Roar AI
Get started
All models
Anthropic · Chat

Claude Haiku 4.5 API in Singapore

Anthropic’s smallest, fastest model, for chat, support and work split across many small agents. Priced in Singapore dollars for teams in Singapore, on the same key as every other model.

InputS$1.34per 1M tokens
OutputS$6.70per 1M tokens
BillingOne bill, in SGDwith every other model

Claude Haiku 4.5 API pricing in Singapore

InputS$1.34 per 1M tokens · $1.03
OutputS$6.70 per 1M tokens · $5.15
Cached inputS$0.1339 per 1M tokens · $0.103
Cache writeS$1.67 per 1M tokens · $1.2875
Batch inputS$0.6695 per 1M tokens · $0.515
Batch outputS$3.35 per 1M tokens · $2.575

In Singapore dollars, the currency your card is charged in, with the published US dollar rate beside each.

For scale: 1,000 requests of about 3,000 tokens in and 1,000 out cost S$10.71 — a long prompt and a page of answer each. Every rate is published and stays the same from one request to the next. See every model.

Prices are our published US dollar rates converted at S$1.30 to the dollar, our rate for October — the same rate your card is charged.

About Claude Haiku 4.5

Haiku 4.5 is the quick one. When it came out in October 2025 it matched the coding of the then-current Sonnet 4 at a third of the cost and more than twice the speed, scoring 73.3% on SWE-bench Verified. It was also the first Haiku that could think before answering and operate a computer.

Anthropic pitches it as a worker a bigger model directs — many Haikus running in parallel under one Opus — and for anything a customer waits on, like live chat. It is the oldest model in Anthropic’s current line, and that shows in what it knows.

What is Claude Haiku 4.5 good for?

  • Live chat and customer-support agents, where speed matters most.
  • Sub-agents running in parallel under a larger model.
  • High-volume sorting, tagging and data extraction.
  • Quick coding help and prototypes.

Where to be careful

  • Its knowledge is old: reliable to February 2025, more than a year behind the 5.x models.
  • Anthropic only guarantees it until mid-October 2026. For new work, plan for a successor.
  • Smaller limits than newer models: 200K tokens of context and 64K of output.

Specs

Made byAnthropic
ReleasedOctober 2025
TypeChat
Context window200K tokens
Longest answer64K tokens
ReadsText, Images, PDFs
Thinks before answeringYes, adjustable
WeightsClosed
Processed inGlobal
Model idclaude-haiku-4-5

Using Claude Haiku 4.5 from Singapore

Roar AI provides access to Claude Haiku 4.5 through the Roar AI gateway, charged in Singapore dollars on one bill with every other model. Requests from Singapore go through our gateway in Singapore. Developers can use Claude Haiku 4.5 alongside other supported models without a separate integration for every provider.

Use the OpenAI SDK you already have — point it at Roar AI and name the model. Read the docs.

from openai import OpenAI

client = OpenAI(base_url="https://api.roar-ai.com/v1", api_key="roar_live_…")

reply = client.chat.completions.create(
    model="claude-haiku-4-5",
    messages=[{"role": "user", "content": "Summarise this contract in plain English."}],
)

Where is Claude Haiku 4.5 processed?

Claude Haiku 4.5 is a frontier model, and requests are processed on international infrastructure, outside Singapore. The model directory says where each model is processed.

Questions

How much does Claude Haiku 4.5 cost in Singapore?

Input is S$1.34 per 1M tokens; output is S$6.70 per 1M tokens. For scale, 1,000 requests of about 3,000 tokens in and 1,000 out cost S$10.71. Prices are our published US dollar rates converted at S$1.30 to the dollar, our rate for October — the same rate your card is charged. The rate is published and does not change from one request to the next.

Is Claude Haiku 4.5 open source?

No. Anthropic does not publish the weights, so it is only available through an API like this one.

Try Claude Haiku 4.5
on one key

Sign up, get a key and call it with the SDK you already use. Pay in your local currency, on one bill.