The deciding difference is operational: vLLM can run on infrastructure you control, Amazon Bedrock cannot. If that constraint is real for you, it settles the choice before anything else is considered.
Frontier models inside your AWS account, with IAM and VPC boundaries.
Use when procurement needs the model call to stay inside your cloud account.
High-throughput open-weight serving on your own GPUs.
| Amazon Bedrock | vLLM | |
|---|---|---|
| Licence | Proprietary | Open source |
| Pricing | usage based | open source |
| Self-hostable | No | Yes |
| Languages | TypeScript, Python | Python |
| Install | — | pip install vllm |
| Keys required | AWS_REGION, AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY | None |
The deciding difference is operational: vLLM can run on infrastructure you control, Amazon Bedrock cannot. If that constraint is real for you, it settles the choice before anything else is considered. Amazon Bedrock: Frontier models inside your AWS account, with IAM and VPC boundaries. vLLM: High-throughput open-weight serving on your own GPUs.
Amazon Bedrock is a hosted service only. vLLM can run on your own infrastructure.
Amazon Bedrock is proprietary (usage based). vLLM is open source (open source).
Every page here answers to Accept: text/markdown and returns the same content at roughly a tenth the tokens. No separate site, no toggle — same URL.
curl -s -H "Accept: text/markdown" https://newagent.build/compare/bedrock-vs-vllm