Skip to main content

Hugging Face

Aggregator

Hugging Face routes one API key to many upstream providers, so you can switch models without new accounts.

PricingDocsStatuspress@huggingface.co
Models108
Cheapest for
14 models
Serves
2 model types
Monthly visits—
Models by type

Models on Hugging Face

ModelInputOutputvs officialContext
Qwen3 Next 80B A3B Instruct$0.09/1MFrom$1.10/1M——
Qwen3 VL 235B A22B Instruct$0.20/1MFrom$0.88/1M——
Qwen3 VL 30B A3B Instruct$0.15/1MFrom$0.60/1M
from $0.389 at SiliconFlow
+54%—
Qwen3.5 122B-A10B$0.29/1MFrom$2.40/1M
from $0.901 at AIHubMix
-25%—
SSao10K Stheno 8bCheapest$0.05/1MFrom$0.05/1M±0%—
Step 3.5 Flash$0.10/1MFrom$0.30/1M
from $0.292 at SiliconFlow
+3%—
Step 3.7 Flash$0.20/1MFrom$1.15/1M
from $0.925 at APIMart
+24%—
WizardLM-2 8x22BCheapest$0.62/1MFrom$0.62/1M±0%—

Hugging Face at a glance

108 models in total: 107 text, 1 moderation. The cheapest is Qwen3-4B at $0.03 /1M. Llama 4 Scout 17B Instruct has the largest context window, 1.31M tokens. The most searched is Kimi K3, with about 658K Google searches a month. The newest is DeepSeek V4 Flash Vision Exp, released Oct 17, 2026.

Cheapest

  1. Qwen3-4B$0.03/1M
  2. Qwen2.5-Coder-7B$0.03/1M
  3. Qwen2p5 Coder 3B$0.03/1M
  4. Llama 3.1 8B Instruct$0.05/1M
  5. DeepSeek R1 Distill Llama 8B$0.05/1M

Largest context

  1. Llama 4 Scout 17B Instruct1.31M
  2. MiMo-V2.51.05M
  3. MiMo-V2.5-Pro1.05M
  4. Kimi K31.05M
  5. GLM-5.31.05M

Most searched

  1. Kimi K3658K
  2. GLM-5.3276K
  3. Qwen3.8 2.4T A95B234K
  4. DeepSeek V4.1 Flash138K
  5. GLM-5.3-Flash121K

Newest

  1. DeepSeek V4 Flash Vision ExpOct 17, 2026
  2. Beam 1.0 501B A23BOct 16, 2026
  3. Nemotron 3.5 Super VL 120B A12BOct 15, 2026
  4. Ling 3.1 FlashOct 13, 2026
  5. MiMo-V2.6-ProSep 21, 2026