Amazon Bedrock
Call open-weight models like Llama, DeepSeek and Qwen through a fully managed AWS API, paying per token.
Overview
Amazon Bedrock is AWS's fully managed API for foundation models. You call open-weight models such as Llama, Mistral, DeepSeek, Qwen, Gemma and gpt-oss without managing any servers, and pay per million input and output tokens. Batch and Flex modes cost about 50% less, and Provisioned Throughput reserves capacity for steady, high-volume use.
Specifications
| Hosting type | Serverless API |
|---|---|
| Model families | Llama, DeepSeek, Qwen, Gemma, gpt-oss |
| LLM models | Llama 3.1 8B Instruct, Llama 3.3 70B Instruct, DeepSeek-R1, DeepSeek-V3.1, Qwen3 32B, Qwen3 235B-A22B, Gemma 3 4B, Gemma 3 12B, Gemma 3 27B, gpt-oss-120b, gpt-oss-20b |
| Pricing range | US$0.04 – US$2.66 |
| Pricing model | Pay per token, Reserved or committed capacity |
| Free tier available | No |
| Data center locations | United States, Canada, Brazil, Ireland, United Kingdom, Germany, France, Sweden, Switzerland, Spain, Japan, South Korea, India, Singapore, Australia |
| Hardware / GPU options | Fully managed. AWS runs the models on its own GPU and AWS Inferentia / Trainium infrastructure; you don't choose hardware. |
| VRAM & memory | |
| Maximum model size | 671B |
| OpenAI-compatible API | Yes |
News about Amazon AWS
All news →LLM Hosting Roundup: Anthropic’s capacity crunch, Vera Rubin and DeepSeek’s $15B (23 Oct 2026)
Anthropic's hunt for cloud capacity, NVIDIA's DSX POD and new Vera Rubin inference benchmarks, Dell's first Groq 3 rack, DeepSeek's reported $15B raise and Reflection's open-weights Beam model.
