LLM Reference
AWS Bedrock

AWS Bedrock

Researched todayHyperscalerTier 1

Amazon Web Services

CodingRAGAgentsLong contextVisionClassificationJSON / Tool useHighlightHyperscaler

AWS Bedrock offers 132 tracked models (110 with output token pricing). This catalog covers coding, rag, and agents; open any model detail page for benchmarks, batch tiers, and migration prompts.

Covers 7 workload areas across 132 tracked models; last verified 2026-09-14.

Use it for

  • Teams comparing token and batch pricing across this provider's models
  • Operators routing coding, rag, and agents workloads through this API
  • Batch buyers auditing discount coverage model-by-model

Do not use it for

  • Final benchmark picks without opening the relevant model detail page

Tracked models

132

Models available through this provider

Priced output routes

110

Models with output token pricing tracked

Cheapest output

$0.040

Mistral Voxtral Mini 3B 2507 on this route

Batch-ready models

3

Models with discounted batch pricing

Latest model release

2026-09-01

13d since newest release

Freshness

2026-09-14

Researched today

fresh

Routes available via routers & gateways

Browse routers ->

Information

TypeHyperscaler
TierTier 1
Models132
CompanyAmazon Web Services
Founded2006
Seattle, Washington, United States

AWS Bedrock is Amazon's fully managed foundation-model service, providing unified API access to top models from Anthropic, Meta, Mistral, and other leading AI labs with built-in tools for RAG, fine-tuning, and AI agent development.

Where this host wins

  • Coding: 42 tracked models with SWE-bench / HumanEval-style scores.
  • RAG: 65 tracked models with ruler / needle retrieval benchmarks.
  • Agentic: 41 tracked models with BFCL, tau-bench, and SWE-bench tool-use coverage.
  • Long-context: 68 tracked models with context-token or InfiniteBench-class signal.

Getting started

Verify: quotas and regions in the linked vendor documentation.

SDKs & libraries

Platform Overview

Amazon Bedrock is a comprehensive, fully managed service for building and scaling generative AI applications. The platform provides access to a diverse array of high-performing foundation models (FMs) from leading AI companies through a unified API, enabling users to select the most suitable models for their specific use cases. Key features include model customization using proprietary data through techniques like fine-tuning and Retrieval Augmented Generation (RAG), which significantly enhances the relevance and accuracy of AI outputs.

Llama 4 Maverick 17B Instruct
$0.24 / $0.97 standard · $0.12 / $0.485 batch
Llama 4 Scout 17B Instruct
$0.17 / $0.66 standard · $0.085 / $0.33 batch

Available Models(132)

View all →

All models available as Serverless

ModelInput (per 1M)Output (per 1M)Batch input (per 1M)Batch output (per 1M)
Claude Fable 5.1$10$50
Claude Mythos 5.1
Claude Opus 5
Claude Sonnet 5
Claude Fable 5$10.00$50.00
Claude Mythos 5
Claude Opus 4.8
Grok 4.3$1.25$2.50
GPT-5.5$5.50$33.00
Claude Opus 4.7$5$25
View full catalog →

Where else to run this