Qwen3.6 35B A3B API

关于 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.

也称为 Alibaba Cloud Qwen3.6 35B A3B, Qwen3.6-35B-A3B, qwen3-6-35b-a3b

Qwen3.6 35B A3B 规格

模型 ID

qwen3-6-35b-a3b

提供方

Alibaba Cloud

类别

文本生成

发布日期

2026年7月29日

上下文窗口

128K 个 token

最大输出

16,384 个 token

输入

文本

输出

文本

结构化输出

JSON Schema

端点

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

备用模型 ID

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

Qwen3.6 35B A3B API 价格最高省 72%

来自 EmpirioLabs 目录的实时按量计费价格。只为实际用量付费，没有月度最低消费。

如何调用 Qwen3.6 35B A3B API

Qwen3.6 35B A3B 提供 OpenAI 兼容的 Chat Completions API。用你的 EmpirioLabs API 密钥把任意 OpenAI SDK 指向 https://api.empiriolabs.ai/v1，并使用模型 ID qwen3-6-35b-a3b。 在EmpirioLabs 控制台获取 API 密钥。

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)

Qwen3.6 35B A3B API 参数

EmpirioLabs 上 Qwen3.6 35B A3B API 支持的请求参数。省略字段时使用默认值。

须知

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.

Qwen3.6 35B A3B API：常见问题

Qwen3.6 35B A3B API 收费多少？

在 EmpirioLabs，Qwen3.6 35B A3B 按量计费。本页的实时价格表始终与 API 的实际计费一致。

Qwen3.6 35B A3B 的上下文窗口有多大？

Qwen3.6 35B A3B 支持 128K token 的上下文窗口，每次响应最多 16,384 个输出 token。

Qwen3.6 35B A3B API 兼容 OpenAI 吗？

兼容。Qwen3.6 35B A3B 提供 OpenAI 兼容的 Chat Completions API，现有 OpenAI SDK 只需把 base_url 指向 https://api.empiriolabs.ai/v1 并把模型 ID 设为 qwen3-6-35b-a3b 即可使用。

集成之前可以在浏览器里试用 Qwen3.6 35B A3B 吗？

可以。EmpirioLabs Playground在浏览器中以与 API 相同的参数运行 Qwen3.6 35B A3B，你可以在写代码之前先测试提示词。

如何获取 Qwen3.6 35B A3B API 密钥？

创建 EmpirioLabs 账户，然后在控制台的 API Keys生成密钥。计费使用按量付费的额度，只为实际发出的请求付费。