Skip to content

Highest Output-Speed Claude Sonnet 4 Inference Providers

Ranks providers by their recent typical output speed in tokens per second. Providers without enough recent data remain visible after ranked rows.

Amazon Bedrock currently ranks first at 50.0 tok/s via amazon-bedrock.

Provider options:
5
Ranked:
4
Metric:
Output speed

Highest output speed endpoint ranking

Highest Output-Speed Claude Sonnet 4 Inference Providers
RankProvider / routeOutput speedSpeed measurementsEndpoint details
#1Provider / route
Amazon Bedrockamazon-bedrock
Output speed50.0 tok/sSpeed measurements
500-token response
10.99 s
Response starts
0.99 s
Output speed
50.0 tok/s
Endpoint details
Input price
$3 / 1M tokens
Output price
$15 / 1M tokens
Uptime (30 min)
99.98%
Context
200K
#2Provider / route
Amazon Bedrockamazon-bedrock/eu-west-1
Output speed48.0 tok/sSpeed measurements
500-token response
12.05 s
Response starts
1.63 s
Output speed
48.0 tok/s
Endpoint details
Input price
$3 / 1M tokens
Output price
$15 / 1M tokens
Uptime (30 min)
Insufficient recent data
Context
200K
#3Provider / route
Google Vertexgoogle-vertex/global
Output speed29.0 tok/sSpeed measurements
500-token response
18.02 s
Response starts
0.78 s
Output speed
29.0 tok/s
Endpoint details
Input price
$3 / 1M tokens
Output price
$15 / 1M tokens
Uptime (30 min)
100.00%
Context
1M
#4Provider / route
Google Vertexgoogle-vertex/europe
Output speed29.0 tok/sSpeed measurements
500-token response
18.24 s
Response starts
0.99 s
Output speed
29.0 tok/s
Endpoint details
Input price
$3 / 1M tokens
Output price
$15 / 1M tokens
Uptime (30 min)
Insufficient recent data
Context
1M
Provider / route
Google Vertexgoogle-vertex
Output speedInsufficient recent dataSpeed measurements
500-token response
Insufficient recent data
Response starts
Insufficient recent data
Output speed
Insufficient recent data
Endpoint details
Input price
$3 / 1M tokens
Output price
$15 / 1M tokens
Uptime (30 min)
Insufficient recent data
Context
1M

Endpoint data fetched .

Claude Sonnet 4 endpoint guide

How to interpret the Highest Output-Speed Claude Sonnet 4 Inference Providers

4 of 5 Claude Sonnet 4 endpoints currently have the published data required for this ranking. Amazon Bedrock leads at 50.0 tok/s via amazon-bedrock. The table keeps unranked routes visible so missing measurements do not look like missing provider availability.

How generation throughput is ranked

The output-speed ranking compares recent median generated tokens per second. It favors routes that complete long generations quickly, while first-token latency remains a separate measure of how responsive the endpoint feels at the beginning.

Compare Amazon Bedrock with the next option

Amazon Bedrock currently ranks second at 48.0 tok/s. Compare that gap with input and output price, response-start time, output speed, 30-minute uptime, context length, and the exact route before deciding whether first place is meaningful for your workload.

Use the route, not only the provider name

Claude Sonnet 4 has 5 published provider options, and performance data is matched to each exact OpenRouter routing tag. Different quantization, context, regional deployment, or provider configuration can change price and behavior even when the underlying model name is identical.