Hugging Face Inference
archivedFree Hugging Face accounts no longer receive monthly Inference Providers credits. Credits must be purchased or included in a paid subscription.
https://router.huggingface.co/v1
Last Probe Latency
—
Healthy Observed Days
—
Rate Limits
— RPM / — RPD
Sign-up Required
Yes
Provider status summarizes sampled models checked with the monitoring account. Your access and limits may differ.
Documentation checked: . Model availability is subject to the provider's current catalog.
Free Hugging Face accounts no longer receive monthly Inference Providers credits. Credits must be purchased or included in a paid subscription.
Historical model list retained for reference; not a current free API catalog.
Info
Models(6)
Model health is unknown until an actual check completes.
meta-llama/Llama-3.3-70B-Instruct
Context: 128K
deepseek-ai/DeepSeek-V3-0324
Context: 128K
openai/gpt-oss-120b
Context: 128K
deepseek-ai/DeepSeek-R1
Context: 128K
Qwen/Qwen3-235B-A22B
Context: 128K
moonshotai/Kimi-K2-Instruct
Context: 128K
No unified per-token rate — paid usage passes through whichever partner (Groq, SambaNova, Together, Cerebras, etc.) serves the request at that partner's own price, with no HF markup.
Quick Start
export API_KEY="your_api_key_here"
curl 'https://router.huggingface.co/v1/chat/completions' \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $API_KEY" \
-d '{
"model": "meta-llama/Llama-3.3-70B-Instruct",
"messages": [
{
"role": "user",
"content": "Hello! How are you?"
}
]
}'