Models
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.
Claude 3.5 Haiku
Later this year
Claude 3.5 Sonnet
Our most intelligent model
Text and image inputText output
200k context window
Claude 3.5 Opus
Later this year
Claude 3 Haiku
Fast and cost-effective
Text and image inputText output
200k context window
Claude 3 Sonnet
Balance of speed and intelligence
Text and image inputText output
200k context window
Claude 3 Opus
Excels at writing and complex tasks
Text and image inputText output
200k context window
Model names
| Model | Anthropic API | AWS Bedrock | GCP Vertex AI |
|---|---|---|---|
| Claude 3.5 Opus | Later this year | Later this year | Later this year |
| Claude 3.5 Sonnet | claude-3-5-sonnet-20240620 | anthropic.claude-3-5-sonnet-20240620-v1:0 | claude-3-5-sonnet@20240620 |
| Claude 3.5 Haiku | Later this year | Later this year | Later this year |
| Model | Anthropic API | AWS Bedrock | GCP Vertex AI |
|---|---|---|---|
| Claude 3 Opus | claude-3-opus-20240229 | anthropic.claude-3-opus-20240229-v1:0 | claude-3-opus@20240229 |
| Claude 3 Sonnet | claude-3-sonnet-20240229 | anthropic.claude-3-sonnet-20240229-v1:0 | claude-3-sonnet@20240229 |
| Claude 3 Haiku | claude-3-haiku-20240307 | anthropic.claude-3-haiku-20240307-v1:0 | claude-3-haiku@20240307 |
Model comparison
Here is a visualization comparing cost vs. speed across Claude 3 and 3.5 models, showcasing the range in tradeoffs between cost and intelligence:
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 3.5 Sonnet | Claude 3 Opus | Claude 3 Sonnet | Claude 3 Haiku | |
|---|---|---|---|---|
| Description | Most intelligent model | Powerful model for highly complex tasks | Balance of intelligence and speed | Fastest and most compact model for near-instant responsiveness |
| Strengths | Highest level of intelligence and capability | Top-level performance, intelligence, fluency, and understanding | Strong utility, balanced for scaled deployments | Quick and accurate targeted performance |
| Multilingual | Yes | Yes | Yes | Yes |
| Vision | Yes | Yes | Yes | Yes |
| API model name | claude-3-5-sonnet-20240620 | claude-3-opus-20240229 | claude-3-sonnet-20240229 | claude-3-haiku-20240307 |
| API format | Messages API | Messages API | Messages API | Messages API |
| Comparative latency | Fast | Moderately fast | Fast | Fastest |
| Context window | ||||
| Max output | ||||
| Cost (Input / Output per ) | $3.00 / $15.00 | $15.00 / $75.00 | $3.00 / $15.00 | $0.25 / $1.25 |
| Training data cut-off | Apr 2024 | Aug 2023 | Aug 2023 | Aug 2023 |
Prompt and output performance
The Claude 3 family excels in:
-
Benchmark performance: Top-tier results in reasoning, coding, multilingual tasks, long-context handling, honesty, and image processing. See the Claude 3 model card for more information.
-
Engaging responses: Claude 3 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.
-
Output quality: When migrating from previous model generations to the Claude 3 family, you may notice larger improvements in overall performance.
Legacy models
We recommend migrating to the Claude 3 family of models. However, we understand that some users may need time to transition from our legacy models:
- Claude Instant 1.2: A fast and efficient model predecessor of Claude Haiku.
- Claude 2.0: The strong-performing predecessor to Claude 3.
- Claude 2.1: An updated version of Claude 2 with improved accuracy and consistency.
These models do not have the vision capabilities of the Claude 3 family and are generally slower, less performant and intelligent.
The model deprecation page contains information on when legacy models will be deprecated.
Legacy model comparison
To help you choose the right model for your needs, this table compares key features and capabilities.
| Claude 2.1 | Claude 2 | Claude Instant 1.2 | |
|---|---|---|---|
| Description | Updated version of Claude 2 with improved accuracy | Predecessor to Claude 3, offering strong all-round performance | Our cheapest small and fast model, a predecessor of Claude Haiku |
| Strengths | Legacy model - performs less well than Claude 3 models | Legacy model - performs less well than Claude 3 models | Legacy model - performs less well than Claude 3 models |
| Multilingual | Yes, with less coverage, understanding, and skill than Claude 3 | Yes, with less coverage, understanding, and skill than Claude 3 | Yes, with less coverage, understanding, and skill than Claude 3 |
| Vision | No | No | No |
| API model name | claude-2.1 | claude-2.0 | claude-instant-1.2 |
| API format | Messages & Text Completions API | Messages & Text Completions API | Messages & Text Completions API |
| Comparative latency | Slower than Claude 3 model of similar intelligence | Slower than Claude 3 model of similar intelligence | Slower than Claude 3 model of similar intelligence |
| Context window | |||
| Max output | |||
| Cost (Input / Output per ) | $8.00 / $24.00 | $8.00 / $24.00 | $0.80 / $2.40 |
| Training data cut-off | Early 2023 | Early 2023 | Early 2023 |
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.
Check out our quickstart guide for step-by-step instructions on how to get up and running with Claude. You’ll learn how to create an account, obtain API keys, and start interacting with our models in no time. You can also head over to claude.ai or our web Console to start experimenting with Claude right away!
If you have any questions or need assistance, don’t hesitate to reach out to our support team or consult the Discord community.