Skip to content
Sovyron

Doubleword

18 modelsProvider docs

As of Nov 22, 2026, Doubleword lists 18 supported models in the Sovyron catalog, including Kimi K3.1 Pro, DeepSeek V4.1 Flash 1017, Muse Spark Open, DeepSeek V4.1 Flash and GLM-5.3-Flash across the kimi-pro, deepseek-flash, muse-spark, glm-flash, glm and qwen families. The cheapest rate in the table is DeepSeek V4 Flash 0731 at $0.18 per 1M output tokens, the priciest Kimi K3 at $15. On a 3:1 input:output blend the metered rates span $0.1125–$6 per 1M tokens, and every price is Doubleword'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

18 of 18 models
Doubleword model prices in USD per 1M tokens, updated Nov 22, 2026
Model1M input1M output1M cache readContextReleased
Kimi K3.1 Pro$2$10—1.0MOct 23, 2026
DeepSeek V4.1 Flash 1017$0.15$0.6$0.0031.0MOct 17, 2026
Muse Spark Open$1.25$4.25—1.0MOct 15, 2026
DeepSeek V4.1 Flash$0.15$0.6$0.0031.0MSep 10, 2026
GLM-5.3-Flash$0.15$0.5$0.031.0MAug 26, 2026
GLM-5.3$1.4$4.4$0.281.0MAug 14, 2026
Qwen3.8 27B$0.45$3$0.045262kAug 14, 2026
DeepSeek V4 Pro 0813$1.32$3.96$0.1321.0MAug 13, 2026
Muse Glimmer 30B$0.11$0.32$0.0132131kAug 10, 2026
DeepSeek V4 Flash 0731$0.09$0.18$0.0181.0MJul 31, 2026
Kimi K3$3$15$0.31.0MJul 16, 2026
GLM-5.2$0.93$3$0.1861.0MJun 13, 2026
Nemotron 3 Ultra 550B A55B$0.5$2.2$0.1251.0MJun 4, 2026
Qwen3.6 35B-A3B$0.14$1$0.14262kApr 17, 2026
Gemma 4 31B IT$0.12$0.35$0.12262kApr 2, 2026
Qwen3.5 35B A3B dottxt$0.35$1.2$0.2262kFeb 23, 2026
Qwen3 VL 235B A22B Instruct$0.21$1.9$0.1155131kSep 23, 2025
Qwen3 Embedding 8B———33kJun 5, 2025