---
id: "coreweave"
site: "coreweave.com"
headquarters: "US"
gateways: ["openrouter"]
models: 30
endpoints: 32
tokens_week: 200262147561
token_share: "1.3%"
rank: 15
cheapest_on: "3 of 31 shared models"
cheaper_than: "67% of offers at the median"
vs_card: "23% off the card price at the median over 13 models"
cache_hit: "80.6%"
uptime_1d: 98.9000
latency_p50_ms: 386
tokens_per_second: 103
trains_on_some: false
retains_on_some: false
quantization: "fp8 (12), bf16 (8), fp4 (6), nvfp4 (4), fp16 (1), int4 (1)"
---
# CoreWeave

`deepseek/deepseek-chat-v3.1`, `deepseek/deepseek-v4.1-flash`, `deepseek/deepseek-v4.1-flash-1017`, `deepseek/deepseek-v4-flash`, `deepseek/deepseek-v4-flash-0731`, `deepseek/deepseek-v4-pro`, `deepseek/deepseek-v4-pro-0813`, `google/gemma-4-26b-a4b-it`, `google/gemma-4-31b-it`, `ibm-granite/granite-4.1-8b`, `ibm-granite/granite-4.2-8b`, `meta-llama/llama-3.1-70b-instruct`, `meta-llama/llama-3.1-8b-instruct`, `meta-llama/llama-3.3-70b-instruct`, `minimax/minimax-m3`, `moonshotai/kimi-k2.6`, `moonshotai/kimi-k2.7-code`, `nvidia/nemotron-3.5-lightning`, `nvidia/nemotron-3.5-super-vl`, `openai/gpt-oss-120b`, `openai/gpt-oss-20b`, `qwen/qwen3-30b-a3b-instruct-2507`, `qwen/qwen3.5-35b-a3b`, `qwen/qwen3.6-27b`, `qwen/qwen3.6-35b-a3b`, `qwen/qwen3.8-27b`, `reflection/beam-1.0-501b-a23b`, `z-ai/glm-5.2`, `z-ai/glm-5.3`, `z-ai/glm-5.3-flash`