CoreWeave vs Google Vertex: LLM provider comparison

At a glance

Metric winners

There is no overall score. Each winner answers one specific question using only directly comparable data.

Fastest on shared models

GVGoogle Vertex

1.24× typical advantage

5 exact models with complete recent speed data

Lowest token cost

GVGoogle Vertex

$0.5487 / 1M

5 exact models using a 1K-input/500-output mix

Most models available

GVGoogle Vertex

51 models

Complete catalog coverage across all indexed modalities

Shared-model benchmark summary

Metric	CCoreWeave☆☆☆☆☆(0)	GVGoogle Vertex☆☆☆☆☆(0)
Speed	CoreWeave9.06 s	Google Vertex7.36 s
TTFT	CoreWeave0.29 s	Google Vertex0.56 s
TPS	CoreWeave57.0 tok/s	Google Vertex74.0 tok/s
Uptime	CoreWeave99.84%	Google Vertex97.80%
Blended	CoreWeave$0.586 / 1M	Google Vertex$0.5487 / 1M

Model	CCoreWeave☆☆☆☆☆(0)	GVGoogle Vertex☆☆☆☆☆(0)
D DeepSeek V3.1Winner · Google Vertex	CoreWeave Speed— Worst comparable value 9.97 s TTFT— Best comparable value 0.35 s TPS— Worst comparable value 52.0 tok/s Uptime— Best comparable value 100.00% Context 161K Route coreweave/fp8 Blended— Best comparable value $0.9167 / 1M	Google Vertex Speed— Best comparable value 7.23 s TTFT— Worst comparable value 0.82 s TPS— Best comparable value 78.0 tok/s Uptime— Worst comparable value 96.26% Context 163.8K Route google-vertex/us-west2 Blended— Worst comparable value $0.9667 / 1M
O gpt-oss-120bWinner · CoreWeave	CoreWeave Speed— Best comparable value 5.92 s TTFT— Best comparable value 0.36 s TPS— Best comparable value 90.0 tok/s Uptime— Best comparable value 99.68% Context 131.1K Route coreweave/fp4 Blended— Best comparable value $0.0733 / 1M	Google Vertex Speed— Worst comparable value 7.36 s TTFT— Worst comparable value 0.51 s TPS— Worst comparable value 73.0 tok/s Uptime— Worst comparable value 99.34% Context 131.1K Route google-vertex/global Blended— Worst comparable value $0.18 / 1M
O gpt-oss-20bWinner · CoreWeave	CoreWeave Speed— Best comparable value 4.18 s TTFT— Best comparable value 0.28 s TPS— Best comparable value 128.0 tok/s Uptime— Best comparable value 87.61% Context 131.1K Route coreweave/fp4 Blended— Best comparable value $0.0633 / 1M	Google Vertex Speed— Worst comparable value 7.51 s TTFT— Worst comparable value 2.08 s TPS— Worst comparable value 92.0 tok/s Uptime— Worst comparable value 49.35% Context 131.1K Route google-vertex/us-central1 Blended— Worst comparable value $0.13 / 1M
Q Qwen3 Coder 480B A35BWinner · Google Vertex	CoreWeave Speed— Worst comparable value 9.06 s TTFT— Best comparable value 0.29 s TPS— Worst comparable value 57.0 tok/s Uptime N/a Context 262.1K Route coreweave/bf16 Blended— Worst comparable value $1.1667 / 1M	Google Vertex Speed— Best comparable value 7.32 s TTFT— Worst comparable value 0.56 s TPS— Best comparable value 74.0 tok/s Uptime 100.00% Context 262.1K Route google-vertex/us-south1 Blended— Best comparable value $0.7467 / 1M
ML Llama 3.3 70B InstructWinner · Google Vertex	CoreWeave Speed— Worst comparable value 18.01 s TTFT— Best comparable value 0.15 s TPS— Worst comparable value 28.0 tok/s Uptime— Best comparable value 100.00% Context 128K Route coreweave/fp16 Blended— Best comparable value $0.71 / 1M	Google Vertex Speed— Best comparable value 7.75 s TTFT— Worst comparable value 0.28 s TPS— Best comparable value 67.0 tok/s Uptime— Worst comparable value 99.71% Context 128K Route google-vertex Blended— Worst comparable value $0.72 / 1M

A per-model winner combines blended price and estimated 500-token response time with equal proportional weight. Ties and rows missing either measurement receive no badge. Comparison data calculated Jul 24, 2026, 6:19 PM UTC. Values use one deterministic route per provider and model; missing measurements remain visible as N/a.