Skip to content
Sovyron

Charm Hyper

23 modelsProvider docs

As of Oct 4, 2026, Charm Hyper lists 23 supported models in the Sovyron catalog, including DeepSeek V4.1 Flash, Kimi K2 Thinking, GLM-5.3, GLM-5.3-Flash and Qwen3.8 2.4T A95B — deepseek-flash, kimi-thinking, glm, glm-flash, qwen and ling families. Its metered rates span $0.157–$6.5328 per 1M tokens on a 3:1 input:output blend, and every price in the table is Charm Hyper's own, normalized to USD — open a model to compare it with the cheapest offer across all providers.

Supported models and pricing

23 of 23 models
Charm Hyper model prices in USD per 1M tokens, updated Oct 4, 2026
Model1M input1M output1M cache readContextReleased
DeepSeek V4.1 Flash$0.33$1.31$0.031.0MSep 10, 2026
Kimi K2 Thinking$0.6$2.5$0.3262kSep 2, 2026
GLM-5.3$1.5243$4.7907$0.28311.0MAug 28, 2026
GLM-5.3-Flash$0.1633$0.5444$0.03161.0MAug 26, 2026
Qwen3.8 2.4T A95B$2$6$0.251.0MAug 26, 2026
Qwen3.8 27B$0.5$3$0.11.0MAug 26, 2026
Qwen3.8 Flash$0.15$0.47$0.0161.0MAug 26, 2026
Inkling$1.0888$4.4096$0.18511.0MAug 15, 2026
DeepSeek V4 Pro 0813$1.4372$4.3116$0.04791.0MAug 14, 2026
DeepSeek V4 Flash 0731$0.44$1.32$0.0441.0MAug 2, 2026
MiniMax-M3$0.3266$1.3066$0.0642512kJul 30, 2026
Kimi K3$3.2664$16.332$0.32661.0MJul 27, 2026
Qwen3.7 Flash$0.2$0.8$0.041.0MJul 27, 2026
Qwen3.8 Max$2$6$0.251.0MJul 19, 2026
DeepSeek V4 Flash$0.2$0.4$0.041.0MJul 6, 2026
DeepSeek V4 Pro$2.4$4.8$0.21.0MJul 6, 2026
Kimi K2.7 Code$1.0344$4.3552$0.2069256kJul 3, 2026
GLM-5.2$1.5243$4.7907$0.15241.0MJun 30, 2026
Qwen3.7 Plus$1.2$4.8$0.241.0MJun 15, 2026
MiniMax-M2.7$0.484$1.852$0.242262kJun 5, 2026
Qwen3.7 Max$2.5$7.5$0.51.0MMay 28, 2026
Gemma 4 26B A4B IT$0.098$0.334$0.049256kApr 30, 2026
GPT OSS 120B$0.178$0.68$0.089131kApr 13, 2026