Qwen3 32B per token, in reais

Confidential Roda em enclave lacrado por hardware. Tamanho médio, boa relação entre qualidade e preço para uso geral.

Where it does well

Sensitive data: the model runs inside a hardware-sealed enclave and not even the machine operator reads the prompt. Context window of 128,000 tokens.

Where it is not the best choice

The last drop of quality — these are open-weight models, not frontier ones.

How to use it on GPUBrasil

The API speaks the OpenAI format. Swap the base_url, use a gpub_live_ key and pass gpub-selado-qwen32 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="gpub-selado-qwen32",
    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 Qwen3 32B cost on GPUBrasil?

R$ 0.70 per 1 million input tokens and R$ 2.90 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 Qwen3 32B?

The API is OpenAI-compatible. Point base_url at https://gpubrazil.com/v1, use a gpub_live_ key and pass gpub-selado-qwen32 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 Qwen3 32B?

128,000 tokens, counting what you send plus what the model answers in the same call.

Similar models