Skip to content
Sovyron

TensorX

25 modelsProvider docs

As of Oct 4, 2026, TensorX lists 25 supported models in the Sovyron catalog, including DeepSeek V4.1 Flash, Qwen3.8 Flash Next, GLM-5.3-Flash, GLM-5.3 and Qwen3.8 27B — deepseek-flash, qwen, glm-flash, glm, deepseek-thinking and kimi-k3 families. Its metered rates span $0.1625–$6 per 1M tokens on a 3:1 input:output blend, and every price in the table is TensorX's own, normalized to USD — open a model to compare it with the cheapest offer across all providers.

Supported models and pricing

25 of 25 models
TensorX model prices in USD per 1M tokens, updated Oct 4, 2026
Model1M input1M output1M cache readContextReleased
DeepSeek V4.1 Flash$0.5$1.5$0.131.0MSep 10, 2026
Qwen3.8 Flash Next$0.2$0.5$0.05262kAug 27, 2026
GLM-5.3-Flash$0.2$0.5$0.051.0MAug 26, 2026
GLM-5.3$1.75$4.5$0.441.0MAug 14, 2026
Qwen3.8 27B$0.4$2.4$0.1262kAug 14, 2026
DeepSeek V4 Pro 0813$2$4$0.51.0MAug 12, 2026
Qwen3.8 2.4T A95B$2.5$6$0.63262kAug 12, 2026
DeepSeek V4 Flash 0731$0.25$0.3$0.061.0MJul 31, 2026
Kimi K3$3$15$0.751.0MJul 16, 2026
GLM-5.2$1.5$4.5$0.3751.0MJun 13, 2026
Kimi K2.7 Code$1.25$4.5$0.3125262kJun 12, 2026
MiniMax-M3$0.4$2$0.11.0MJun 1, 2026
DeepSeek V4 Pro$1.75$3.5$0.43751.0MApr 24, 2026
Kimi K2.6$1$4$0.25262kApr 21, 2026
GLM-5.1$1.4$4.4$0.35203kApr 7, 2026
GLM-5V-Turbo$1.2$4$0.3203kApr 1, 2026
GLM-5-Turbo$1.2$4$0.3203kMar 16, 2026
Qwen3.5 122B-A10B$0.5$3.5$0.125262kFeb 23, 2026
Qwen3.5 9B$0.15$0.2$0.0375262kFeb 23, 2026
GLM-5$1$3.2$0.25203kFeb 12, 2026
MiniMax-M2.5$0.3$1.2$0.075197kFeb 12, 2026
Kimi K2.5$0.5$2.8$0.125262kJan 1, 2026
DeepSeek V3.2$0.3$0.5$0.075164kDec 1, 2025
Qwen3 235B-A22B-2507$0.072$0.464$0.018131kJul 21, 2025
DeepSeek R1 0528$0.66$2.6$0.165164kMay 28, 2025