Qwen3.6 35B A3B API

Sobre Qwen3.6 35B A3B

Qwen3.6 35B A3B is a 256-expert mixture-of-experts reasoning model with 128K context, function tools, and strict structured JSON output.

Text-only. This build does not accept image or video input, unlike the base Qwen3.6 35B A3B. Weights Served from the 2-bit eschamoe W2 build published by Escha Labs (eschalabs.com) as EschaLabs/Qwen3.6-35B-A3B-Escha-W2 on Hugging Face, under Apache-2.0. The experts are quantized to 2 bits, mixed per projection (gate_up_proj at 2-bit and down_proj at 3-bit), the dense layers are int8, and the KV cache is FP16. Escha Labs publishes the quality comparison against an FP8 baseline of the same model: parity or better on math, graduate science, tool use and long context, about 2 percent lower on broad knowledge, and about 7 percent lower on long-horizon code generation, which is the one clear gap. See the model card for the full benchmark table and protocol. Behavior Supports streaming, function tools, structured JSON output including strict schemas, and thinking mode on by default. Set enable_thinking=false for direct answers. With thinking on, the reasoning arrives in reasoning_content and the answer in content, so read both. A low max_tokens with thinking on can be spent entirely on reasoning, so allow room for the answer. Caching Automatic prefix cache reads are billed at the cached-input rate when reported. Explicit cache controls are not supported. Cancelling a streaming request mid-generation bills only the tokens produced up to that point.

Também conhecido como Alibaba Cloud Qwen3.6 35B A3B, Qwen3.6-35B-A3B, qwen3-6-35b-a3b

Especificações de Qwen3.6 35B A3B

ID do modelo

qwen3-6-35b-a3b

Provedor

Alibaba Cloud

Categoria

Geração de Texto

Lançado

29 de jul. de 2026

Janela de contexto

128K tokens

Saída máxima

16.384 tokens

Entrada

Texto

Saída

Texto

Saída estruturada

JSON Schema

Endpoints

POST/v1/chat/completionsPOST/v1/responsesPOST/v1/messagesPOST/v1/completionsPOST/v1beta/models/qwen3-6-35b-a3b:generateContent

IDs de modelo alternativos

qwen3.6-35b-a3bqwen/qwen3.6-35b-a3bEschaLabs/Qwen3.6-35B-A3B-Escha-W2

Preços da API Qwen3.6 35B A3BEconomize até 72%

Tarifas pay-as-you-go ao vivo do catálogo EmpirioLabs. Você paga só pelo que usa, sem mínimo mensal.

Como chamar a API Qwen3.6 35B A3B

Qwen3.6 35B A3B atende a API Chat Completions compatível com OpenAI. Aponte qualquer SDK OpenAI para https://api.empiriolabs.ai/v1 com sua chave de API EmpirioLabs e use o id de modelo qwen3-6-35b-a3b. Obtenha uma chave de API no painel EmpirioLabs.

curl https://api.empiriolabs.ai/v1/chat/completions \
  -H "Authorization: Bearer $EMPIRIOLABS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen3-6-35b-a3b",
    "messages": [
      {"role": "user", "content": "Write a haiku about the ocean."}
    ]
  }'

from openai import OpenAI

client = OpenAI(
    base_url="https://api.empiriolabs.ai/v1",
    api_key="YOUR_EMPIRIOLABS_API_KEY",
)

response = client.chat.completions.create(
    model="qwen3-6-35b-a3b",
    messages=[{"role": "user", "content": "Write a haiku about the ocean."}],
)
print(response.choices[0].message.content)

Parâmetros da API Qwen3.6 35B A3B

Parâmetros de requisição suportados pela API Qwen3.6 35B A3B na EmpirioLabs. Os padrões valem quando um campo é omitido.

Bom saber

Text-only. This build does not accept image or video input, unlike the base Qwen3.6 35B A3B.

Weights

Served from the 2-bit eschamoe W2 build published by Escha Labs (eschalabs.com) as EschaLabs/Qwen3.6-35B-A3B-Escha-W2 on Hugging Face, under Apache-2.0. The experts are quantized to 2 bits, mixed per projection (gate_up_proj at 2-bit and down_proj at 3-bit), the dense layers are int8, and the KV cache is FP16. Escha Labs publishes the quality comparison against an FP8 baseline of the same model: parity or better on math, graduate science, tool use and long context, about 2 percent lower on broad knowledge, and about 7 percent lower on long-horizon code generation, which is the one clear gap. See the model card for the full benchmark table and protocol.

Behavior

Supports streaming, function tools, structured JSON output including strict schemas, and thinking mode on by default. Set enable_thinking=false for direct answers. With thinking on, the reasoning arrives in reasoning_content and the answer in content, so read both. A low max_tokens with thinking on can be spent entirely on reasoning, so allow room for the answer.

Caching

Automatic prefix cache reads are billed at the cached-input rate when reported. Explicit cache controls are not supported. Cancelling a streaming request mid-generation bills only the tokens produced up to that point.

API Qwen3.6 35B A3B: perguntas frequentes

Quanto custa a API Qwen3.6 35B A3B?

Na EmpirioLabs, Qwen3.6 35B A3B é cobrado por uso. A tabela de tarifas ao vivo desta página sempre corresponde ao que a API cobra.

Qual é a janela de contexto de Qwen3.6 35B A3B?

Qwen3.6 35B A3B suporta uma janela de contexto de 128K tokens com até 16.384 tokens de saída por resposta.

A API Qwen3.6 35B A3B é compatível com OpenAI?

Sim. Qwen3.6 35B A3B atende a API Chat Completions compatível com OpenAI, então SDKs OpenAI existentes funcionam apontando base_url para https://api.empiriolabs.ai/v1 e definindo o id de modelo qwen3-6-35b-a3b.

Posso testar Qwen3.6 35B A3B no navegador antes de integrar?

Sim. O playground da EmpirioLabs executa Qwen3.6 35B A3B no navegador com os mesmos parâmetros que a API expõe, para você testar prompts antes de escrever código.

Como consigo uma chave de API Qwen3.6 35B A3B?

Crie uma conta EmpirioLabs e gere uma chave em API Keys no painel. A cobrança usa créditos pay-as-you-go, então você paga apenas pelas requisições que faz.