No longer supported

This model is deprecated (released July 2023) and is no longer actively maintained or recommended by Anthropic. Consider using their current flagship model instead.

deprecatedlegacyllm Proprietary

Claude 2.0

by Anthropic· Released July 2023· Cutoff Early 2023

Claude 2.0 is an earlier generation large language model by Anthropic, succeeding Claude 1.3. It offered improved performance on coding, math, and reasoning tasks compared to its predecessor, with a 100K token context window. It has been superseded by Claude 3 and later models.

Official Site API Docs

Input cost

$8.00 per 1M tokens

Output cost

$24.00 per 1M tokens

Context window

100K tokens

Max output

4096 tokens

Modalities

text

License

proprietary

Capabilities

Text GenerationCode GenerationReasoningSummarizationQuestion AnsweringCreative Writing

Best For

General-purpose text generation and analysis with a large context window, now deprecated in favor of newer Claude models.

Strengths

Large 100K token context window
Strong performance on coding and math tasks
Improved safety and helpfulness over Claude 1.3

Limitations

Deprecated and no longer recommended for new projects
Higher latency compared to newer models
Lacks multimodal capabilities (text-only)
Higher pricing than Claude 3 Haiku and Sonnet

Use Cases

Document summarization of long texts

Code generation and debugging

Complex reasoning and analysis

Creative writing and storytelling

Question answering over large documents

Data extraction from lengthy reports

Educational tutoring and explanations

Improvements Over Previous Model

Context window increased from 9K tokens (Claude 1.3) to 100K tokens
Improved coding performance on HumanEval (71.2% vs 56.5% for Claude 1.3)
Better math reasoning on GSM8K (88.0% vs 85.4% for Claude 1.3)
Reduced harmful outputs through improved safety training
Longer output capability up to 4096 tokens (vs 2048 in Claude 1.3)

Back to all models