Amazon Bedrock
23 indexed models
- Headquarters
United States- Server regions
eu-west-1 · Irelandus-east-1 · United States- Model types
- 23 text
Same-model provider benchmark
Amazon Bedrock vs Google Vertex: LLM provider comparison
Compare Amazon Bedrock and Google Vertex on 13 exact shared text models. ProviderBench keeps speed, price, and catalog coverage separate so naturally faster model catalogs cannot distort the result.
Google Vertex
49 indexed models
- Headquarters
- United States
- Server regions
europe-west1 · Belgium
europe-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
1.21× typical advantage
12 exact models with complete recent speed data
Lowest token cost
$10.2546 / 1M
13 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
| Metric | Amazon Bedrock | Google Vertex |
|---|---|---|
| Typical 500-token response | 14.43 s | 13.21 s |
| Typical response start | 1.66 s | 1.62 s |
| Typical output speed | 41.5 tok/s | 50.0 tok/s |
| Blended token price | $10.2613 / 1M | $10.2546 / 1M |
| Typical route uptime | 99.93% | 99.90% |
Visual comparison
Price and performance charts
Amazon BedrockGoogle VertexEstimated seconds using recent median response-start and output-speed data. Lower is better.
Google Vertex has the lower typical same-model response ratio across 12 measured models.
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 13 priced shared models.
| Model | Amazon Bedrock | Google Vertex |
|---|---|---|
 Claude Sonnet 5Winner · Google Vertex anthropic/claude-sonnet-5 | Amazon Bedrock
| Google Vertex
|
Claude Fable 5Winner · Google Vertex anthropic/claude-fable-5 | Amazon Bedrock
| Google Vertex
|
Claude Opus 4.8Winner · Google Vertex anthropic/claude-opus-4.8 | Amazon Bedrock
| Google Vertex
|
Claude Opus 4.7Winner · Google Vertex anthropic/claude-opus-4.7 | Amazon Bedrock
| Google Vertex
|
Claude Sonnet 4.6Winner · Google Vertex anthropic/claude-sonnet-4.6 | Amazon Bedrock
| Google Vertex
|
Claude Opus 4.6Winner · Google Vertex anthropic/claude-opus-4.6 | Amazon Bedrock
| Google Vertex
|
Claude Opus 4.5Winner · Google Vertex anthropic/claude-opus-4.5 | Amazon Bedrock
| Google Vertex
|
Claude Haiku 4.5Winner · Google Vertex anthropic/claude-haiku-4.5 | Amazon Bedrock
| Google Vertex
|
Claude Sonnet 4.5Winner · Google Vertex anthropic/claude-sonnet-4.5 | Amazon Bedrock
| Google Vertex
|
 gpt-oss-120bWinner · Amazon Bedrock openai/gpt-oss-120b | Amazon Bedrock
| Google Vertex
|
openai/gpt-oss-20b | Amazon Bedrock
| Google Vertex
|
Claude Opus 4.1Winner · Google Vertex anthropic/claude-opus-4.1 | Amazon Bedrock
| Google Vertex
|
Claude Sonnet 4Winner · Amazon Bedrock anthropic/claude-sonnet-4 | Amazon Bedrock
| Google Vertex
|
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 Google Vertex analysis
How Amazon Bedrock and Google Vertex compare for AI inference
Amazon Bedrock and Google Vertex share 13 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
12 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
13 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 23 indexed models and lists 2 published server regions; Google Vertex has 49 models and lists 7 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 Amazon Bedrock and Google Vertex.
Amazon Bedrock vs Anthropic
10 shared model benchmarks
Google Vertex vs NovitaAI
12 shared model benchmarks
Amazon Bedrock vs Azure
7 shared model benchmarks
Google Vertex vs DeepInfra
10 shared model benchmarks
Amazon Bedrock vs SiliconFlow
3 shared model benchmarks
Google Vertex vs Parasail
6 shared model benchmarks