Hugging Face

Hugging Face

meta

Access Hugging Face models through Everstack's OpenAI-compatible gateway with routing, fallback, retries, and observability.

https://router.huggingface.co/v1
Models
21
Max context
1.0M
Input range
$0.10 - $30.00
Discovery
dynamic

Activity

Managed-cloud usage across this serving provider.

Daily period usage
Aggregated managed Everstack traffic. Buckets below 5 tenants or 100 requests are withheld.

Hugging Face models

21 shown
Hugging Face: DeepSeek V4 Pro 0813 (Hugging Face)stable

DeepSeek V4 Pro 0813 (Hugging Face) supports Chat, Function Calling, Reasoning workloads through Everstack.

by huggingfaceAug 12, 20261M context$1.32 input$3.96 output
ChatFunction CallingReasoning
Hugging Face: Qwen3.8 2.4T A95B (Hugging Face)stable

Qwen3.8 2.4T A95B (Hugging Face) supports Chat, Function Calling, Reasoning workloads through Everstack.

by huggingfaceAug 12, 2026262.1K context$2.50 input$6.25 output
ChatFunction CallingReasoning
Hugging Face: DeepSeek V4 Flash 0731 (Hugging Face)stable

DeepSeek V4 Flash 0731 (Hugging Face) supports Chat, Function Calling, Reasoning workloads through Everstack.

by huggingfaceJul 31, 20261.0M context$0.14 input$0.28 output
ChatFunction CallingReasoning
Hugging Face: Inkling Small (Hugging Face)stable

Inkling Small (Hugging Face) supports Chat, Function Calling, Vision, Reasoning workloads through Everstack.

by huggingfaceJul 30, 2026524.3K context$0.50 input$1.20 output
ChatFunction CallingVision
Hugging Face: Kimi K3 (Hugging Face)stable

Kimi K3 (Hugging Face) supports Chat, Function Calling, Vision, Reasoning workloads through Everstack.

by huggingfaceJul 16, 20261M context$3.00 input$15.00 output
ChatFunction CallingVision
Hugging Face: Inkling (Hugging Face)stable

Inkling (Hugging Face) supports Chat, Function Calling, Vision, Reasoning workloads through Everstack.

by huggingfaceJul 15, 20261.0M context$1.00 input$4.05 output
ChatFunction CallingVision
Hugging Face: GLM-5.2 (Hugging Face)stable

GLM-5.2 (Hugging Face) supports Chat, Function Calling, Reasoning workloads through Everstack.

by huggingfaceJun 13, 2026262.1K context$1.40 input$4.40 output
ChatFunction CallingReasoning
Hugging Face: Kimi K2.7 Code (Hugging Face)stable

Kimi K2.7 Code (Hugging Face) supports Chat, Function Calling, Vision, Reasoning workloads through Everstack.

by huggingfaceJun 12, 2026262.1K context$0.95 input$4.00 output
ChatFunction CallingVision
Hugging Face: MiniMax-M3 (Hugging Face)stable

MiniMax-M3 (Hugging Face) supports Chat, Function Calling, Vision, Reasoning workloads through Everstack.

by huggingfaceJun 1, 2026524.3K context$0.30 input$1.20 output
ChatFunction CallingVision
Hugging Face: Step 3.7 Flash (Hugging Face)stable

Step 3.7 Flash (Hugging Face) supports Chat, Function Calling, Vision, Reasoning workloads through Everstack.

by huggingfaceMay 29, 2026262.1K context$0.20 input$1.15 output
ChatFunction CallingVision
Hugging Face: DeepSeek V4 Pro (HF)stable

DeepSeek V4 Pro (HF) supports Chat, Function Calling, Reasoning workloads through Everstack.

by huggingfaceApr 24, 20261.0M context$0.43 input$0.87 output
ChatFunction CallingReasoning
Hugging Face: Kimi K2.6 (HF)stable

Kimi K2.6 (HF) supports Chat, Function Calling, Vision, Reasoning workloads through Everstack.

by huggingfaceApr 20, 2026262.1K context$0.95 input$4.00 output
ChatFunction CallingVision
Hugging Face: GLM-5.1 (HF)stable

GLM-5.1 (HF) supports Chat, Function Calling, Reasoning workloads through Everstack.

by huggingfaceApr 3, 2026202.8K context$1.00 input$3.20 output
ChatFunction CallingReasoning
Hugging Face: Qwen3 Next 80B Instruct (HF)stable

Qwen3 Next 80B Instruct (HF) supports Chat, Function Calling workloads through Everstack.

by huggingfaceSep 11, 2025262.1K context$0.25 input$1.00 output
ChatFunction Calling
Hugging Face: Qwen3 Coder 480B (HF)stable

Qwen3 Coder 480B (HF) supports Chat, Function Calling workloads through Everstack.

by huggingfaceJul 23, 2025262.1K context$2.00 input$2.00 output
ChatFunction Calling
Hugging Face: GPT-3.5 Turbodeprecated

GPT-3.5 Turbo supports Chat, Function Calling workloads through Everstack.

by huggingface16.4K context$0.50 input$1.50 output
ChatFunction Calling
Hugging Face: GPT-4deprecated

GPT-4 supports Chat, Function Calling workloads through Everstack.

by huggingface8.2K context$30.00 input$60.00 output
ChatFunction Calling
Hugging Face: GPT-4 Turbodeprecated

GPT-4 Turbo supports Chat, Function Calling, Vision workloads through Everstack.

by huggingface128K context$10.00 input$30.00 output
ChatFunction CallingVision
Hugging Face: GPT-4odeprecated

GPT-4o supports Chat, Function Calling, Vision workloads through Everstack.

by huggingface128K context$5.00 input$15.00 output
ChatFunction CallingVision
Hugging Face: GPT-4o Minideprecated

GPT-4o Mini supports Chat, Function Calling, Vision workloads through Everstack.

by huggingface128K context$0.15 input$0.60 output
ChatFunction CallingVision
Hugging Face: Text Embedding Ada 002deprecated

Text Embedding Ada 002 supports Embeddings workloads through Everstack.

by huggingface8.2K context$0.10 input- output
Embeddings