Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
Inference Providers
·
Metrics for top trending models
Browse all models
Learn more
Model
Provider
Input $/1M
Output $/1M
Context
Latency(s)
Throughput(t/s)
Tools
Structured
HuggingFaceTB/SmolLM3-3B
SmolLM3-3B
hf-inference
-
-
-
0.11
91
Yes
Yes
katanemo/Arch-Router-1.5B
Arch-Router-1.5B
hf-inference
-
-
-
0.19
69
No
Yes