Skip to content
ProviderBench home

Same-model provider benchmark

Google Vertex vs Together: LLM provider comparison

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

This pair has fewer than three complete same-model speed measurements. The available catalog comparison remains visible, but the page is excluded from search indexing and no speed winner is estimated.

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

Together

19 indexed models

Headquarters
United States
Server regions
N/a
Model types
17 text, 2 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

Not enough comparable data.

N/a

2 exact models with complete recent speed data

Lowest token cost

Google Vertex

$0.3433 / 1M

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

Most models available

Google Vertex

49 models

Complete catalog coverage across all indexed modalities

Shared-model benchmark summary

MetricGoogle Vertex(0)Together(0)
Typical 500-token response9.99 s11.05 s
Typical response start0.68 s0.56 s
Typical output speed56.5 tok/s48.0 tok/s
Blended token price$0.3433 / 1M$0.48 / 1M
Typical route uptime98.70%97.95%

Visual comparison

Price and performance charts

Google VertexTogether
500-token response by shared model

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

Neither provider has a clear response-time advantage.

Blended token price by shared model

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

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

Shared text models

3 exact models · newest first

ModelGoogle Vertex(0)Together(0)
gpt-oss-120bWinner · Google Vertex

openai/gpt-oss-120b

Google Vertex
Blended price
$0.18 / 1M
500-token response
12.44 s
Response starts
1.08 s
Output speed
44.0 tok/s
Route uptime
97.39%
Context
131.1K
Route
google-vertex/global
Together
Blended price
$0.3 / 1M
500-token response
9.95 s
Response starts
0.33 s
Output speed
52.0 tok/s
Route uptime
96.97%
Context
131.1K
Route
together
gpt-oss-20b

openai/gpt-oss-20b

Google Vertex
Blended price
$0.13 / 1M
500-token response
12.99 s
Response starts
6.74 s
Output speed
80.0 tok/s
Route uptime
N/a
Context
131.1K
Route
google-vertex/us-central1
Together
Blended price
$0.1 / 1M
500-token response
N/a
Response starts
N/a
Output speed
N/a
Route uptime
0.23%
Context
131.1K
Route
together
Llama 3.3 70B InstructWinner · Google Vertex

meta-llama/llama-3.3-70b-instruct

Google Vertex
Blended price
$0.72 / 1M
500-token response
7.53 s
Response starts
0.28 s
Output speed
69.0 tok/s
Route uptime
100.00%
Context
128K
Route
google-vertex
Together
Blended price
$1.04 / 1M
500-token response
12.15 s
Response starts
0.78 s
Output speed
44.0 tok/s
Route uptime
98.94%
Context
131.1K
Route
together/fp8

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.

Google Vertex vs Together analysis

How Google Vertex and Together compare for AI inference

Google Vertex and Together share 3 indexed text models, including gpt-oss-120b, gpt-oss-20b, Llama 3.3 70B Instruct. There is not enough paired speed data to name a response-time winner.

Same-model speed evidence

2 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

Google Vertex has 49 indexed models and lists 7 published server regions; Together has 19 models and lists no regions. 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 Google Vertex and Together.

Google Vertex vs NovitaAI

14 shared model benchmarks

Together vs DeepInfra

12 shared model benchmarks

Google Vertex vs Amazon Bedrock

12 shared model benchmarks

Together vs Parasail

9 shared model benchmarks

Google Vertex vs Anthropic

10 shared model benchmarks

Together vs Venice

8 shared model benchmarks