Overview

yes

Editorial Notes

This is the essential reference for understanding the Claude model family and should be one of the first pages you read before building anything with the Anthropic API. Focus on the capability differences between model tiers (Haiku, Sonnet, Opus) as this directly impacts your cost, latency, and quality tradeoffs in production. Pay attention to context window sizes and maximum output token limits, since these constraints will shape your prompt design and chunking strategies. When comparing with OpenAI’s model lineup, note that Anthropic’s naming convention signals capability tier rather than generation number.


Original Documentation

Claude is a family of state-of-the-art large language models developed by Anthropic. This guide introduces the available models and compares their performance.


Choosing a model#

If you’re unsure which model to use, consider starting with Claude Opus 4.6 for the most complex tasks. It is the latest generation model with exceptional performance in coding and reasoning.

All current Claude models support text and image input, text output, multilingual capabilities, and vision. Models are available via the Claude API, AWS Bedrock, and Google Vertex AI.

Once you’ve picked a model, learn how to make your first API call.

Latest models comparison#

FeatureClaude Opus 4.6Claude Sonnet 4.6Claude Haiku 4.5
DescriptionThe most intelligent model for building agents and codingThe best combination of speed and intelligenceThe fastest model with near-frontier intelligence
Claude API IDclaude-opus-4-6claude-sonnet-4-6claude-haiku-4-5-20251001
Claude API aliasclaude-opus-4-6claude-sonnet-4-6claude-haiku-4-5
AWS Bedrock IDanthropic.claude-opus-4-6-v1anthropic.claude-sonnet-4-6anthropic.claude-haiku-4-5-20251001-v1:0
GCP Vertex AI IDclaude-opus-4-6claude-sonnet-4-6claude-haiku-4-5@20251001
Pricing1$5 / input MTok
$25 / output MTok
$3 / input MTok
$15 / output MTok
$1 / input MTok
$5 / output MTok
Extended thinkingYesYesYes
Adaptive thinkingYesYesNo
Priority TierYesYesYes
Comparative latencyModerateFastFastest
Context window200K tokens /
1M tokens (beta)3
200K tokens /
1M tokens (beta)3
200K tokens
Max output128K tokens64K tokens64K tokens
Reliable knowledge cutoffMay 20252Aug 20252Feb 2025
Training data cutoffAug 2025Jan 2026Jul 2025

1 - See the pricing page for complete pricing information including batch API discounts, prompt caching rates, extended thinking costs, and vision processing fees.

2 - Reliable knowledge cutoff indicates the date through which a model’s knowledge is most extensive and reliable. Training data cutoff is the broader date range of training data used. For more information, see Anthropic’s Transparency Hub.

3 - Claude Opus 4.6 and Sonnet 4.6 support a 1M token context window when using the context-1m-2025-08-07 beta header. Long context pricing applies to requests exceeding 200K tokens.

Models with the same snapshot date (e.g., 20240620) are identical across all platforms and do not change. The snapshot date in the model name ensures consistency and allows developers to rely on stable performance across different environments.

Starting with Claude Sonnet 4.5 and all subsequent models (including Claude Sonnet 4.6), AWS Bedrock and Google Vertex AI offer two endpoint types: global endpoints (dynamic routing for maximum availability) and regional endpoints (guaranteed data routing through specific geographic regions). For more information, see the third-party platform pricing section.

Legacy models

The following models are still available. Consider migrating to current models for improved performance:

FeatureClaude Sonnet 4.5Claude Opus 4.5Claude Opus 4.1Claude Sonnet 4Claude Opus 4Claude Haiku 3 (deprecated)
Claude API IDclaude-sonnet-4-5-20250929claude-opus-4-5-20251101claude-opus-4-1-20250805claude-sonnet-4-20250514claude-opus-4-20250514claude-3-haiku-20240307
Claude API aliasclaude-sonnet-4-5claude-opus-4-5claude-opus-4-1claude-sonnet-4-0claude-opus-4-0
AWS Bedrock IDanthropic.claude-sonnet-4-5-20250929-v1:0anthropic.claude-opus-4-5-20251101-v1:0anthropic.claude-opus-4-1-20250805-v1:0anthropic.claude-sonnet-4-20250514-v1:0anthropic.claude-opus-4-20250514-v1:0anthropic.claude-3-haiku-20240307-v1:0
GCP Vertex AI IDclaude-sonnet-4-5@20250929claude-opus-4-5@20251101claude-opus-4-1@20250805claude-sonnet-4@20250514claude-opus-4@20250514claude-3-haiku@20240307
Pricing$3 / input MTok
$15 / output MTok
$5 / input MTok
$25 / output MTok
$15 / input MTok
$75 / output MTok
$3 / input MTok
$15 / output MTok
$15 / input MTok
$75 / output MTok
$0.25 / input MTok
$1.25 / output MTok
Extended thinkingYesYesYesYesYesNo
Priority TierYesYesYesYesYesNo
Comparative latencyFastModerateModerateFastModerateFast
Context window200K tokens /
1M tokens (beta)1
200K tokens200K tokens200K tokens /
1M tokens (beta)1
200K tokens200K tokens
Max output64K tokens64K tokens32K tokens64K tokens32K tokens4K tokens
Reliable knowledge cutoffJan 20252May 20252Jan 20252Jan 20252Jan 202523
Training data cutoffJul 2025Aug 2025Mar 2025Mar 2025Mar 2025Aug 2023

Claude Haiku 3 (claude-3-haiku-20240307) is deprecated and will be retired on April 19, 2026. Migrate to Claude Haiku 4.5 before the retirement date. See model deprecations for details.

1 - Claude Sonnet 4.5 and Claude Sonnet 4 support a 1M token context window when using the context-1m-2025-08-07 beta header. Long context pricing applies to requests exceeding 200K tokens.

2 - Reliable knowledge cutoff indicates the date through which a model’s knowledge is most extensive and reliable. Training data cutoff is the broader date range of training data used.

3 - Some Haiku models have a single training data cutoff date.

Prompt and output performance#

Claude 4 models excel in:

  • Performance: Top-tier results in reasoning, coding, multilingual tasks, long-context handling, honesty, and image processing. See the Claude 4 blog post for more information.

  • Engaging responses: Claude models are ideal for applications that require rich, human-like interactions.

  • If you prefer more concise responses, you can adjust your prompts to guide the model toward the desired output length. Refer to the prompt engineering guides for details.

  • For prompting best practices, see the prompting best practices guide.

  • Output quality: When migrating from previous model generations to Claude 4, you may notice larger improvements in overall performance.

Migrating to Claude 4.6#

If you’re currently using older Claude models, consider migrating to Claude Opus 4.6 to take advantage of improved intelligence and enhanced capabilities. For detailed migration instructions, see Migrating to Claude 4.6.

Get started with Claude#

If you’re ready to start exploring what Claude can do for you, dive in! Whether you’re a developer looking to integrate Claude into your applications or a user wanting to experience the power of AI firsthand, the following resources can help.

Looking to chat with Claude? Visit claude.ai!

Explore Claude’s capabilities and development flow. Learn how to make your first API call in minutes. Craft and test powerful prompts directly in your browser.

If you have any questions or need assistance, don’t hesitate to reach out to the support team or consult the Discord community.

Link last verified June 7, 2026. View original ↗
Source: Anthropic Platform Docs
Link last verified: 2026-02-26