Claude Haiku 4.5
Anthropic's fastest, most affordable AI model that delivers near-frontier coding performance at one-third the cost of premium models.
What is Claude Haiku 4.5?
Claude Haiku 4.5 is Anthropic's smallest, fastest AI model that punches way above its weight class.
It matches the coding performance of Claude Sonnet 4 (which was state-of-the-art five months ago) but runs twice as fast and costs just $1 per million input tokens versus $3 for Sonnet.
Most builders use it for high-volume tasks like customer support bots, rapid prototyping, or orchestrating multiple AI agents in parallel. It's the first Haiku model with extended thinking, computer use, and context awareness built in.
Scores 73.3% on SWE-bench Verified (real GitHub coding tasks). Available through Claude.ai or the API at $1/$5 per million input/output tokens.
Good to Know
Costs $1/$5 per million input/output tokens (one-third the price of Sonnet 4.5)
Runs twice as fast as Claude Sonnet 4 with similar coding performance
First Haiku model with extended thinking, computer use, and context awareness
Supports 200K token context window with up to 64K output tokens
Scores 73.3% on SWE-bench Verified (real-world coding benchmark)
How Vibe Coders Use Claude Haiku 4.5
Running customer support chatbots that handle thousands of conversations daily without breaking the bank
Prototyping new features fast by having Haiku write and test code in seconds
Building multi-agent systems where Sonnet plans the work and multiple Haiku agents execute subtasks in parallel
Powering real-time pair programming tools that need to respond instantly as you type
Frequently Asked Questions
Related Terms
Reusable instruction packages that teach Claude how to complete specific tasks consistently, loaded dynamically only when needed.
The practice of crafting specific instructions to get better outputs from AI models like ChatGPT, Claude, or Gemini.
Anthropic's most capable AI model, optimized for complex coding, long-running tasks, and enterprise workflows with a 1M token context window.
AI safety company that builds Claude, a large language model focused on being helpful, honest, and harmless with strong reasoning capabilities.
Anthropic's mid-tier AI model released September 2025, optimized for coding and agentic tasks with a 200k token context window.
Join 0 others building with AI