]
}' 
