Official

anthropic / claude-3.5-sonnet

Anthropic's most intelligent language model to date, with a 200K token context window and image understanding (claude-3-5-sonnet-20241022)

  • Public
  • 8.7K runs
  • License
Run with an API
Playground API Examples README

Pricing

Official model
Pricing for official models works differently from other models. Instead of being billed by time, you’re billed by input and output, making pricing more predictable.
Learn more

This language model is priced by how many input tokens are sent as inputs and how many output tokens are generated.

Check out our docs for more information about how per-token pricing works on Replicate.

Readme

Claude 3.5 Sonnet

Claude 3.5 Sonnet is Anthropic’s latest frontier large language model, offering state-of-the-art performance with significantly improved speed and cost-effectiveness compared to previous models.

This Replicate model is built on claude-3-5-sonnet-20241022, hosted on Anthropic and Vertex APIs.

Key features

  • Best-in-class performance on graduate-level reasoning (GPQA), undergraduate knowledge (MMLU), and coding (HumanEval)
  • 2x faster inference speed compared to Claude 3 Opus
  • 200K token context window
  • Advanced vision capabilities for interpreting images, charts, and graphics
  • Exceptional natural language understanding and generation
  • Industry-leading safety and privacy protections

Use cases

  • Complex customer support
  • Multi-step workflow orchestration
  • Code generation and debugging
  • Legacy code migration
  • Visual analysis and interpretation
  • Content generation with natural tone
  • Academic and research assistance

Limitations

  • Model does not learn from user interactions
  • No persistent memory between sessions
  • Subject to hallucinations and potential biases
  • Cannot access real-time information
  • Limited to text and image inputs

Safety

  • Rigorous safety testing and red teaming conducted
  • Evaluated by UK and US AI Safety Institutes
  • Enhanced safety mechanisms based on expert feedback
  • No training on user data without explicit consent
  • Built-in safeguards against misuse

Getting started

To use Claude 3.5 Sonnet via Replicate:

import replicate

output = replicate.run(
    "anthropic/claude-3.5-sonnet",
    input={
        "prompt": "Your prompt here"
    }
)

Privacy policy & license

Data from this model is sent to Anthropic and Google Cloud Vertex AI.

Usage of this model is subject to Anthropic’s terms of service. Please refer to their website for full terms and conditions.