Qwen3.6 35B A3B API

About 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.

Also known as Alibaba Cloud Qwen3.6 35B A3B, Qwen3.6-35B-A3B, qwen3-6-35b-a3b

Qwen3.6 35B A3B specs

Model ID

qwen3-6-35b-a3b

Provider

Alibaba Cloud

Category

Text Generation

Released

Jul 29, 2026

Context window

128K tokens

Max output

16,384 tokens

Input

Text

Output

Text

Structured output

JSON Schema

Endpoints

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

Alternate model IDs

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

Qwen3.6 35B A3B API pricingSave up to 72%

Live pay-as-you-go rates from the EmpirioLabs catalog. You are billed only for what you use, with no monthly minimum.

How to call the Qwen3.6 35B A3B API

Qwen3.6 35B A3B serves the OpenAI-compatible Chat Completions API. Point any OpenAI SDK at https://api.empiriolabs.ai/v1 with your EmpirioLabs API key and use the model id qwen3-6-35b-a3b. Get an API key from the EmpirioLabs dashboard.

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 parameters

Request parameters supported by the Qwen3.6 35B A3B API on EmpirioLabs. Defaults apply when a field is omitted.

Good to know

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: common questions

How much does the Qwen3.6 35B A3B API cost?

On EmpirioLabs, Qwen3.6 35B A3B is billed pay as you go. The live rate card on this page always matches what the API charges.

What is the context window of Qwen3.6 35B A3B?

Qwen3.6 35B A3B supports a 128K-token context window with up to 16,384 output tokens per response.

Is the Qwen3.6 35B A3B API OpenAI-compatible?

Yes. Qwen3.6 35B A3B serves the OpenAI-compatible Chat Completions API, so existing OpenAI SDKs work by pointing base_url at https://api.empiriolabs.ai/v1 and setting the model id to qwen3-6-35b-a3b.

Can I try Qwen3.6 35B A3B in the browser before integrating?

Yes. The EmpirioLabs playground runs Qwen3.6 35B A3B in the browser with the same parameters the API exposes, so you can test prompts before writing code.

How do I get a Qwen3.6 35B A3B API key?

Create an EmpirioLabs account, then generate a key under API Keys in the dashboard. Billing is pay-as-you-go credits, so you only pay for the requests you make.