Claude Fable 5.1 API in Australia

In Australian 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 A$121.13 — 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 A$1.47 to the dollar, our rate for October — the same rate your card is charged.

Fable 5.1 sits above Opus in Anthropic’s lineup. It is the model for jobs that take a long time and many steps: an agent that plans, uses tools across several applications, recovers when something breaks and checks its own work before it reports back. Anthropic’s numbers show where the jump is — 55.8% on Terminal-Bench 4.0, up from 42.0% for Fable 5, and 65.0% on Humanity’s Last Exam with tools.

It always thinks before it answers. You choose how hard, from low to max effort, and the default is high. That makes it the slowest model Anthropic sells, so it earns its place on problems a cheaper model gets wrong, not on everyday drafting.

It reads text, images and PDFs, holds up to a million tokens in one request — a large codebase or a long set of documents at once — and can write answers up to 128K tokens long. It calls tools and works across several applications within a single task, which is what its agent results measure.

• Long-running coding agents that work through a large change on their own.
• Research that has to verify its own findings before it reports.
• Building finished documents, spreadsheets and slide decks from a brief.
• The hardest reasoning problems, where Opus still falls short.

• Slow. Anthropic rates it the slowest model in its current lineup, so it is a poor fit for anything a person sits waiting on.
• Requests touching cybersecurity or biology can trip Anthropic’s safety filters and be refused or handed to an older model.
• Check whether Opus 5.5 or Sonnet 5.5 already does the job first. For most work, they do.

Roar AI provides access to Claude Fable 5.1 through the Roar AI gateway, charged in Australian dollars on one bill with every other model. Requests from Australia go through our gateway in Singapore today; a gateway in Sydney is coming. Developers can use Claude Fable 5.1 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-fable-5-1",
    messages=[{"role": "user", "content": "Summarise this contract in plain English."}],
)

Claude Fable 5.1 is a frontier model, and requests are processed on international infrastructure, outside Australia. The model directory says where each model is processed.

Claude Fable 5.1 vs GPT-6 AstraHead to headClaude Opus 5Similar priceClaude Opus 5.5Similar priceGPT-5.6 SolSimilar price

Every Claude model: Claude API. Explore all AI models available in Australia