Skip to content
Sovyron

HPC-AI

9 modelsProvider docs

As of Nov 22, 2026, HPC-AI lists 9 supported models in the Sovyron catalog, including GLM-5.2, Kimi K2.7 Code, DeepSeek V4 Flash, DeepSeek V4 Pro and GPT-5.5 across the glm, kimi-code, deepseek-flash, deepseek-pro, gpt and claude-opus families. The cheapest rate in the table is DeepSeek V4 Flash at $0.28 per 1M output tokens, the priciest GPT-5.5 at $30. On a 3:1 input:output blend the metered rates span $0.175–$11.25 per 1M tokens, and every price is HPC-AI's own, normalized to USD. Offer mix: metered per-token rates only, with no free-tier or subscription offers in the catalog. Open a model to compare it with the cheapest offer across all providers.

Supported models and pricing

9 of 9 models
HPC-AI model prices in USD per 1M tokens, updated Nov 22, 2026
Model1M input1M output1M cache readContextReleased
GLM-5.2$1.4$4.4$0.261.0MJun 13, 2026
Kimi K2.7 Code$0.95$4$0.19256kJun 12, 2026
DeepSeek V4 Flash$0.14$0.28$0.0281.0MApr 24, 2026
DeepSeek V4 Pro$1.74$3.48$0.1451.0MApr 24, 2026
GPT-5.5$5$30$0.51.1MApr 23, 2026
Claude Opus 4.7$5$25$0.51.0MApr 16, 2026
GLM-5.1$0.615$2.46$0.133202kApr 7, 2026
MiniMax-M2.5$0.3$1.2$0.03196kFeb 12, 2026
Kimi K2.5$0.6$3$0.1256kJan 27, 2026