Loading page
LightweightAnthropic
Claude 3.5 Haiku
Claude 3.5 Haiku is Anthropic's lightweight model designed for fast responses and high-volume tasks, featuring text and image input with a 200K token context window.
Context 200K
Tier Lightweight
Knowledge Apr 2024
Tools Supported
Modalities text, image
Input from
$0.800 / 1M tokens
across 1 provider
API Pricing
| Provider | Input / 1M | Output / 1M |
|---|---|---|
| $0.800 | $4.00 |
Prices updated daily. Last check: Sep 6, 2026
Claude 3.5 Haiku pricing by provider
Input, output, and batch rates, plus alternatives, for one provider at a time.
Performance & Benchmarks
Source: Artificial Analysis →Intelligence
6.5 / 100
Coding
15.9 / 100
Reasoning & Knowledge
- MMLU-Pro63.4%
- GPQA Diamond40.8%
- Humanity's Last Exam3.6%
Coding
- LiveCodeBench31.4%
Math
- AIME3.3%
- MATH-50072.1%
Agentic & Tool Use
- Terminal-Bench Hard2.3%
- Terminal-Bench v2.110.1%
- τ²-bench24.6%
Instruction & Long Context
- IFBench42.8%
- Long-Context Reasoning27.3%
Benchmarks measured Sep 2026. Scores are independent evaluations, not vendor-reported.
Model Details
General
- Creator
- Anthropic
- Family
- Haiku
- Tier
- Lightweight
- Context Window
- 200K
- Knowledge Cutoff
- Apr 2024
- Modalities
- Text, Image
Capabilities
- Tool Calling
- Yes
- Open Source
- No
- Subtypes
- Chat Completion
Strengths & Limitations
Strengths
- 200,000 token context window allows processing of lengthy documents
- Supports both text and image input modalities
- Tool calling functionality enables integration with external APIs and systems
- Optimized for speed with faster response times than larger models in the family
- Multimodal capabilities in a lightweight model tier
- April 2024 knowledge cutoff provides relatively recent training data
- Chat completion format supports conversational applications
Limitations
- Proprietary model with no open-source weights available
- Lightweight tier means reduced reasoning capability compared to Opus variants
- No video input support, limited to text and static images
- Older model generation as Anthropic has released Claude Opus 4.6
- Knowledge cutoff predates some competing models with more recent training data
Key Features
•200,000 token context window
•Text and image input processing
•Tool calling with function execution
•Chat completion API format
•Streaming response support
•Multimodal vision capabilities
•JSON mode for structured outputs
•Batch processing compatibility
About Claude 3.5 Haiku
Claude 3.5 Haiku is Anthropic's lightweight model in the Claude 3.5 series, positioned as the fastest and most cost-effective option in the family. While Anthropic has released more capable models like Claude Opus 4.6, Haiku serves as the efficiency-focused tier for applications requiring quick responses and high throughput.
The model supports both text and image inputs with a 200,000 token context window, enabling it to process lengthy documents and maintain extended conversations. Claude 3.5 Haiku includes tool calling capabilities and maintains a knowledge cutoff of April 2024. Despite its lightweight positioning, it handles multimodal inputs and can process visual content alongside text prompts.
Claude 3.5 Haiku is commonly used for applications where speed and cost efficiency are prioritized over maximum reasoning capability, such as content moderation, customer support automation, and high-volume text processing tasks. It competes with other lightweight models in the market while offering Anthropic's safety-focused approach and multimodal capabilities.
Common Use Cases
Claude 3.5 Haiku is well-suited for high-volume applications requiring fast processing speeds and cost efficiency. Its lightweight design makes it ideal for tasks like content moderation, customer support chatbots, document summarization, and automated text classification. The 200K context window enables processing of lengthy documents, research papers, or extended conversation histories. Its multimodal capabilities allow for applications involving image analysis combined with text processing, such as document OCR, visual content moderation, or image captioning at scale. Organizations choosing Haiku typically prioritize response speed and operational efficiency over the maximum reasoning capabilities found in larger models.
Frequently Asked Questions
How much does Claude 3.5 Haiku cost per million tokens?
Claude 3.5 Haiku pricing varies by provider and pricing type (standard vs batch). Check the pricing table above for current rates across all providers offering this model.
What is Claude 3.5 Haiku best used for?
Claude 3.5 Haiku excels at high-volume tasks requiring fast responses, such as content moderation, customer support automation, document processing, and text classification. Its 200K context window and multimodal capabilities make it suitable for applications processing lengthy documents with images, while maintaining cost efficiency.
How does Claude 3.5 Haiku compare to other lightweight models?
Claude 3.5 Haiku offers a larger 200,000 token context window than many lightweight competitors, plus multimodal image processing capabilities. It includes tool calling functionality and maintains Anthropic's safety-focused training approach, though it trades maximum speed for these additional capabilities compared to text-only lightweight alternatives.