Skip to content
Sovyron

CoreWeave

29 modelsProvider docs

As of Oct 4, 2026, CoreWeave lists 29 supported models in the Sovyron catalog, including DeepSeek V4.1 Flash, GLM-5.3-Flash, Granite 4.2 8B, Qwen3.8 27B and DeepSeek V4 Pro 0813 — deepseek-flash, glm-flash, granite, qwen, deepseek-thinking and nemotron families. Its metered rates span $0.055–$1.9725 per 1M tokens on a 3:1 input:output blend, and every price in the table is CoreWeave's own, normalized to USD — open a model to compare it with the cheapest offer across all providers.

Supported models and pricing

29 of 29 models
CoreWeave model prices in USD per 1M tokens, updated Oct 4, 2026
Model1M input1M output1M cache readContextReleased
DeepSeek V4.1 Flash$0.2$0.65$0.031.0MSep 10, 2026
GLM-5.3-Flash$0.15$0.5$0.051.0MAug 26, 2026
Granite 4.2 8B$0.1$0.15$0.05131kAug 24, 2026
Qwen3.8 27B$0.4$3$0.15262kAug 14, 2026
DeepSeek V4 Pro 0813$1.31$3.96$0.0441.0MAug 13, 2026
Nemotron 3.5 Lightning$0.07$0.2$0.04262kAug 11, 2026
DeepSeek V4 Flash 0731$0.13$0.28$0.07262kJul 31, 2026
GLM-5.2$0.76$2.42$0.141.0MJun 16, 2026
Kimi K2.7 Code$0.71$3.5$0.15262kJun 12, 2026
MiniMax-M3$0.23$0.96$0.05262kJun 12, 2026
Nemotron 3 Ultra$0.5$2.15$0.1262kJun 4, 2026
Mellum2 12B A2.5B$0.05$0.1$0.05131kJun 1, 2026
Granite 4.1 8B$0.05$0.1$0.05131kApr 29, 2026
DeepSeek V4 Flash$0.14$0.28$0.071.0MApr 24, 2026
DeepSeek V4 Pro$1.15$2.55$0.21.0MApr 24, 2026
Qwen3.6 27B$0.6$3.6$0.12262kApr 22, 2026
Kimi K2.6$0.65$3.41$0.15262kApr 20, 2026
Qwen3.6 35B-A3B$0.25$1.25$0.25262kApr 15, 2026
Gemma 4 26B A4B$0.1$0.3$0.05262kApr 2, 2026
Gemma 4 31B$0.1$0.34$0.1262kApr 2, 2026
Qwen3.5 35B-A3B$0.25$1.25$0.25262kFeb 24, 2026
DeepSeek V3.1$0.55$1.65$0.55161kAug 21, 2025
GPT OSS 120B$0.03$0.17$0.03131kAug 5, 2025
GPT OSS 20B$0.03$0.13$0.03131kAug 5, 2025
Qwen3 30B A3B Instruct 2507$0.1$0.3$0.1262kJul 29, 2025
Qwen3 14B Instruct$0.05$0.22$0.0533kApr 29, 2025
Llama 3.3 70B$0.71$0.71$0.71128kDec 1, 2024
Llama 3.1 70B$0.8$0.8$0.8131kJul 23, 2024
Llama 3.1 8B$0.22$0.22$0.22131kJul 23, 2024