Baseten vs CoreWeave: 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

CCoreWeave

1.98× typical advantage

5 exact models with complete recent speed data

Lowest token cost

CCoreWeave

$1.8307 / 1M

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

Most models available

CCoreWeave

20 models

Complete catalog coverage across all indexed modalities

Shared-model benchmark summary

Metric	BBaseten☆☆☆☆☆(0)	CCoreWeave☆☆☆☆☆(0)
Speed	Baseten8.69 s	CoreWeave5.92 s
TTFT	Baseten1.22 s	CoreWeave0.50 s
TPS	Baseten66.0 tok/s	CoreWeave90.0 tok/s
Uptime	Baseten99.10%	CoreWeave99.82%
Blended	Baseten$1.844 / 1M	CoreWeave$1.8307 / 1M

Model	BBaseten☆☆☆☆☆(0)	CCoreWeave☆☆☆☆☆(0)
ZA GLM 5.2Winner · Baseten	Baseten Speed— Best comparable value 13.22 s TTFT— Worst comparable value 2.11 s TPS— Best comparable value 45.0 tok/s Uptime— Best comparable value 100.00% Context 524.3K Route baseten/fp8 Blended— Worst comparable value $2.4 / 1M	CoreWeave Speed— Worst comparable value 20.46 s TTFT— Best comparable value 1.94 s TPS— Worst comparable value 27.0 tok/s Uptime— Worst comparable value 99.96% Context 262.1K Route coreweave/fp4 Blended— Best comparable value $2.3933 / 1M
D DeepSeek V4 ProWinner · Baseten	Baseten Speed— Best comparable value 8.38 s TTFT— Best comparable value 0.81 s TPS— Best comparable value 66.0 tok/s Uptime— Worst comparable value 98.46% Context 262.1K Route baseten/fp4 Blended $2.32 / 1M	CoreWeave Speed— Worst comparable value 64.00 s TTFT— Worst comparable value 1.50 s TPS— Worst comparable value 8.0 tok/s Uptime— Best comparable value 98.59% Context 1M Route coreweave/fp8 Blended $2.32 / 1M
M Kimi K2.6Winner · CoreWeave	Baseten Speed— Worst comparable value 6.71 s TTFT— Worst comparable value 2.77 s TPS— Worst comparable value 127.0 tok/s Uptime N/a Context 262K Route baseten/fp4 Blended $1.9667 / 1M	CoreWeave Speed— Best comparable value 3.30 s TTFT— Best comparable value 0.34 s TPS— Best comparable value 169.0 tok/s Uptime 99.89% Context 262.1K Route coreweave/fp4 Blended $1.9667 / 1M
ZA GLM 5.1Winner · CoreWeave	Baseten Speed— Worst comparable value 8.69 s TTFT— Worst comparable value 1.22 s TPS— Worst comparable value 67.0 tok/s Uptime— Worst comparable value 89.84% Context 202.8K Route baseten/fp4 Blended— Best comparable value $2.3 / 1M	CoreWeave Speed— Best comparable value 4.38 s TTFT— Best comparable value 0.50 s TPS— Best comparable value 129.0 tok/s Uptime— Best comparable value 100.00% Context 202.8K Route coreweave/fp8 Blended— Worst comparable value $2.4 / 1M
O gpt-oss-120bWinner · CoreWeave	Baseten Speed— Worst comparable value 15.61 s TTFT— Worst comparable value 0.46 s TPS— Worst comparable value 33.0 tok/s Uptime— Best comparable value 99.73% Context 128.1K Route baseten/fp4 Blended— Worst comparable value $0.2333 / 1M	CoreWeave Speed— Best comparable value 5.92 s TTFT— Best comparable value 0.36 s TPS— Best comparable value 90.0 tok/s Uptime— Worst comparable value 99.68% Context 131.1K Route coreweave/fp4 Blended— Best comparable value $0.0733 / 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.