What architecture does Qwen 3.6 27B use?

Qwen 3.6 27B is built on a hybrid architecture that integrates linear attention mechanisms with a sparse mixture-of-experts framework. The combination is designed to keep inference efficient at long context while preserving the capability profile of a larger network.

How does Qwen 3.6 27B compare to the prior Qwen 3.5-35B-A3B generation?

Alibaba Cloud positions Qwen 3.6 27B as a clear step up from the 3.5-35B-A3B generation, with significantly improved agentic coding, mathematical and code reasoning, spatial intelligence, and object localization and detection performance.

What modalities does Qwen 3.6 27B accept?

Qwen 3.6 27B is a native vision-language model. It accepts interleaved text and images within a single context window of up to 256K tokens, and supports file input alongside text and vision.

Does Qwen 3.6 27B support tool calling?

Yes. Qwen 3.6 27B is tagged for tool use and is tuned for agentic coding workflows. The model can select and invoke registered functions across multi-turn sessions through AI Gateway.

How do I access Qwen 3.6 27B through AI Gateway?

Authenticate with an AI Gateway API key or OIDC token and reference ``alibaba/qwen3.6-27b`` as the model. You can call Qwen 3.6 27B through AI SDK, Chat Completions API, Responses API, Messages API, or other API formats, from TypeScript or Python.

Does Qwen 3.6 27B support zero data retention?

Yes, Zero Data Retention is available for this model. Zero Data Retention is offered on a per-provider basis. See https://vercel.com/docs/ai-gateway/capabilities/zdr for details.

Where can I see live latency and cost data for Qwen 3.6 27B?

This page shows live throughput, time-to-first-token, and pricing metrics for Qwen 3.6 27B measured across real AI Gateway traffic.

Alibaba Cloud

Qwen 3.6 27B

Qwen 3.6 27B is a Qwen 3.6 native vision-language model from Alibaba Cloud built on a hybrid linear-attention plus sparse mixture-of-experts architecture, with a context window of 256K tokens and improvements in agentic coding, math and code reasoning, spatial intelligence, and object detection. Your use is subject to Alibaba Cloud's Terms & Privacy Policies.

View API reference

Input and output price: Input $0.60, Output $3.60, Per 1M tokens
24h uptime: Loading AI Gateway uptime

Get API key Read the docs

import { streamText } from 'ai'

const result = streamText({
  model: 'alibaba/qwen3.6-27b',
  prompt: 'Why is the sky blue?'
})

Read docs

Overview Playground Providers Uptime Status Throughput Latency API Similar About FAQ

Copy link to headingPlayground

Try out Qwen 3.6 27B by Alibaba Cloud. Usage is billed to your team at API rates. Free users (those who haven't made a payment) get $5 of credits every 30 days.

Qwen 3.6 27B

Copy link to headingProviders

Route requests across multiple providers. Copy a provider slug to set your preference. Visit the docs for more info. Using a provider means you agree to their terms, listed under Legal.

Provider

Context	Max Output	Latency	Throughput	Input	Output	Cache	Web Search	Capabilities	ZDR	No Training	Free Tier	Release Date

Alibaba Cloud

Legal:Terms•Privacy

256K

0.8 s

141 tps

$0.60/M

$3.60/M

—

04/22/2026

Getting started

Call Qwen 3.6 27B through AI Gateway with the AI SDK generateText and streamText functions, or through the OpenAI Chat Completions, OpenAI Responses, and Anthropic Messages APIs by changing the base URL. AI Gateway authenticates the request and routes it to an available provider.

Install the AI SDK (pnpm add ai dotenv), create an API key from the API Keys page, and set it as AI_GATEWAY_API_KEY in your environment. Full setup is covered in the text generation quickstart.

index.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'alibaba/qwen3.6-27b',
    prompt: 'Why is the sky blue?',
  });

  console.log(result.text);
}

main().catch(console.error);

Top-level parameters

The same Qwen 3.6 27B request in each API format AI Gateway supports.

top-level-params.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'alibaba/qwen3.6-27b',
    system: 'You are a concise technical assistant.',
    prompt: 'Summarize the tradeoffs between static generation and SSR.',
    maxOutputTokens: 1024,
  });

  console.log(result.text);
}

main().catch(console.error);

Standard parameters like prompt, messages, temperature, and tools work as documented in the AI SDK docs. These are the parameters with model-specific behavior.

Parameter	Type	Required	Description
`model`	`string`	Yes	Model ID in the form `creator/model`, e.g. `alibaba/qwen3.6-27b`. AI Gateway routes the request to an available provider.
`maxOutputTokens`	`number`	No	Hard cap on generated tokens. Qwen 3.6 27B supports up to `256,000` output tokens. Reasoning tokens count toward this limit.
`reasoning`	`'provider-default' \| 'none' \| 'minimal' \| 'low' \| 'medium' \| 'high' \| 'xhigh'`	No	Provider-agnostic reasoning effort, available in AI SDK 7 or later. Maps to the provider’s native reasoning configuration; reasoning settings under `providerOptions` take precedence when both are set. See the Reasoning section below.
`providerOptions`	`Record<string, JSONValue>`	No	AI Gateway routing options under `gateway`, plus any provider-native options under the provider’s own namespace — see the table below.

Input limits

Input	Formats	Sources	Max count	Max size	Limits
Text	—	—	—	—	Prompt and response share the 256K-token context window
Image	—	URL, base64, Uint8Array	—	—	Sent as image parts in messages; counts as input tokens
PDF	—	URL, base64, Uint8Array	—	—	Sent as file parts in messages; counts as input tokens

Provider options

Set AI Gateway routing options under providerOptions.gateway. For provider-specific options, pass them under the provider’s namespace as documented by the AI SDK.

Learn more in the AI SDK alibaba provider docs.

provider-options.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'alibaba/qwen3.6-27b',
    prompt: 'Why is the sky blue?',
    providerOptions: {
      gateway: {
        only: ['alibaba'],
      },
    },
  });

  console.log(result.text);
}

main().catch(console.error);

These AI Gateway routing options apply to every model. Provider-specific options pass through under the provider’s own namespace (for example providerOptions.anthropic) exactly as documented by the AI SDK.

Parameter	Type	Required	Description
`providerOptions.gateway.only`	`string[]`	No	Restrict routing to these provider slugs. Requests fail over only within the listed providers.
`providerOptions.gateway.order`	`string[]`	No	Preferred provider order. Listed providers are tried first; unlisted providers remain available as fallbacks.
`providerOptions.gateway.sort`	`'cost' \| 'ttft' \| 'tps'`	No	Rank candidate providers by price, time to first token, or tokens per second instead of the default routing order.
`providerOptions.gateway.zeroDataRetention`	`boolean`	No	Route only to providers with a zero-data-retention policy for this model.

Routing across providers

AI Gateway serves the same model through multiple providers and fails over automatically. order expresses a preference while keeping every provider eligible; only is a hard allowlist — if none of the listed providers are available the request fails instead of falling back.

Options under a provider's own namespace (for example providerOptions.anthropic) are forwarded to that provider with the request. Providers ignore option namespaces that don't apply to them, so it is safe to set provider options alongside gateway routing options.

Reasoning

AI Gateway bridges reasoning across every API format. The AI SDK exposes a provider-agnostic top-level reasoning level (none, minimal, low, medium, high, or xhigh); the Chat Completions and Responses formats take the same effort under reasoning.effort; and the Anthropic Messages format uses a native thinking token budget. Whichever you send, the gateway maps it to the target model’s native configuration, converting between effort levels and token budgets as needed. Reasoning-related settings under providerOptions take full precedence over the top-level reasoning value and are never merged. Reasoning tokens typically count toward your output-token usage, though how they’re reported and billed varies by provider.

Learn more in the AI Gateway reasoning guide.

reasoning.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'alibaba/qwen3.6-27b',
    prompt: 'Explain the Monty Hall problem step by step.',
    reasoning: 'high',
  });

  console.log(result.text);
}

main().catch(console.error);

Image input

Send images alongside text as message parts. Images count as input tokens.

image-input.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'alibaba/qwen3.6-27b',
    messages: [
      {
        role: 'user',
        content: [
          { type: 'text', text: 'Describe this image.' },
          { type: 'image', image: 'https://example.com/photo.jpg' },
        ],
      },
    ],
  });

  console.log(result.text);
}

main().catch(console.error);

PDF input

Attach PDFs as file parts. Their contents count as input tokens.

pdf-input.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'alibaba/qwen3.6-27b',
    messages: [
      {
        role: 'user',
        content: [
          { type: 'text', text: 'Summarize this document.' },
          {
            type: 'file',
            mediaType: 'application/pdf',
            data: 'https://example.com/document.pdf',
          },
        ],
      },
    ],
  });

  console.log(result.text);
}

main().catch(console.error);

Tool calling

Expose tools the model can call. Define each tool’s inputs with a Zod schema.

tool-calling.ts

import { generateText, tool } from 'ai';
import { z } from 'zod';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'alibaba/qwen3.6-27b',
    prompt: 'What is the weather in San Francisco?',
    tools: {
      getWeather: tool({
        description: 'Get the current weather for a location',
        inputSchema: z.object({ location: z.string() }),
        execute: async ({ location }) => ({ location, temperatureC: 18 }),
      }),
    },
  });

  console.log(result.text);
}

main().catch(console.error);

Copy link to headingMore models by Alibaba Cloud

Model

Context	Latency	Throughput	Input	Output	Cache	Web Search	Capabilities	Providers	ZDR	No Training	Free Tier	Release Date

alibaba/qwen3.8-max-0902

991K

2.9 s

43 tps

$2/M

$6/M

Read$0.25/M

Write$2.50/M

—

09/01/2026

alibaba/qwen3.8-flash

991K

0.8 s

96 tps

$0.15/M

$0.47/M

Read$0.02/M

Write$0.20/M

—

08/26/2026

alibaba/qwen3.8-27b

0.4 s

939 tps

$0.10/M

$0.40/M

Read$0.01/M

Write$0.63/M

—

08/14/2026

alibaba/qwen3.8-max

3.0 s

67 tps

$2/M

$6/M

Read$0.25/M

Write$2.50/M

—

08/02/2026

alibaba/qwen3.7-flash

991K

1.3 s

99 tps

$0.03/M+2 more

$0.13/M+2 more

Read$0.006/M

Write$0.04/M

—

07/28/2026

alibaba/qwen3.7-plus

2.3 s

65 tps

$0.40/M+1 more

$1.60/M+1 more

Read$0.08/M

Write$0.50/M

—

06/02/2026

Copy link to headingAbout Qwen 3.6 27B

Qwen 3.6 27B, released on April 22, 2026, is a Qwen 3.6 native vision-language model in Alibaba Cloud's Qwen 3 family. It is built on a hybrid architecture that combines linear attention mechanisms with a sparse mixture-of-experts (MoE) framework, a design intended to keep inference efficient at long context while preserving the capability profile of a larger network.

Compared with the prior 3.5-35B-A3B generation, Qwen 3.6 27B brings improvements across several axes. Agentic coding ability is stronger, which matters for pipelines that chain tool calls and multi-step plans. Mathematical and code reasoning have been upgraded for benchmark-style problem solving and real-world programming tasks. Spatial intelligence, object localization, and object detection are sharper, which improves the model's grounding when it must reason about positions of elements within an image.

Native vision-language support means images are treated as first-class inputs alongside text rather than processed through a bolt-on encoder. Qwen 3.6 27B accepts file input and is tagged for reasoning, tool use, and implicit caching, so it can ingest documents and images, decide when to invoke registered tools, and reuse cached prefixes when serving repeated long prompts. The context window of 256K tokens accommodates extended multimodal sessions, document plus image inputs, and long agent traces.

You can integrate Qwen 3.6 27B through AI SDK, Chat Completions API, Responses API, Messages API, or other API formats, from TypeScript or Python. Maximum output is 256K tokens tokens per request.

Copy link to headingWhat To Consider When Choosing a Provider

Configuration: Sparse MoE architectures keep active compute small per token, but providers serve the model through different infrastructure paths. Check the live cost and latency metrics on this page before sizing high-volume workloads, and confirm vision payload limits with your selected provider.
Zero Data Retention: Zero Data Retention is available for this model. It is offered on a per-provider and model basis. See the documentation for details.
Authentication: AI Gateway authenticates requests using an API key or OIDC token. You do not need to manage provider credentials directly.

Copy link to headingWhen to Use Qwen 3.6 27B

Best for

Agentic Multimodal Coding: Pipelines that combine reasoning, tool use, and image input within a single session
Spatial And Object Tasks: Workloads requiring sharper object localization, detection, and 2D grounding
Math And Code Reasoning: Step-by-step accuracy in mathematical and programming problems over raw throughput
Long-Context Multimodal Sessions: Combined text and image inputs handled within the window of 256K tokens
Repeated Long Prefixes: Implicit caching reduces cost on shared system prompts and document inputs

Consider alternatives when

Text-Only Workloads: A dedicated text model offers lower cost per token when vision is never used
Maximum Reasoning Depth: A thinking-mode model is a better match when extended chain-of-thought matters most
Latency-Critical Pipelines: A smaller, faster vision model serves simple multimodal tasks at lower cost
Image Or Video Generation: A generation-class model fits tasks that produce pixels rather than read them

Copy link to headingConclusion

Qwen 3.6 27B brings the Qwen 3.6 generation's improvements in agentic coding, reasoning, and spatial intelligence to a hybrid linear-attention plus sparse MoE architecture. Routing through AI Gateway gives you a single integration surface across the Qwen 3.6 line, with provider failover and consolidated billing.

Copy link to headingFrequently Asked Questions

What architecture does Qwen 3.6 27B use?
Qwen 3.6 27B is built on a hybrid architecture that integrates linear attention mechanisms with a sparse mixture-of-experts framework. The combination is designed to keep inference efficient at long context while preserving the capability profile of a larger network.
How does Qwen 3.6 27B compare to the prior Qwen 3.5-35B-A3B generation?
Alibaba Cloud positions Qwen 3.6 27B as a clear step up from the 3.5-35B-A3B generation, with significantly improved agentic coding, mathematical and code reasoning, spatial intelligence, and object localization and detection performance.
What modalities does Qwen 3.6 27B accept?
Qwen 3.6 27B is a native vision-language model. It accepts interleaved text and images within a single context window of up to 256K tokens, and supports file input alongside text and vision.
Does Qwen 3.6 27B support tool calling?
Yes. Qwen 3.6 27B is tagged for tool use and is tuned for agentic coding workflows. The model can select and invoke registered functions across multi-turn sessions through AI Gateway.
How do I access Qwen 3.6 27B through AI Gateway?
Authenticate with an AI Gateway API key or OIDC token and reference `alibaba/qwen3.6-27b` as the model. You can call Qwen 3.6 27B through AI SDK, Chat Completions API, Responses API, Messages API, or other API formats, from TypeScript or Python.
Does Qwen 3.6 27B support zero data retention?
Yes, Zero Data Retention is available for this model. Zero Data Retention is offered on a per-provider basis. See https://vercel.com/docs/ai-gateway/capabilities/zdr for details.
Where can I see live latency and cost data for Qwen 3.6 27B?
This page shows live throughput, time-to-first-token, and pricing metrics for Qwen 3.6 27B measured across real AI Gateway traffic.

Agent Stack

Core Platform

Tools

Learn

Build

Explore

Qwen 3.6 27B

Copy link to headingPlayground

Copy link to headingProviders

Copy link to headingUptime24 hours

Copy link to headingThroughput24 hours

Copy link to headingLatency24 hours

Getting started

Top-level parameters

Input limits

Provider options

Routing across providers

Reasoning

Image input

PDF input

Tool calling

Copy link to headingMore models by Alibaba Cloud

Copy link to headingAbout Qwen 3.6 27B

Copy link to headingWhat To Consider When Choosing a Provider

Copy link to headingWhen to Use Qwen 3.6 27B

Best for

Consider alternatives when

Copy link to headingConclusion

Copy link to headingFrequently Asked Questions