Skip to content
Sovyron

Hugging Face

78 modelsProvider docs

As of Oct 4, 2026, Hugging Face lists 78 supported models in the Sovyron catalog, including DeepSeek V4.1 Flash, Hy4 preview, GLM-5.3-Flash, DeepSeek V4 Flash Vision Exp and GLM-5.3 — deepseek-flash, Hy, glm-flash, glm, qwen and deepseek-thinking families. Its metered rates span $0.0075–$6 per 1M tokens on a 3:1 input:output blend, and every price in the table is Hugging Face's own, normalized to USD — open a model to compare it with the cheapest offer across all providers. Offer mix: 1 free-tier offer.

Supported models and pricing

78 of 78 models
Hugging Face model prices in USD per 1M tokens, updated Oct 4, 2026
Model1M input1M output1M cache readContextReleasedTags
DeepSeek V4.1 Flash$0.3$1.2—1.0MSep 10, 2026
Hy4 preview$0.834$2.501—1.0MAug 28, 2026
GLM-5.3-Flash$0.15$0.5—1.0MAug 26, 2026
DeepSeek V4 Flash Vision Exp$0.44$1.32—1.0MAug 21, 2026
GLM-5.3$1.4$4.4—1.0MAug 14, 2026
Qwen3.8 27B$0.4$3—262kAug 14, 2026
DeepSeek V4 Pro 0813$1.32$3.96—1.0MAug 12, 2026
Qwen3.8 2.4T A95B$2.5$6.25—262kAug 12, 2026
DeepSeek V4 Flash 0731$0.14$0.28—1.0MJul 31, 2026
Inkling Small$0.5$1.2—524kJul 30, 2026
Kimi K3$3$15—1.0MJul 16, 2026
Inkling$1$4.05—1.0MJul 15, 2026
Hy3$0.14$0.58—262kJul 6, 2026
GLM-5.2$1.4$4.4—262kJun 13, 2026
Kimi K2.7 Code$0.95$4—262kJun 12, 2026
MiniMax-M3$0.3$1.2—524kJun 1, 2026
Step 3.7 Flash$0.2$1.15—262kMay 29, 2026
DeepSeek V4 Flash$0.14$0.28—1.0MApr 24, 2026
DeepSeek V4 Pro$0.435$0.87$0.00361.0MApr 24, 2026
MiMo-V2.5$0.4$2—262kApr 22, 2026
MiMo-V2.5-Pro$1$3—1.0MApr 22, 2026
Qwen3.6 27B$0.47$3.19—262kApr 22, 2026
Kimi K2.6$0.95$4$0.16262kApr 20, 2026
Qwen3.6 35B-A3B$0.15$0.95—262kApr 17, 2026
GLM-5.1$1$3.2$0.2203kApr 3, 2026
Gemma 4 26B A4B IT$0.13$0.4—262kApr 2, 2026
Gemma 4 31B IT$0.14$0.4—262kApr 2, 2026
MiniMax-M2.7$0.3$1.2$0.06205kMar 18, 2026
Qwen3.5 122B-A10B$0.4$3.2—262kFeb 23, 2026
Qwen3.5 27B$0.3$2.4—262kFeb 23, 2026
Qwen3.5 35B-A3B$0.25$2—262kFeb 23, 2026
Qwen3.5 9B$0.17$0.25—262kFeb 23, 2026
MiniMax-M2.5$0.3$1.2$0.03205kFeb 12, 2026
GLM-5$1$3.2$0.2203kFeb 11, 2026
Qwen3 Coder Next$0.2$1.5—262kFeb 3, 2026
Qwen3.5 397B-A17B$0.6$3.6—262kFeb 1, 2026
Step 3.5 Flash$0.1$0.3—262kJan 29, 2026
Kimi K2.5$0.6$3$0.1262kJan 1, 2026
MiniMax-M2.1$0.3$1.2—205kDec 23, 2025
GLM-4.7$0.6$2.2$0.11205kDec 22, 2025
MiMo-V2-Flash$0.1$0.3—262kDec 16, 2025
GLM-4.6V-Flash$0.3$0.9—131kDec 8, 2025
DeepSeek V3.2$0.28$0.4—164kDec 1, 2025
Kimi K2 Thinking$0.6$2.5$0.15262kNov 6, 2025
MiniMax-M2$0.3$1.2—205kOct 27, 2025
GLM-4.6$0.55$2.2—205kSep 30, 2025
Qwen3 VL 235B A22B Instruct$0.3$1.5—131kSep 23, 2025
Qwen3 VL 235B A22B Thinking$0.98$3.95—131kSep 23, 2025
Qwen3 Next 80B A3B Thinking$0.3$2—262kSep 11, 2025
Qwen3-Next 80B-A3B Instruct$0.25$1—262kSep 11, 2025
Kimi-K2-Instruct-0905$1$3—262kSep 4, 2025
DeepSeek V3.1$0.27$1—131kAug 21, 2025
GLM-4.5V$0.6$1.8—66kAug 11, 2025
GLM-4.7-Flashfreefree—200kAug 8, 2025free
GPT OSS 120B$0.25$0.69—131kAug 5, 2025
GPT OSS 20B$0.1$0.5—131kAug 5, 2025
GLM-4.5$0.6$2.2—131kJul 28, 2025
GLM-4.5-Air$0.13$0.85—131kJul 28, 2025
Qwen3 235B A22B Thinking 2507$0.3$3—262kJul 25, 2025
Qwen3 Coder 480B A35B Instruct$2$2—262kJul 23, 2025
Qwen3 235B A22B Instruct 2507$0.855$2.565—262kJul 21, 2025
Kimi K2 Instruct$1$3—131kJul 14, 2025
DeepSeek R1 0528$3$5—164kMay 28, 2025
Qwen3 30B A3B$0.12$0.5—41kApr 28, 2025
Qwen3 235B-A22B$0.2$0.8—41kApr 1, 2025
Qwen3 32B$0.29$0.59—131kApr 1, 2025
Qwen3-Coder 30B-A3B Instruct$0.07$0.26—262kApr 1, 2025
DeepSeek V3 0324$0.27$1.12—164kMar 24, 2025
Gemma 3 12B IT$0.05$0.15—131kMar 12, 2025
Gemma 3 27B IT$0.08$0.16—131kMar 12, 2025
Gemma 3 4B IT$0.05$0.1—131kMar 12, 2025
DeepSeek-R1$0.7$2.5—64kJan 20, 2025
Qwen 3 Embedding 4B$0.01free—32kJan 1, 2025
Qwen 3 Embedding 8B$0.01free—32kJan 1, 2025
DeepSeek-V3$0.4$1.3—64kDec 26, 2024
Llama-3.3-70B-Instruct$0.59$0.79—131kDec 6, 2024
Qwen2.5 Coder 32B Instruct$0.06$0.2—131kNov 12, 2024
Llama 3.1 8B Instruct$0.06$0.06—131kJul 23, 2024