Claude 3.5 Haiku

Claude 3.5 Haiku
Claude 3.5 Haiku

Our fastest model, delivering advanced coding, tool use, and reasoning at an accessible price

    Explore the 3.5 Haiku model card

    Announcements

    • New

      Claude 3.5 Haiku and a new Claude 3.5 Sonnet

      Oct 22, 2024

      Claude 3.5 Haiku is the next generation of our fastest model. For the same cost and similar speed as Claude 3 Haiku, Claude 3.5 Haiku improves across every skill set and surpasses Claude 3 Opus, the largest model in our previous generation, on many intelligence benchmarks.

      Read more

    Availability and pricing

    Claude 3.5 Haiku will be made available later this month across our first-party API, Amazon Bedrock, and Google Cloud’s Vertex AI—initially as a text-only model and with image input to follow.

    Pricing for Claude 3.5 Haiku starts at $0.25 per million input tokens and $1.25 per million output tokens, with up to 90% cost savings with prompt caching and 50% cost savings with the Message Batches API. To learn more, check out our pricing page.

    Use cases

    With fast speeds, improved instruction following, and more accurate tool use, Claude 3.5 Haiku is well suited for user-facing products, specialized sub-agent tasks, and generating personalized experiences from huge volumes of data. Popular use cases include:

    Code completions

    Claude 3.5 Haiku offers quick, accurate code suggestions and completions to accelerate development workflows. It's ideal for software teams looking to streamline their coding process and boost productivity.

    Interactive chatbots

    With enhanced conversational abilities and rapid response times, Claude 3.5 Haiku excels at powering responsive chatbots that can handle high volumes of user interactions. It's particularly valuable for customer service, e-commerce, and educational platforms requiring scalable engagement.

    Data extraction and labeling

    Claude 3.5 Haiku efficiently processes and categorizes information, making it effective for rapid data extraction and automated labeling tasks. This capability is especially useful for organizations dealing with large volumes of unstructured data across finance, healthcare, and research.

    Real-time content moderation

    Claude 3.5 Haiku provides reliable, immediate content moderation through its improved reasoning and content understanding capabilities. This makes it valuable for social platforms, online communities, and media organizations that need to maintain safe, appropriate content at scale.

    Benchmarks

    Claude 3.5 Haiku offers strong performance and speed across a variety of coding, tool use, and reasoning tasks.

    These benchmarks measure how large language models like Claude 3.5 Haiku compare on key academic and practical skills.

    Trust & Safety

    Anthropic's commitment to safety shapes every step of our AI development. During Claude 3.5 Haiku’s development, we conducted extensive safety evaluations spanning multiple languages and policy domains. We also enhanced Claude's ability to navigate sensitive content with appropriate care. Our internal testing confirms that Claude 3.5 Haiku delivers substantial advances in capabilities while upholding our rigorous safety standards.

    Our initial testing of Claude 3.5 Haiku has been very promising. We were particularly impressed by its performance in reasoning tasks, where it significantly exceeded our expectations. We’re excited about how this advancement could enhance our AI-assisted problem-solving capabilities and upcoming features.
    James Peterson
    Product Analyst at Fathom Video
    Claude 3.5 Haiku exceeded our expectations, handling complex tasks with impressive skill. It consistently outperformed, even when pushed to its limits. We were genuinely surprised and impressed by Claude 3.5 Haiku’s versatility and robust capabilities across a wide range of challenges.
    João Paulo Martins
    CTO at Advolve
    Claude 3.5 Haiku shows impressive reasoning and code generation abilities, including demonstrating powerful multi-turn code refinement which reduced code-related errors by 60%, and puts it in the same territory as substantially bigger models.
    Sean Ward
    CEO at iGent

    Frequently asked questions

    We offer a family of Claude models across the spectrum of speed, price, and performance. Claude 3.5 Haiku is our fastest model to date. We recommend Claude 3.5 Haiku for critical use cases where low latency matters, like user-facing chatbots and code completions.

    Pricing depends on how you want to use Claude 3.5 Haiku. To learn more, check out our pricing page.