Claude Haiku 4.5 API
Claude's fastest and most affordable model. Perfect for chat, classification, and high-volume tasks.
💰 Save up to 70% vs official Anthropic pricingTechnical Specifications
| Provider | Anthropic |
| Model Family | Claude Haiku 4.5 |
| Release Date | 2026-05 |
| Context Window | 200K |
| Max Output Tokens | 8,192 |
| Input Price | $1.00 / 1M tokens |
| Output Price | $5.00 / 1M tokens |
| Vision Support | Yes ✓ |
| Function Calling | Yes ✓ |
| JSON Mode | No |
| Streaming | Yes ✓ |
| Fine Tuning | Not Available |
| Status | Active ✓ |
Overview
Claude Haiku 4.5 is Anthropic's current haiku-class AI model, released in 2026-05. Claude's fastest and most affordable model. Perfect for chat, classification, and high-volume tasks.
With a 200K context window and maximum output of 8,192 tokens, Claude Haiku 4.5 is well-suited for fastest claude and budget-friendly. At $1.00/1M input and $5.00/1M output, it offers balanced pricing within the Anthropic ecosystem.
Claude Haiku 4.5 supports 3 capabilities: Vision, Tool Use, Streaming. Fine-tuning is not available for this model. The model serves as an fastest claude solution for developers building multimodal AI applications.
Through AI API Hub, you can access Claude Haiku 4.5 with USDT & USDC payments, no credit card required. All via a fully OpenAI-compatible API — just change your base URL and start building in 30 seconds.
API Examples
Python
from openai import OpenAI
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="https://api.apiyihe.org/v1"
)
response = client.chat.completions.create(
model="claude-haiku-4.5",
messages=[
{"role": "user", "content": "Hello"}
]
)
print(response.choices[0].message.content)JavaScript / Node.js
import OpenAI from "openai";
const client = new OpenAI({
apiKey: process.env.API_KEY,
baseURL: "https://api.apiyihe.org/v1"
});
const response = await client.chat.completions.create({
model: "claude-haiku-4.5",
messages: [
{ role: "user", content: "Hello" }
]
});
console.log(response.choices[0].message.content);cURL
curl https://api.apiyihe.org/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "claude-haiku-4.5",
"messages": [
{"role": "user", "content": "Hello"}
]
}'Compare Alternatives
Frequently Asked Questions
What is Claude Haiku 4.5?
Claude Haiku 4.5 is Anthropic's current haiku model. Claude's fastest and most affordable model. Perfect for chat, classification, and high-volume tasks.. It features a 200K context window, supports Vision, Tool Use, Streaming, and is available through AI API Hub with USDT/USDC payments.
How much does Claude Haiku 4.5 cost?
Claude Haiku 4.5 pricing: $1.00 per 1M input tokens, $5.00 per 1M output tokens. Pay-as-you-go with no minimum commitment. Sign up at AI API Hub and start with as little as $5.
Claude Haiku 4.5 vs GPT-5.5?
Claude Haiku 4.5: $1.00/$1M input, 200K context. GPT-5.5: $5.00/$1M input, 256K context. Claude Haiku 4.5 is more cost-effective. Fastest Claude. Compare them at /compare/claude-haiku-4.5-vs-gpt-5.5/.
Claude Haiku 4.5 context window?
Claude Haiku 4.5 has a 200K context window, capable of processing up to 200,000 tokens in a single request. Maximum output tokens: 8,192.
Does Claude Haiku 4.5 support function calling?
Yes, Claude Haiku 4.5 supports function/tool calling, allowing you to define functions that the model can invoke. This enables AI agents, API integrations, and structured data extraction.
Is Claude Haiku 4.5 multimodal?
Partially — Claude Haiku 4.5 supports vision (image input) but not native audio processing.
Claude Haiku 4.5 API rate limits?
Claude Haiku 4.5 rate limits: 10K RPM. Higher tier plans offer increased throughput. For high-volume production use, consider Anthropic's faster variant models.
How to access Claude Haiku 4.5 API?
Access Claude Haiku 4.5 through AI API Hub: (1) Register at api.apiyihe.org/register?aff=8JZC, (2) Deposit USDT/USDC, (3) Get your API key instantly, (4) Use the OpenAI-compatible endpoint https://api.apiyihe.org/v1 with model name "claude-haiku-4.5". Start building in under 30 seconds.