Skip to content
Sovyron

Keln

13 modelsProvider docs

As of Nov 22, 2026, Keln lists 13 supported models in the Sovyron catalog, including Kimi K3.1 Pro, MiniMax-M3.1-Flash, DeepSeek V4.1 Flash 1017, DeepSeek V4.1 Flash and GLM-5.3-Flash across the kimi-pro, minimax-m-flash, deepseek-flash, glm-flash, glm and qwen families. The cheapest rate in the table is Gemma 4 31B IT at $0.46 per 1M output tokens, the priciest Kimi K3.1 Pro at $10. On a 3:1 input:output blend the metered rates span $0.2275–$4 per 1M tokens, and every price is Keln'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

13 of 13 models
Keln model prices in USD per 1M tokens, updated Nov 22, 2026
Model1M input1M output1M cache readContextReleased
Kimi K3.1 Pro$2$10$0.241.0MOct 23, 2026
MiniMax-M3.1-Flash$0.15$0.6$0.0181.0MOct 19, 2026
DeepSeek V4.1 Flash 1017$0.3$1.2$0.011.0MOct 17, 2026
DeepSeek V4.1 Flash$0.3$1.2$0.031.0MSep 10, 2026
GLM-5.3-Flash$0.15$0.5$0.051.0MAug 26, 2026
GLM-5.3$1.4$4.4$0.291.0MAug 14, 2026
Qwen3.8 27B$0.5$3.2$0.151.0MAug 14, 2026
DeepSeek V4 Pro 0813$1.32$3.96$0.151.0MAug 13, 2026
Qwen3.8 2.4T A95B$2.5$6.25$0.31.0MAug 12, 2026
GLM-5.2$1.4$4.4$0.281.0MJun 13, 2026
Nemotron 3 Ultra 550B A55B$0.8$3$0.14262kJun 4, 2026
Gemma 4 31B IT$0.15$0.46$0.15262kApr 2, 2026
GPT OSS 120B$0.15$0.6$0.1131kAug 5, 2025