Skip to content
Sovyron

ai&

13 modelsProvider docs

As of Oct 4, 2026, ai& lists 13 supported models in the Sovyron catalog, including DeepSeek V4.1 Flash, GLM-5.3-Flash, GLM-5.3, Qwen3.8 27B and Motif 3 — deepseek-flash, glm-flash, glm, qwen, motif and kimi-k3 families. Its metered rates span $0.175–$5.375 per 1M tokens on a 3:1 input:output blend, and every price in the table is ai&'s own, normalized to USD — open a model to compare it with the cheapest offer across all providers.

Supported models and pricing

13 of 13 models
ai& model prices in USD per 1M tokens, updated Oct 4, 2026
Model1M input1M output1M cache readContextReleased
DeepSeek V4.1 Flash$0.3$0.6$0.021.0MSep 10, 2026
GLM-5.3-Flash$0.15$0.5$0.031.0MAug 26, 2026
GLM-5.3$1$4$0.31.0MAug 14, 2026
Qwen3.8 27B$0.4$3$0.2262kAug 14, 2026
Motif 3$0.5$2$0.2262kAug 7, 2026
Kimi K3$3$12.5$0.51.0MJul 16, 2026
GLM-5.2$1$4$0.31.0MJun 13, 2026
Kimi K2.7 Code$0.75$3.5$0.2262kJun 12, 2026
DeepSeek V4 Flash$0.15$0.25$0.081.0MApr 24, 2026
DeepSeek V4 Pro$1$2.5$0.251.0MApr 24, 2026
Qwen3.6 27B$0.32$3.2$0.2262kApr 22, 2026
Gemma 4 31B IT$0.2$0.5$0.05262kApr 2, 2026
GPT OSS 120B$0.15$0.6$0.08131kAug 5, 2025