Inference provider

CoreWeave

Headquarters: US · US

22

models

22

endpoints

CoreWeave website preview
CoreWeave website

Catalogue

Available models

ModelEndpointContextInput /MOutput /MCached input /MCache write /MUptime 1d
DeepSeek V3.1coreweave/fp8161K$0.55$1.65$0.55—100.00%
DeepSeek V4 Flash 0731coreweave/fp8262K$0.13$0.28$0.07—100.00%
DeepSeek V4 Pro 0813coreweave/fp81.0M$1.31$3.96$0.04—100.00%
DeepSeek V4.1 Flashcoreweave/fp81.0M$0.15$0.65$0.006—99.79%
GLM 5.2coreweave/fp41.0M$0.62$2.42$0.14—100.00%
GLM 5.3 Flashcoreweave/nvfp41.0M$0.15$0.50$0.03—97.36%
Gemma 4 26B A4Bcoreweave/bf16262K$0.10$0.30$0.05—100.00%
Gemma 4 31Bcoreweave/fp4262K$0.10$0.34$0.10—100.00%
Granite 4.2 8Bcoreweave/bf16131K$0.10$0.15$0.05—100.00%
Kimi K2.6coreweave/fp4262K$0.65$3.41$0.15—100.00%
Kimi K2.7 Codecoreweave/int4262K$0.71$3.50$0.15—100.00%
Llama 3.1 8B Instructcoreweave/bf16131K$0.22$0.22$0.22—100.00%
Llama 3.3 70B Instructcoreweave/fp16128K$0.71$0.71$0.71—100.00%
MiniMax M3coreweave/fp4262K$0.23$0.96$0.05—100.00%
Nemotron 3.5 Lightningcoreweave/bf16262K$0.07$0.20$0.04—100.00%
Qwen3.6 35B A3Bcoreweave/fp8262K$0.25$1.25$0.25—100.00%
Qwen3.8 27Bcoreweave/fp8262K$0.40$3.00$0.15—99.78%
gpt-oss-120bcoreweave/fp4131K$0.03$0.17$0.03—99.79%
gpt-oss-20bcoreweave/fp4131K$0.03$0.13$0.03—100.00%