Skip to content
ProviderBench home

Same-model provider benchmark

Amazon Bedrock vs CoreWeave: LLM provider comparison

Compare Amazon Bedrock and CoreWeave on 3 exact shared text models. ProviderBench keeps speed, price, and catalog coverage separate so naturally faster model catalogs cannot distort the result.

Amazon Bedrock

24 indexed models

Headquarters
United States
Server regions
eu-west-1 · Irelandus-east-1 · United States
Model types
24 text

CoreWeave

20 indexed models

Headquarters
United States
Server regions
United States
Model types
20 text

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

Amazon Bedrock

1.16× typical advantage

3 exact models with complete recent speed data

Lowest token cost

CoreWeave

$0.3122 / 1M

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

Most models available

Amazon Bedrock

24 models

Complete catalog coverage across all indexed modalities

Shared-model benchmark summary

MetricAmazon Bedrock(0)CoreWeave(0)
SpeedAmazon Bedrock5.09 sCoreWeave5.92 s
TTFTAmazon Bedrock0.37 sCoreWeave0.31 s
TPSAmazon Bedrock111.0 tok/sCoreWeave90.0 tok/s
UptimeAmazon Bedrock99.56%CoreWeave99.68%
BlendedAmazon Bedrock$0.3722 / 1MCoreWeave$0.3122 / 1M
Green value Better comparable resultRed value Worse comparable result

Visual comparison

Price and performance charts

Amazon BedrockCoreWeave
500-token response by shared model

Estimated seconds using recent median response-start and output-speed data. Lower is better.

Amazon Bedrock has the lower typical same-model response ratio across 3 measured models.

Blended token price by shared model

USD per 1 million tokens using a 1,000-input/500-output mix. Lower is better.

CoreWeave has the lower typical price ratio across 3 priced shared models.

Shared text models

3 exact models · newest first

ModelAmazon Bedrock(0)CoreWeave(0)
gpt-oss-120bWinner · CoreWeave
Amazon Bedrock
Speed— Best comparable value
5.09 s
TTFT— Worst comparable value
0.59 s
TPS— Best comparable value
111.0 tok/s
Uptime— Worst comparable value
99.56%
Context
131.1K
Route
amazon-bedrock
Blended— Worst comparable value
$0.3 / 1M
CoreWeave
Speed— Worst comparable value
5.92 s
TTFT— Best comparable value
0.36 s
TPS— Worst 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
gpt-oss-20bWinner · CoreWeave
Amazon Bedrock
Speed— Best comparable value
3.11 s
TTFT— Worst comparable value
0.35 s
TPS— Best comparable value
181.0 tok/s
Uptime— Worst comparable value
24.76%
Context
131.1K
Route
amazon-bedrock
Blended— Worst comparable value
$0.0967 / 1M
CoreWeave
Speed— Worst comparable value
4.18 s
TTFT— Best comparable value
0.28 s
TPS— Worst 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
Llama 3.1 70B InstructWinner · Amazon Bedrock
Amazon Bedrock
Speed— Worst comparable value
12.57 s
TTFT— Worst comparable value
0.37 s
TPS
41.0 tok/s
Uptime— Worst comparable value
99.92%
Context
131.1K
Route
amazon-bedrock
Blended— Best comparable value
$0.72 / 1M
CoreWeave
Speed— Best comparable value
12.50 s
TTFT— Best comparable value
0.31 s
TPS
41.0 tok/s
Uptime— Best comparable value
100.00%
Context
128K
Route
coreweave/bf16
Blended— Worst comparable value
$0.8 / 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 . Values use one deterministic route per provider and model; missing measurements remain visible as N/a.

Amazon Bedrock vs CoreWeave analysis

How Amazon Bedrock and CoreWeave compare for AI inference

Amazon Bedrock and CoreWeave share 3 indexed text models, including gpt-oss-120b, gpt-oss-20b, Llama 3.1 70B Instruct. Amazon Bedrock has the stronger typical response-time result on the directly measured set.

Same-model speed evidence

3 shared models currently have complete response-start and output-speed measurements on both providers. The speed comparison uses per-model ratios before taking the median, so naturally faster model catalogs do not improve the result.

Token pricing on one workload

3 shared models have complete input and output prices on both providers. Prices use the same 1,000-input/500-output-token mix and are normalized to one million tokens for readability.

Catalog and deployment differences

Amazon Bedrock has 24 indexed models and lists 2 published server regions; CoreWeave has 20 models and lists 1 region. Verify data residency, privacy terms, limits, and production latency directly before choosing.

Related same-model benchmarks

Compare with other providers

Explore qualified alternatives with the most shared measured models. Recommendations include comparisons for both Amazon Bedrock and CoreWeave.

Amazon Bedrock vs Google Vertex

11 shared model benchmarks

CoreWeave vs DeepInfra

16 shared model benchmarks

Amazon Bedrock vs Anthropic

10 shared model benchmarks

CoreWeave vs SiliconFlow

15 shared model benchmarks

Amazon Bedrock vs Azure

6 shared model benchmarks

CoreWeave vs NovitaAI

14 shared model benchmarks