Claude Fable 5 per token, in reais

Frontier O modelo mais capaz da Anthropic, para raciocínio pesado e trabalho autônomo longo. Pensa sempre.

Where it does well

The problem the others cannot solve — long reasoning and hours-long autonomous work. Context window of 1,000,000 tokens.

Where it is not the best choice

Anything cost- or latency-sensitive; it is the most expensive model in the catalogue.

What you save

The maker's list price is US$ 50.00 per 1M output tokens. At R$ 5.17 to the dollar plus Brazil's 3.5% IOF tax, buying direct costs about R$ 267.44 — against R$ 239.90 here, or 10% less.

And there is a difference in kind beyond the number: the price here is fixed in reais, so a rising dollar does not change your bill.

How to use it on GPUBrasil

The API speaks the OpenAI format. Swap the base_url, use a gpub_live_ key and pass claude-fable-5 as the model.

from openai import OpenAI

client = OpenAI(
    base_url="https://gpubrazil.com/v1",
    api_key="gpub_live_...",
)

r = client.chat.completions.create(
    model="claude-fable-5",
    messages=[{"role": "user", "content": "Explain what a token is."}],
)
print(r.choices[0].message.content)

The same endpoint works in Cursor, Cline, Continue, Zed, Aider, Open WebUI and LibreChat — they all accept an OpenAI-compatible endpoint.

Create an account →   See every model and price →

FAQ

How much does Claude Fable 5 cost on GPUBrasil?

R$ 47.95 per 1 million input tokens and R$ 239.90 per 1 million output tokens, billed in Brazilian reais. No subscription and no minimum purchase — you pay only for the tokens you use.

How do I call Claude Fable 5?

The API is OpenAI-compatible. Point base_url at https://gpubrazil.com/v1, use a gpub_live_ key and pass claude-fable-5 as the model. It works with the OpenAI SDK and with tools like Cursor, Cline, Continue, Zed and Open WebUI with no adaptation.

What is the context window of Claude Fable 5?

1,000,000 tokens, counting what you send plus what the model answers in the same call.

Similar models