Claude Haiku 4.5 Economy

Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence with significantly lower cost and latency than larger Claude models. With performance comparable to Claude Sonnet 4 across reasoning, coding, and computer-use tasks, it brings advanced capabilities to real-time, high-volume applications. As the first Haiku model to support extended thinking, Haiku 4.5 offers adjustable reasoning depth, summarized or interleaved thinking, and tool-assisted workflows spanning coding, Bash, web search, and computer use. Scoring over 73% on SWE-bench Verified, it ranks among the world’s leading coding models while remaining highly responsive for sub-agent orchestration, parallel execution, and large-scale deployment.

Claude Haiku 4.5 Economy

As the first Haiku model to support extended thinking, Haiku 4.5 offers adjustable reasoning depth, summarized or interleaved thinking, and tool-assisted workflows spanning coding, Bash, web search, and computer use. Scoring over 73% on SWE-bench Verified, it ranks among the world’s leading coding models while remaining highly responsive for sub-agent orchestration, parallel execution, and large-scale deployment.

Base URL

https://api.icreat.ai/llm/anthropic

Authentication

All API requests must be authenticated with an API Key. You can obtain an API Key from the console.

export ICREAT_API_KEY="your-api-key-here"

HTTP Request Headers

import os

API_KEY = os.environ.get("ICREAT_API_KEY")
headers = {
    "Content-Type": "application/json",
    "Authorization": "Bearer " + API_KEY,
}

Protect your API Key

Never expose your API Key in client-side code or public repositories. Use environment variables or a backend proxy.

Code Examples

This model is invoked via the Anthropic-compatible Messages API, supporting streaming and non-streaming modes.

POST/v1/messages

curl --fail-with-body --connect-timeout 10 --max-time 60 \
  -X POST https://api.icreat.ai/llm/anthropic/v1/messages \
  -H "Authorization: Bearer ${ICREAT_API_KEY}" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "claude-haiku-4-5",
  "messages": [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "Which is healthier, coffee or tea?"}
  ],
  "stream": false
}'

Input Schema

Total: 4 Required: 2 Optional: 2

modelstringrequired

Model ID. Must be iCreat model_code (claude-haiku-4-5).

messagesarray[object]required

Conversation messages.

max_tokensinteger

Maximum tokens to generate.

streamboolean

Whether to stream the response.

Output Schema

Anthropic Messages compatible response.

Total: 4

idstring

Message ID.

typestring

Object type, always message.

rolestring

Role, always assistant.

contentarray[object]

Content blocks from the model.

LLM-friendly prompt

Below is an LLM-friendly Markdown prompt you can copy into Cursor, ChatGPT, or other AI assistants to help them understand this model's API integration, call flow, and key parameters.

# claude-haiku-4-5

> Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence with significantly lower cost and latency than larger Claude models.

## Overview

Call via iCreat Anthropic-compatible Messages API; supports streaming and non-streaming.

## API Info

- **Base URL**: `https://api.icreat.ai/llm/anthropic`
- **Endpoint (POST)**: `/v1/messages`
- **Model ID**: `claude-haiku-4-5`
- **Auth**: `Authorization: Bearer ${ICREAT_API_KEY}`

## Call Flow

Single POST; `stream: false` returns full JSON, `stream: true` streams via SSE.

### Input

- `model` (required): iCreat model_code `claude-haiku-4-5`
- `messages` (required): conversation messages
- Common optional: `max_tokens`, `stream`

### Output

- Read reply from `content` text blocks (e.g. `content[0].text`)

## Notes

- `model` must be the iCreat model_code
- Other fields follow the Anthropic Messages protocol