Back to providers
Hugging Face Inference
UnhealthyTelemetry updated 38m agoInference API and dedicated endpoints for open-source models hosted on the Hugging Face Hub. Offers serverless inference for popular models and dedicated GPU endpoints for production workloads.
API Base URL
https://api-inference.huggingface.co
Authentication
bearer
Uptime (24h)
0.0%
Uptime (7d)
36.3%
Supported Regions
us-east-1eu-west-1
Latency (TTFT)
Time to first token percentiles
No latency data available
Health History
Uptime over the last 7 days
7-Day Uptime36.31% — Critical
24-Hour Uptime0.00% — Critical
Current Status
unhealthy
Last Checked
38m ago
Supported Models (3)
Models available through this provider. Click a model to view details.
| Model | Pricing (per 1M) | Rate Limits | Regions |
|---|---|---|---|
DeepSeek V4 deepseek-v4 | In: $0.18 Out: $0.36 | 300 RPM / 500K TPM | us-east-1eu-west-1 |
Llama 4 Maverick llama-4-maverick | In: $0.30 Out: $0.30 | 300 RPM / 500K TPM | us-east-1eu-west-1 |
Qwen3 32B qwen3-32b | In: $0.18 Out: $0.18 | 300 RPM / 500K TPM | us-east-1eu-west-1 |