Claude 4.5 Haiku
Anthropic's fastest and most efficient model, delivering frontier-level coding performance at a fraction of the cost and more than twice the speed of its predecessors.
Anthropic Fast, efficient coding and reasoning at scale
Claude 4.5 Haiku is a lightweight text generation model developed by Anthropic, released in October 2025. It is designed to deliver high throughput and low latency while maintaining strong performance on coding and reasoning tasks. The model supports a 200,000-token context window and can generate up to 64,000 tokens in a single response, making it capable of handling long documents and complex multi-turn conversations. It accepts text, images, and PDFs as input and is available through Anthropic's API, AWS Bedrock, and Google Cloud Vertex AI.
Claude 4.5 Haiku is built for production applications where speed and cost efficiency are priorities, such as customer support systems, real-time coding assistants, document processing pipelines, and autonomous AI agents. It supports tool calling, reasoning, and multi-step workflow automation, enabling agentic use cases without requiring a heavier model. Its knowledge cutoff is February 2025. Developers looking to build high-volume applications will find it suited to scenarios where response time and per-token cost are key constraints.
What Claude 4.5 Haiku supports
Large Context Window
Processes up to 200,000 tokens of input in a single request, enabling analysis of lengthy documents, large codebases, and extended conversations.
Extended Output
Generates up to 64,000 tokens in a single response, supporting long-form code generation, detailed reports, and multi-step outputs.
Coding Performance
Delivers strong results on coding tasks, producing code generation and debugging outputs comparable to heavier models at lower cost and higher speed.
Multimodal Input
Accepts text, images, and PDFs as input, allowing document analysis and vision-based tasks within the same model.
Tool Calling & Agents
Supports tool calling and multi-step workflow automation, enabling integration into agentic pipelines that require external API calls or sequential reasoning.
Built-in Reasoning
Includes a reasoning mode that allows the model to work through complex problems step by step before producing a final answer.
High Throughput Speed
Optimized for low-latency responses, making it suitable for real-time applications such as live coding assistants and customer support bots.
Ready to build with Claude 4.5 Haiku?
Get Started FreeBenchmark scores
Scores represent accuracy — the percentage of questions answered correctly on each test.
| Benchmark | What it tests | Score |
|---|---|---|
| MMLU-Pro | Expert knowledge across 14 academic disciplines | 80.0% |
| GPQA Diamond | PhD-level science questions (biology, physics, chemistry) | 64.6% |
| LiveCodeBench | Real-world coding tasks from recent competitions | 51.1% |
| HLE | Questions that challenge frontier models across many domains | 4.3% |
| SciCode | Scientific research coding and numerical methods | 34.4% |
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, long codebases, and extended conversations in a single request.
What is the knowledge cutoff date for Claude 4.5 Haiku?
Claude 4.5 Haiku has a knowledge cutoff of February 2025, meaning it does not have information about events that occurred after that date.
Where can I access Claude 4.5 Haiku via API?
Claude 4.5 Haiku is available through Anthropic's own API, as well as through AWS Bedrock and Google Cloud Vertex AI.
What input types does Claude 4.5 Haiku support?
The model accepts text, images, and PDFs as input, supporting both purely text-based and multimodal use cases.
Does Claude 4.5 Haiku support agentic workflows?
Yes. Claude 4.5 Haiku supports tool calling, reasoning, and multi-step workflow automation, making it compatible with agentic application architectures.
Documentation & links
Parameters & options
Explore similar models
Anthropic Claude 4.6 Sonnet
Anthropic's most capable Sonnet model yet, delivering near-Opus-level intelligence for coding, agents, and computer use with a 1M token context window.
Anthropic Claude 4.6 Opus
Anthropic's most intelligent model, setting new standards in agentic coding, complex reasoning, and professional knowledge work.
Anthropic Claude 4.5 Opus
Anthropic's most powerful flagship model, setting the state of the art in coding, agentic workflows, and real-world computer use.
Google Gemini 3.1 Pro
Google's frontier reasoning model delivering enhanced software engineering, agentic reliability, and multimodal intelligence across a 1M-token context window.
OpenAI GPT‑5.2 Pro
The most capable model series yet for professional knowledge work.
Nvidia Nemotron 3 Nano 30B
NVIDIA's compact open-weight hybrid MoE model with 30B total / 3.5B active parameters, delivering strong reasoning and coding performance up to 1M context.
Start building with Claude 4.5 Haiku
No API keys required. Create AI-powered workflows with Claude 4.5 Haiku in minutes — free.