Skip to main content
MindStudio
Pricing
BlogAbout
My Workspace
Text Generation Model

Claude 4.5 Haiku

Claude 4.5 Haiku is a text generation model from Anthropic with a 200,000-token context window and image input support.

PublisherAnthropic
TypeText
Context Window200,000 tokens
ReleasedOctober 2025
Input$1.00/MTok
Output$5.00/MTok

Fast, vision-capable text generation from Anthropic

Claude 4.5 Haiku is a large language model developed by Anthropic, released in October 2025. It belongs to the Haiku tier of Anthropic's Claude model family, which is designed for tasks that require low latency and high throughput. The model supports a 200,000-token context window and can process image inputs alongside text, making it suitable for multimodal workflows.

Claude 4.5 Haiku is well-suited for applications that need to handle long documents, extended conversations, or image-based queries at scale. Its maximum response size of 64,000 tokens allows for detailed outputs without truncation in most use cases. Developers typically reach for Haiku-tier models when building production systems where response speed and cost efficiency are priorities alongside capable language understanding.

What Claude 4.5 Haiku supports

Long Context Window

Processes up to 200,000 tokens of input in a single request, enabling analysis of long documents, codebases, or extended conversation histories.

Image Understanding

Accepts image inputs alongside text prompts, allowing the model to describe, analyze, or answer questions about visual content.

Extended Response Output

Generates responses up to 64,000 tokens, supporting detailed summaries, long-form drafts, and comprehensive code outputs in a single reply.

Instruction Following

Handles structured prompts and multi-step instructions, making it suitable for agentic workflows and tool-use pipelines.

Low-Latency Chat

Designed for high-throughput, responsive interactions, making it appropriate for real-time chat interfaces and production API integrations.

Ready to build with Claude 4.5 Haiku?

Get Started Free

Benchmark scores

Scores represent accuracy — the percentage of questions answered correctly on each test.

BenchmarkWhat it testsScore
MMLU-ProExpert knowledge across 14 academic disciplines80.0%
GPQA DiamondPhD-level science questions (biology, physics, chemistry)64.6%
LiveCodeBenchReal-world coding tasks from recent competitions51.1%
HLEQuestions that challenge frontier models across many domains4.3%
SciCodeScientific research coding and numerical methods34.4%

Common questions about Claude 4.5 Haiku

What is the context window size for Claude 4.5 Haiku?

Claude 4.5 Haiku supports a context window of 200,000 tokens, allowing it to process large documents or long conversation histories in a single request.

Does Claude 4.5 Haiku support image inputs?

Yes. Claude 4.5 Haiku accepts image inputs alongside text, enabling multimodal tasks such as image description and visual question answering.

What is the maximum response length for Claude 4.5 Haiku?

The model can generate responses of up to 64,000 tokens per reply, which accommodates detailed outputs such as long-form documents or extensive code.

When was Claude 4.5 Haiku released?

Claude 4.5 Haiku was released in October 2025 by Anthropic.

What is Claude 4.5 Haiku best suited for?

It is designed for use cases that require fast response times and high throughput, such as real-time chat applications, document analysis, and production API integrations where latency and cost efficiency matter.

Parameters & options

Max Temperature1
Max Response Size64,000 tokens
ReasoningSelect

When enabled, the model will explain its thought process step-by-step before providing a final answer. This can help users understand how the model arrived at its conclusions, but may result in longer responses.

Default: false
DisabledEnabled
Max Reasoning SizeNumber

You can allocate a larger thinking budget to support more thorough reasoning. Must be less than max. response size

Range: 1024–32000
ToolsTools
Web SearchAllow models to search the web for the latest information before generating a response.
Web FetchAllow models to retrieve full content from specified web pages and PDF documents
Code ExecutionAllow models to write and run code to solve problems.
mcpServersMCP Servers

Start building with Claude 4.5 Haiku

No API keys required. Create AI-powered workflows with Claude 4.5 Haiku in minutes — free.