Anthropic's Claude in Amazon Bedrock

Build generative AI solutions with Anthropic’s state-of-the-art model, Claude

Introducing the latest Claude models

Choose the exact combination of intelligence, speed, and cost to suit your needs. All of the latest Claude models are available now in Amazon Bedrock.
The upgraded Claude 3.5 Sonnet delivers across-the-board improvements over its predecessor, with particularly significant gains in coding—an area where it already led the field, according to Anthropic. It also includes a groundbreaking new capability in public beta: computer use. Developers can direct Claude to use computers the way people do—by looking at a screen, moving a cursor, clicking buttons, and typing text, accomplishing tasks that require hundreds of steps. The model also raises the bar across a range of cognitive tasks. It more deeply understands nuanced instructions and context, generates creative solutions to problems, recognizes and corrects mistakes, and delivers more sophisticated analysis around complex data.
Claude 3.5 Haiku is the next generation of Anthropic’s fastest model. Claude 3.5 Haiku improves across every skill set and surpasses even Claude 3 Opus, the largest model in Anthropic’s previous generation, on many intelligence benchmarks—including coding. With fast speeds, improved instruction following, and more accurate tool use, Claude 3.5 Haiku is well suited for user-facing products, specialized sub-agent tasks, and generating personalized experiences from huge volumes of data—like purchase history, pricing, or inventory data. The new Claude 3.5 Haiku will be released initially as a text-only model.
Opus is a highly intelligent model with reliable performance on complex tasks. It can navigate open-ended prompts and sight-unseen scenarios with remarkable fluency and human-like understanding. Use Opus to automate tasks, and accelerate research and development across a diverse range of use cases and industries.

Trustworthy AI Systems

Anthropic was founded to create the world’s safest and most capable large language model. Claude is Anthropic’s frontier, state-of-the-art large language models that offers important features for enterprises like advanced reasoning, vision analysis, code generation, and multilingual processing. Hear from Neerav Kingsland, Head of Global Accounts at Anthropic, as he discusses what Claude’s availability in Amazon Bedrock can provide for businesses around the world.

Benefits

Anthropic's Claude models have a 200,000 token context window enabling you to relay a large volume of information to Claude. This translates to roughly 150,000 words, or over 500 pages of material. You can now upload technical documentation like entire codebases, financial statements, or even long literary works. By being able to talk to large bodies of content or data, Claude can summarize, perform Q&A, forecast trends, compare and contrast multiple documents, and much more.
Claude 3.5 Sonnet exhibits near-human levels of comprehension and fluency on complex tasks, leading the frontier of general intelligence. Claude can be used for sophisticated dialogue, nuanced creative content generation, complex reasoning, math, coding, and scientific queries. It can edit, rewrite, summarize, classify, extract structured data, perform Q&A based on provided content, and more. Claude models offer increased steerability, giving users more control, and produce predictable, high-quality outputs. In practical business scenarios, Claude 3.5 Sonnet can help financial analysts analyze complex financial reports, identify key trends, and generate insightful summaries for stakeholders. Marketing teams can leverage Claude's exceptional writing skills to craft compelling ad copy, product descriptions, and social media content that resonates with target audiences. Healthcare professionals can employ Claude to quickly summarize patient records, identify potential drug interactions, and assist in diagnostic processes. Legal firms can use Claude to efficiently review and summarize lengthy legal documents, identify relevant precedents, and draft initial contract templates.
Claude 3.5 Sonnet offers best-in-class vision capabilities compared to other leading models. It can accurately transcribe text from imperfect images—a core capability for retail, logistics, and financial services, where AI may glean more insights from an image, graphic, or illustration than from text alone. The latest Claude models demonstrate a strong aptitude for understanding a wide range of visual formats, including photos, charts, graphs and technical diagrams. With Claude, you can extract more insights from documents, process web UI and diverse product documentation, generate image catalog metadata, and more.
Claude 3.5 Haiku is fast and cost-effective for its intelligence category, excelling at complex tasks demanding rapid responses like knowledge retrieval or sales automation. With new latency-optimized inference available in public preview, enterprises can achieve even faster response times for their mission-critical AI applications without compromising quality.
Claude is based on Anthropic’s leading safety research, and built with techniques including Constitutional AI. With industry-leading resistance to jailbreaks and misuse, Claude is designed to reduce brand risk, and aims to be helpful, honest, and harmless.

Amazon and Anthropic strategic collaboration

In this fireside chat, Dario Amodei, CEO and co-founder of Anthropic, discusses Claude and how Anthropic and AWS are working together to accelerate the responsible deployment of generative AI.

Unleashing the power of generative AI

In this fireside chat, Daniela Amodei, President and Co-founder of Anthropic, unveils ground-breaking advancements to revolutionize the enterprise landscape with generative AI. This discussion sheds light on the generative AI innovations that are poised to propel businesses into the next frontier of AI transformation. Anthropic and AWS are committed to delivering enterprise-grade AI solutions that prioritize accuracy, trustworthiness, reliability, and industry-leading safeguards.

Prompt engineering best practices from Anthropic

Prompt engineering is the process of guiding LLMs to produce desired outputs. Get an overview of prompt engineering best practices and learn how to choose the most appropriate formats, phrases, words, and symbols to get the most out of generative AI solutions while improving accuracy and performance. This session uses Anthropic's Claude LLM as an example of how prompt engineering helps to solve complex customer use cases. Also learn how prompts can be integrated with your architecture and how to use API parameters for tuning the model parameters using Amazon Bedrock.

Use cases

Claude can act as an always-on virtual sales representative, ensure speedy and friendly resolution to service requests, and increase customer satisfaction.

Claude can extract relevant information from business emails and documents, categorize and summarize survey responses, and wrangle reams of text with high speed and accuracy.

Claude is able to parse legal documents and answer questions about them, so lawyers can reduce costs and focus on higher-level work.

Claude can help insurance agents make faster, better claims decisions by providing insights across customer conversations, claims documents, and policies.

Claude can help boost developer productivity by assisting with in-line code generation, debugging, and having natural-language conversation to help developers understand existing code.

Model versions

Claude 3.5 Sonnet

Anthropic’s most intelligent and advanced model, Claude 3.5 Sonnet, demonstrates exceptional capabilities across a diverse range of tasks and evaluations. Claude 3.5 Sonnet excels in coding, writing, visual data extraction, agentic tasks, and tool use. The upgraded Claude 3.5 Sonnet (Claude 3.5 Sonnet v2) can now generate computer actions—like keystrokes and mouse clicks—accomplishing tasks that require hundreds of steps. According to Anthropic, you can automate busywork and mundane tasks with the first frontier-level AI model to reliably use computers in this way.

Max Tokens: 200K

Languages: English, Spanish, Japanese, and multiple other languages.

Fine-tuning supported: No

Supported Use Cases: RAG or search & retrieval over vast amounts of knowledge, product recommendations, forecasting, targeted marketing, code generation, quality control, parse text from images.

Read the blog

Claude 3.5 Haiku

Claude 3.5 Haiku, the latest generation of Anthropic's fastest model, is optimal for fast, high-performance tasks. Claude 3.5 Haiku is a text-only model that excels across areas like writing, data extraction and labeling, and code completion. With its new latency-optimized inference capability available in public preview, Claude 3.5 Haiku delivers even faster response times while maintaining high accuracy.

Max Tokens: 200K

Languages: English, Spanish, Japanese, and multiple other languages.

Fine-tuning supported: No

Supported Use Cases: Code completions, interactive chat bots, data extraction and labeling, and real-time content moderation.

Read the blog

 

Claude 3 Opus

Claude 3 Opus is a powerful and reliable AI model, with top-level performance on highly complex tasks. It can navigate open-ended prompts and sight-unseen scenarios with remarkable fluency and human-like understanding.

Max Tokens: 200K

Languages: English, Spanish, Japanese, and multiple other languages.

Fine-tuning supported: No

Supported Use Cases: Task automation, interactive coding, research review, brainstorming and hypothesis generation, advanced analysis of charts & graphs, financials and market trends, forecasting.

Read the blog

Claude 3 Haiku

Anthropic’s fastest, most compact model for near-instant responsiveness. It answers simple queries and requests with speed.

Max tokens: 200K

Languages: English, Spanish, Japanese, and multiple other languages.

Fine-tuning supported: Yes

Supported use cases: Quick and accurate support in live interactions, translations, content moderation, optimize logistics, inventory management, extract knowledge from unstructured data.

Read the blog

Read the fine-tuning technical blog

Claude 3 Sonnet

Claude 3 Sonnet is engineered to be dependable for scaled AI deployments across a variety of use cases.

Max tokens: 200K

Languages: English, Spanish, Japanese, and multiple other languages.

Fine-tuning supported: No

Supported use cases: RAG or search & retrieval over vast amounts of knowledge, product recommendations, forecasting, targeted marketing, code generation, quality control, parse text from images.

Read the blog

Claude 2.1

Claude 2.1 is a large language model (LLM) by Anthropic with a 200K token context window, reduced hallucination rates, and improved accuracy over long documents.

Max tokens: 200K

Languages: English and multiple other languages

Fine-tuning supported: No

Supported use cases: Summarization, Q&A, trend forecasting, comparing and contrasting multiple documents, and analysis. Claude 2.1 excels at the core capabilities of Claude 2.0 and Claude Instant.

Read the blog

Claude 2.0

Claude 2.0 is a leading LLM from Anthropic that enables a wide range of tasks from sophisticated dialogue and creative content generation to detailed instruction.

Max tokens: 100K

Languages: English and multiple other languages

Fine-tuning supported: No

Supported use cases: Thoughtful dialogue, content creation, complex reasoning, creativity, and coding.

Claude Instant

Claude Instant is Anthropic's faster, lower-priced yet very capable LLM.

Max tokens: 100K

Languages: English and multiple other languages

Fine-tuning supported: Yes (Preview)

Supported use cases: Casual dialogue, text analysis, summarization, and document comprehension.