What is Claude 2 used for?

Claude 2 is used for structured outputs, coding, and math-heavy prompts. The family description and listed model capabilities point to those workloads as the best fit.

How does Claude 2 compare to Computer Use?

Claude 2 by Anthropic is strongest where you need structured outputs, while Computer Use by Anthropic is the closest related family to check for agent. Claude 2 has 2 listed variants and reaches up to 200k context, so compare the specs and pricing tables before choosing a production model.

Which Claude 2 model should I use?

For the lowest listed input price, start with Claude 2 through Anthropic at $8/1M input tokens. For the most capable/latest local choice, evaluate Claude 2.1 with 200k context and structured outputs.

Claude 2 Models by Anthropic

AnthropicProprietary

2 models2023Up to 200k ctxFrom $8/1M input

About

Claude 2 is a cutting-edge large language model developed by Anthropic, aimed at generating human-like text and assisting with diverse tasks. Released in July 2023, it enhances the capabilities of Claude 1.3 with improved performance and an impressive context window of up to 100,000 tokens, facilitating extensive document processing. This makes it ideal for summarization, coding assistance, and complex reasoning tasks. Trained with reinforcement learning from human feedback, Claude 2 excels in producing safe and relevant responses, scoring in the 90th percentile of the GRE reading and writing benchmarks. It stands as a strong competitor to leading models like OpenAI's GPT-4 124.

Archived Variants

Use-when guidance is derived from seed capabilities, context, release, and replacement fields.

2 in view2 retired

Claude 2.1Archived

Keep only for existing workloads; choose a current variant for new builds.

2023-11200k contextstructured outputs

Claude 2Archived

Keep only for existing workloads; choose a current variant for new builds.

2023-07100k contextstructured outputs

Current Claude 2 variants with use-when guidance and lifecycle status
Model	Use when	Released	Signals	Status
Claude 2.1	Keep only for existing workloads; choose a current variant for new builds.	2023-11	200k contextstructured outputs	Archived
Claude 2	Keep only for existing workloads; choose a current variant for new builds.	2023-07	100k contextstructured outputs	Archived

Release Timeline

2 release groups

2023-11

1 retired

Claude 2.1

200k contextstructured outputs

Archived

2023-07

1 retired

Claude 2

100k contextstructured outputs

Archived

Specifications(2 models)

Claude 2 model specifications comparison
Model	Released	Context	Structured Outputs
Claude 2.1	2023-11	200k	Yes
Claude 2	2023-07	100k	Yes

Available From(2 providers)

Anthropic

AWS Bedrock

Pricing

Claude 2 model pricing by provider
Model	Provider	Input / 1M	Output / 1M	Type
Claude 2.1	AWS Bedrock	$8	$24	Serverless
Claude 2	AWS Bedrock	$8	$24	Serverless
Claude 2	Anthropic	$8	$24	Serverless
Claude 2.1	Anthropic	$8	$24	Serverless

Frequently Asked Questions

What is Claude 2 used for?: Claude 2 is used for structured outputs, coding, and math-heavy prompts. The family description and listed model capabilities point to those workloads as the best fit.
How does Claude 2 compare to Computer Use?: Claude 2 by Anthropic is strongest where you need structured outputs, while Computer Use by Anthropic is the closest related family to check for agent. Claude 2 has 2 listed variants and reaches up to 200k context, so compare the specs and pricing tables before choosing a production model.
Which Claude 2 model should I use?: For the lowest listed input price, start with Claude 2 through Anthropic at $8/1M input tokens. For the most capable/latest local choice, evaluate Claude 2.1 with 200k context and structured outputs.