Skip to content
Sovyron

Adzuki AI

12 modelsProvider docs

As of Nov 22, 2026, Adzuki AI lists 12 supported models in the Sovyron catalog, including Kimi K3.1 Pro, DeepSeek V4.1 Flash, GLM-5.3-Flash, GLM-5.3 and Qwen3.8 Max across the kimi-pro, deepseek-flash, glm-flash, glm, qwen-max and kimi families. The cheapest rate in the table is MiMo-V2.5 at $0.5714 per 1M output tokens, the priciest Kimi K3 at $28.5714. On a 3:1 input:output blend the metered rates span $0.3571–$11.4286 per 1M tokens, and every price is Adzuki 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

12 of 12 models
Adzuki AI model prices in USD per 1M tokens, updated Nov 22, 2026
Model1M input1M output1M cache readContextReleased
Kimi K3.1 Pro$3.7143$19.4286$0.37141.0MOct 23, 2026
DeepSeek V4.1 Flash$0.5714$2.2857$0.01141.0MSep 10, 2026
GLM-5.3-Flash$0.2286$0.8$0.06571.0MAug 26, 2026
GLM-5.3$2.2857$8$0.57141.0MAug 14, 2026
Qwen3.8 Max$3.4286$10.2857$0.42861.0MAug 3, 2026
Kimi K3$5.7143$28.5714$0.57141.0MJul 16, 2026
Seed 2.1 Pro$1.7143$8.5714$0.34291.0MJun 23, 2026
MiniMax-M3$1.2$4.8$0.241.0MJun 1, 2026
DeepSeek V4 Pro$2.5714$7.7143$0.08571.0MApr 24, 2026
MiMo-V2.5$0.2857$0.5714$0.00571.0MApr 22, 2026
MiMo-V2.5-Pro$0.8571$1.7143$0.00711.0MApr 22, 2026
Seed 2.0 Lite$0.1714$1.0286$0.0343256kFeb 14, 2026