logoCloud Edventures

AI/ML infrastructure

Amazon Bedrock Model Picker & Pricing

Explore all Amazon Bedrock foundation models — Claude, Titan, Llama, Mistral, and more. Compare by use case, context window, latency, and pricing. Get cost estimates for your token volume.

Try Bedrock in a live AI Playground — 15 free creditsExplore all tools →

Claude 3.5 Sonnet

Anthropic

Fast

Context

200K

Max Output

8K

Input / 1M tokens

$3

Output / 1M tokens

$15

Advanced reasoningCode generationAnalysis

Best for: Complex tasks requiring deep reasoning

Claude 3.5 Haiku

Anthropic

Fast

Context

200K

Max Output

8K

Input / 1M tokens

$0.25

Output / 1M tokens

$1.25

SpeedCost efficiencySimple tasks

Best for: High-volume, low-latency tasks

Claude 3 Opus

Anthropic

Slow

Context

200K

Max Output

4K

Input / 1M tokens

$15

Output / 1M tokens

$75

Highest reasoningComplex analysisNuance

Best for: Research and complex decision-making

Titan Text Express

Amazon

Fast

Context

8K

Max Output

8K

Input / 1M tokens

$0.2

Output / 1M tokens

$0.6

AWS nativeFine-tunableCost efficient

Best for: General text tasks within AWS ecosystem

Titan Text Lite

Amazon

Fast

Context

4K

Max Output

4K

Input / 1M tokens

$0.15

Output / 1M tokens

$0.2

Cheapest optionSimple tasks

Best for: Basic text generation and classification

Titan Embeddings V2

Amazon

Fast

Context

8K

Max Output

N/A

Input / 1M tokens

$0.02

Output / 1M tokens

N/A

EmbeddingsSemantic searchRAG

Best for: Text embeddings for search and RAG pipelines

Llama 3.1 70B

Meta

Medium

Context

128K

Max Output

2K

Input / 1M tokens

$2.65

Output / 1M tokens

$3.5

Open weightsStrong reasoningCustomizable

Best for: Tasks requiring open-source model flexibility

Llama 3.1 8B

Meta

Fast

Context

128K

Max Output

2K

Input / 1M tokens

$0.3

Output / 1M tokens

$0.6

LightweightFastOpen weights

Best for: Simple tasks with open-source requirement

Mistral Large

Mistral AI

Medium

Context

128K

Max Output

8K

Input / 1M tokens

$4

Output / 1M tokens

$12

MultilingualCodeFunction calling

Best for: Multilingual and code tasks

Mistral 7B

Mistral AI

Fast

Context

32K

Max Output

8K

Input / 1M tokens

$0.15

Output / 1M tokens

$0.2

LightweightEU complianceSpeed

Best for: Simple tasks with EU data requirements

Command R+

Cohere

Medium

Context

128K

Max Output

4K

Input / 1M tokens

$3

Output / 1M tokens

$15

RAG optimizedCitationsLong context

Best for: RAG pipelines with source citations

Command R

Cohere

Fast

Context

128K

Max Output

4K

Input / 1M tokens

$0.5

Output / 1M tokens

$1.5

RAGEfficientCitations

Best for: Cost-effective RAG workflows

Build with Amazon Bedrock hands-on

Spin up an AI Playground with Bedrock access. Build RAG pipelines, AI agents, and prompt flows with real AWS infrastructure.

Launch AI Playground →