Skip to content

Same-model provider benchmark

Anthropic vs Google Vertex: LLM provider comparison

Compare Anthropic and Google Vertex on 10 exact shared text models. ProviderBench keeps speed, price, and catalog coverage separate so naturally faster model catalogs cannot distort the result.

Anthropic

12 indexed models

Headquarters
United States
Server regions
N/a
Model types
12 text

Google Vertex

49 indexed models

Headquarters
United States
Server regions
europe-west1 · Belgiumeurope-west4 · NetherlandsGlobalus-central1 · United Statesus-east5 · United Statesus-south1 · United Statesus-west2 · United States
Model types
36 text, 6 image, 3 video, 2 embeddings, 1 speech, 1 transcription

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

1.22× typical advantage

10 exact models with complete recent speed data

Lowest token cost

Equal result

Tie

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

Most models available

49 models

Complete catalog coverage across all indexed modalities

Shared-model benchmark summary

MetricAnthropicGoogle Vertex
Typical 500-token response16.85 s13.21 s
Typical response start2.06 s1.62 s
Typical output speed33.0 tok/s50.0 tok/s
Blended token price$12.6 / 1M$12.6 / 1M
Typical route uptime99.87%99.80%

Visual comparison

Price and performance charts

AnthropicGoogle Vertex
500-token response by shared model

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

Google Vertex has the lower typical same-model response ratio across 10 measured models.

Blended token price by shared model

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

Neither provider has a clear token-price advantage.

Shared text models

10 exact models · newest first

ModelAnthropicGoogle Vertex
Claude Sonnet 5Winner · Google Vertex

anthropic/claude-sonnet-5

Anthropic
Blended price
$4.6667 / 1M
500-token response
12.21 s
Response starts
3.44 s
Output speed
57.0 tok/s
Route uptime
99.99%
Context
1M
Route
anthropic
Google Vertex
Blended price
$4.6667 / 1M
500-token response
10.86 s
Response starts
3.28 s
Output speed
66.0 tok/s
Route uptime
99.83%
Context
1M
Route
google-vertex/global
Claude Fable 5Winner · Google Vertex

anthropic/claude-fable-5

Anthropic
Blended price
$23.3333 / 1M
500-token response
25.34 s
Response starts
5.34 s
Output speed
25.0 tok/s
Route uptime
94.79%
Context
1M
Route
anthropic
Google Vertex
Blended price
$23.3333 / 1M
500-token response
14.47 s
Response starts
4.47 s
Output speed
50.0 tok/s
Route uptime
99.62%
Context
1M
Route
google-vertex/global
Claude Opus 4.8Winner · Anthropic

anthropic/claude-opus-4.8

Anthropic
Blended price
$11.6667 / 1M
500-token response
12.27 s
Response starts
2.06 s
Output speed
49.0 tok/s
Route uptime
99.87%
Context
1M
Route
anthropic
Google Vertex
Blended price
$11.6667 / 1M
500-token response
14.32 s
Response starts
4.71 s
Output speed
52.0 tok/s
Route uptime
100.00%
Context
1M
Route
google-vertex/global
Claude Opus 4.7Winner · Google Vertex

anthropic/claude-opus-4.7

Anthropic
Blended price
$11.6667 / 1M
500-token response
12.69 s
Response starts
2.06 s
Output speed
47.0 tok/s
Route uptime
N/a
Context
1M
Route
anthropic
Google Vertex
Blended price
$11.6667 / 1M
500-token response
8.40 s
Response starts
1.05 s
Output speed
68.0 tok/s
Route uptime
99.90%
Context
1M
Route
google-vertex/global
Claude Sonnet 4.6Winner · Google Vertex

anthropic/claude-sonnet-4.6

Anthropic
Blended price
$7 / 1M
500-token response
18.73 s
Response starts
1.49 s
Output speed
29.0 tok/s
Route uptime
N/a
Context
1M
Route
anthropic
Google Vertex
Blended price
$7 / 1M
500-token response
11.26 s
Response starts
1.26 s
Output speed
50.0 tok/s
Route uptime
100.00%
Context
1M
Route
google-vertex/global
Claude Opus 4.6Winner · Google Vertex

anthropic/claude-opus-4.6

Anthropic
Blended price
$11.6667 / 1M
500-token response
21.99 s
Response starts
3.47 s
Output speed
27.0 tok/s
Route uptime
N/a
Context
1M
Route
anthropic
Google Vertex
Blended price
$11.6667 / 1M
500-token response
16.73 s
Response starts
2.02 s
Output speed
34.0 tok/s
Route uptime
100.00%
Context
1M
Route
google-vertex/global
Claude Opus 4.5Winner · Google Vertex

anthropic/claude-opus-4.5

Anthropic
Blended price
$11.6667 / 1M
500-token response
17.36 s
Response starts
1.73 s
Output speed
32.0 tok/s
Route uptime
N/a
Context
200K
Route
anthropic
Google Vertex
Blended price
$11.6667 / 1M
500-token response
12.10 s
Response starts
0.99 s
Output speed
45.0 tok/s
Route uptime
99.94%
Context
200K
Route
google-vertex/global
Claude Haiku 4.5Winner · Google Vertex

anthropic/claude-haiku-4.5

Anthropic
Blended price
$2.3333 / 1M
500-token response
7.61 s
Response starts
0.95 s
Output speed
75.0 tok/s
Route uptime
99.31%
Context
200K
Route
anthropic
Google Vertex
Blended price
$2.3333 / 1M
500-token response
7.28 s
Response starts
0.62 s
Output speed
75.0 tok/s
Route uptime
99.76%
Context
200K
Route
google-vertex/global
Claude Sonnet 4.5Winner · Google Vertex

anthropic/claude-sonnet-4.5

Anthropic
Blended price
$7 / 1M
500-token response
16.35 s
Response starts
1.64 s
Output speed
34.0 tok/s
Route uptime
100.00%
Context
1M
Route
anthropic
Google Vertex
Blended price
$7 / 1M
500-token response
14.98 s
Response starts
1.47 s
Output speed
37.0 tok/s
Route uptime
99.80%
Context
1M
Route
google-vertex/global
Claude Opus 4.1Winner · Anthropic

anthropic/claude-opus-4.1

Anthropic
Blended price
$35 / 1M
500-token response
24.08 s
Response starts
2.34 s
Output speed
23.0 tok/s
Route uptime
N/a
Context
200K
Route
anthropic
Google Vertex
Blended price
$35 / 1M
500-token response
24.51 s
Response starts
1.78 s
Output speed
22.0 tok/s
Route uptime
N/a
Context
200K
Route
google-vertex/global

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.

Anthropic vs Google Vertex analysis

How Anthropic and Google Vertex compare for AI inference

Anthropic and Google Vertex share 10 indexed text models, including Claude Sonnet 5, Claude Fable 5, Claude Opus 4.8, Claude Opus 4.7, Claude Sonnet 4.6. Google Vertex has the stronger typical response-time result on the directly measured set.

Same-model speed evidence

10 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

10 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

Anthropic has 12 indexed models and lists no published server regions; Google Vertex has 49 models and lists 7 regions. Verify data residency, privacy terms, limits, and production latency directly before choosing.