10/15/25, 8:05 PM Models overview - Claude Docs
Models & pricing Models overview
MODELS & PRICING
Models overview Copy page
Claude is a family of state-of-the-art large language models developed by Anthropic. This
guide introduces our models and compares their performance with legacy models.
The next generation of Claude Models:
Claude Sonnet 4.5 - Our best model for complex agents and coding, with the highest
intelligence across most tasks. Learn more.
Claude Opus 4.1 - Exceptional model for specialized complex tasks requiring advanced
reasoning. Learn more.
Claude Sonnet 4.5 Claude Opus 4.1
Our best model for complex agents and Exceptional model for specialized
coding complex tasks
Text and image input Text and image input
Text output Text output
200k context window (1M context beta 200k context window
available) Superior reasoning capabilities
Highest intelligence across most tasks
Model names
Ask Docs
https://docs.claude.com/en/docs/about-claude/models/overview 1/8
10/15/25, 8:05 PM Models overview - Claude Docs
Model Claude API AWS Bedrock GCP Vertex AI
Claude claude-sonnet-4-5- anthropic.claude-sonnet- claude-sonnet-4-
Sonnet 4.5 20250929 4-5-20250929-v1:0 5@20250929
Claude claude-sonnet-4-20250514 anthropic.claude-sonnet- claude-sonnet-
Sonnet 4 4-20250514-v1:0 4@20250514
Claude claude-3-7-sonnet- anthropic.claude-3-7- claude-3-7-
Sonnet 3.7 20250219 sonnet-20250219-v1:0 sonnet@20250219
( claude-3-7-sonnet-latest
)
Claude claude-opus-4-1-20250805 anthropic.claude-opus-4- claude-opus-4-
Opus 4.1 1-20250805-v1:0 1@20250805
Claude claude-opus-4-20250514 anthropic.claude-opus-4- claude-opus-
Opus 4 20250514-v1:0 4@20250514
Claude claude-3-5-haiku- anthropic.claude-3-5- claude-3-5-
Haiku 3.5 20241022 haiku-20241022-v1:0 haiku@20241022
( claude-3-5-haiku-latest )
Claude claude-3-haiku-20240307 anthropic.claude-3-haiku- claude-3-
Haiku 3 20240307-v1:0 haiku@20240307
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 future models, 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.
Model aliases
For convenience during development and testing, we offer aliases for our model ids. These
aliases automatically point to the most recent snapshot of a given model. When we release
https://docs.claude.com/en/docs/about-claude/models/overview 2/8
10/15/25, 8:05 PM Models overview - Claude Docs
new model snapshots, we migrate aliases to point to the newest version of a model,
typically within a week of the new release.
While aliases are useful for experimentation, we recommend using specific model versions
(e.g., claude-sonnet-4-5-20250929 ) in production applications to ensure consistent
behavior.
Model Alias Model ID
Claude Opus 4.1 claude-opus-4-1 claude-opus-4-1-20250805
Claude Opus 4 claude-opus-4-0 claude-opus-4-20250514
Claude Sonnet 4.5 claude-sonnet-4-5 claude-sonnet-4-5-20250929
Claude Sonnet 4 claude-sonnet-4-0 claude-sonnet-4-20250514
Claude Sonnet 3.7 claude-3-7-sonnet-latest claude-3-7-sonnet-20250219
Claude Haiku 3.5 claude-3-5-haiku-latest claude-3-5-haiku-20241022
Aliases are subject to the same rate limits and pricing as the underlying model version they
reference.
Model comparison table
To help you choose the right model for your needs, we’ve compiled a table comparing the
key features and capabilities of each model in the Claude family:
Claude Claude Claude Claude Claude Claude
Feature Sonnet 4.5 Sonnet 4 Sonnet 3.7 Opus 4.1 Opus 4 Haiku 3.5
Description Our best High- High- Exceptional Our Our fastest
model for performance performance model for previous model
complex model model with specialized flagship
agents and early complex model
coding extended tasks
thinking
Strengths Highest High High Very high Very high Intelligence
intelligence intelligence intelligence intelligence intelligence at blazing
across most and with and and speeds
tasks with toggleable capability capability
https://docs.claude.com/en/docs/about-claude/models/overview 3/8
10/15/25, 8:05 PM Models overview - Claude Docs
Claude Claude Claude Claude Claude Claude
Feature Sonnet 4.5 Sonnet 4 Sonnet 3.7 Opus 4.1 Opus 4 Haiku 3.5
exceptional balanced extended for
agent and performance thinking specialized
coding tasks
capabilities
Multilingual Yes Yes Yes Yes Yes Yes
Vision Yes Yes Yes Yes Yes Yes
Extended Yes Yes Yes Yes Yes No
thinking
Priority Tier Yes Yes Yes Yes Yes Yes
API model claude- claude- claude-3- claude- claude- claude-3-
name sonnet- sonnet-4- 7-sonnet- opus-4-1- opus-4- 5-haiku-
4-5- 20250514 20250219 20250805 20250514 20241022
20250929
Comparative Fast Fast Fast Moderately Moderately Fastest
latency Fast Fast
Context 200K / 200K / 200K 200K 200K 200K
window 1M (beta)1 1M (beta)1
Max output 64000 64000 64000 32000 32000 8192 tokens
tokens tokens tokens tokens tokens
Reliable Jan 20252 Jan 20252 Oct 20242 Jan 20252 Jan 20252 3
knowledge
cutoff
Training Jul 2025 Mar 2025 Nov 2024 Mar 2025 Mar 2025 Jul 2024
data cutoff
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. For example, Claude Sonnet 4.5 was trained on
publicly available information through July 2025, but its knowledge is most extensive and reliable through January 2025.
For more information, see Anthropic’s Transparency Hub.
3 - Haiku models have a single training data cutoff date.
https://docs.claude.com/en/docs/about-claude/models/overview 4/8
10/15/25, 8:05 PM Models overview - Claude Docs
Include the beta header output-128k-2025-02-19 in your API request to increase the
maximum output token length to 128k tokens for Claude Sonnet 3.7.
We strongly suggest using our streaming Messages API to avoid timeouts when generating
longer outputs. See our guidance on long requests for more details.
Model pricing
The table below shows the price per million tokens for each model:
Base Input 5m Cache 1h Cache Cache Hits & Output
Model Tokens Writes Writes Refreshes Tokens
Claude Opus 4.1 $15 / MTok $18.75 / $30 / MTok $1.50 / MTok $75 / MTok
MTok
Claude Opus 4 $15 / MTok $18.75 / $30 / MTok $1.50 / MTok $75 / MTok
MTok
Claude Sonnet 4.5 $3 / MTok $3.75 / MTok $6 / MTok $0.30 / MTok $15 / MTok
Claude Sonnet 4 $3 / MTok $3.75 / MTok $6 / MTok $0.30 / MTok $15 / MTok
Claude Sonnet 3.7 $3 / MTok $3.75 / MTok $6 / MTok $0.30 / MTok $15 / MTok
Claude Sonnet 3.5 $3 / MTok $3.75 / MTok $6 / MTok $0.30 / MTok $15 / MTok
(deprecated)
Claude Haiku 3.5 $0.80 / MTok $1 / MTok $1.6 / MTok $0.08 / MTok $4 / MTok
Claude Opus 3 $15 / MTok $18.75 / $30 / MTok $1.50 / MTok $75 / MTok
(deprecated) MTok
Claude Haiku 3 $0.25 / MTok $0.30 / $0.50 / $0.03 / MTok $1.25 /
MTok MTok MTok
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.
https://docs.claude.com/en/docs/about-claude/models/overview 5/8
10/15/25, 8:05 PM Models overview - Claude Docs
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 our prompt engineering guides
for details.
For specific Claude 4 prompting best practices, see our Claude 4 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
In most cases, you can switch from Claude 3.7 models to Claude 4 models with minimal
changes:
1. Update your model name:
From: claude-3-7-sonnet-20250219
To: claude-sonnet-4-5-20250929 or claude-opus-4-1-20250805
2. Your existing API calls will continue to work without modification, although API
behavior has changed slightly in Claude 4 models (see API release notes for details).
For more details, see Migrating to Claude 4.
Get started with Claude
If you’re ready to start exploring what Claude can do for you, let’s 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, we’ve got you covered.
Looking to chat with Claude? Visit claude.ai!
https://docs.claude.com/en/docs/about-claude/models/overview 6/8
10/15/25, 8:05 PM Models overview - Claude Docs
Intro to Claude Quickstart Claude Console
Explore Claude’s Learn how to make your Craft and test powerful
capabilities and first API call in minutes. prompts directly in your
development flow. browser.
If you have any questions or need assistance, don’t hesitate to reach out to our support
team or consult the Discord community.
Was this page helpful? Yes No
Quick start Choosing a model
Company Help and security
Anthropic Availability
Careers Status
Economic Futures Support center
Research
News
Trust center
Transparency
Learn Terms and policies
Courses Privacy policy
https://docs.claude.com/en/docs/about-claude/models/overview 7/8
10/15/25, 8:05 PM Models overview - Claude Docs
MCP connectors Disclosure policy
Customer stories Usage policy
Engineering blog Commercial terms
Events Consumer terms
Powered by Claude
Service partners
Startups program
https://docs.claude.com/en/docs/about-claude/models/overview 8/8
