Claude 3.5 Haiku

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

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 a similar speed to 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 is available 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 $1 per million input tokens and $5 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.

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

Head of AI 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

We’ve been testing Claude 3.5 Haiku for sales email generation, and we’re seeing better performance compared to our previous model. What stands out is the improvement in writing style - the emails feel more natural and on-brand. This kind of nuanced communication is exactly what we need for effective sales outreach.

Tyler Phillips

Principal Product Manager, AI Platform, Apollo

Our early testing for Claude 3.5 Haiku validates a lot of what Anthropic is saying—it has made a huge leap in intelligence. It’s head and shoulders above Claude 3 Haiku. We’re excited to integrate it with our new Replit Agent free experience.

Michele Catasta

President at Replit

Frequently asked questions

When should I use Claude 3.5 Haiku?

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.

How much does it cost to use Claude 3.5 Haiku?

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