Qwen 3.5 Plus
Qwen 3.5 Plus is Alibaba Cloud's advanced multimodal model combining a context window of 1M tokens with strong scientific reasoning, visual analysis, and adaptive tool use for complex agentic workflows. Your use is subject to Alibaba Cloud's Terms & Privacy Policies.
View API reference- Input and output price
- Input $0.40, Output $2.50, Per 1M tokens
- 24h uptime
- Loading AI Gateway uptime
import { streamText } from 'ai'
const result = streamText({ model: 'alibaba/qwen3.5-plus', prompt: 'Why is the sky blue?'})Copy link to headingPlayground
Try out Qwen 3.5 Plus 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 3.5 Plus
Qwen 3.5 Plus
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.
Copy link to headingUptime24 hours
Direct request success rate on AI Gateway and per-provider. Visit the docs for more info.
Copy link to headingThroughput24 hours
P50 throughput on live AI Gateway traffic, in tokens per second (TPS). Visit the docs for more info.
Copy link to headingLatency24 hours
P50 time to first token (TTFT) on live AI Gateway traffic, in milliseconds. View the docs for more info.
Getting started
Call Qwen 3.5 Plus 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.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'alibaba/qwen3.5-plus', prompt: 'Why is the sky blue?', });
console.log(result.text);}
main().catch(console.error);Top-level parameters
The same Qwen 3.5 Plus request in each API format AI Gateway supports.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'alibaba/qwen3.5-plus', 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/qwen3.5-plus. AI Gateway routes the request to an available provider. |
maxOutputTokens | number | No | Hard cap on generated tokens. Qwen 3.5 Plus supports up to 64,000 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 1M-token context window |
| Image | — | URL, base64, Uint8Array | — | — | Sent as image parts in messages; counts as input tokens |
| — | 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.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'alibaba/qwen3.5-plus', 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.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'alibaba/qwen3.5-plus', 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.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'alibaba/qwen3.5-plus', 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.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'alibaba/qwen3.5-plus', 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.
import { generateText, tool } from 'ai';import { z } from 'zod';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'alibaba/qwen3.5-plus', 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 |
|---|
| 991K | 5.1 s | 43 tps | $2/M | $6/M | Read$0.25/M Write$2.50/M | — | +3 | | 09/01/2026 | |||||
| 991K | 4.8 s | 69 tps | $0.15/M | $0.47/M | Read$0.02/M Write$0.20/M | — | +3 | | 08/26/2026 | |||||
| 1M | 0.1 s | 150 tps | $0.10/M | $0.40/M | Read$0.01/M Write$0.63/M | — | +1 |   +4 | 08/14/2026 | |||||
| 1M | 1.2 s | 64 tps | $2/M | $6/M | Read$0.25/M Write$2.50/M | — | +2 |  | 08/02/2026 | |||||
| 991K | 1.6 s | 70 tps | $0.03/M+2 more | $0.13/M+2 more | Read$0.006/M Write$0.04/M | — | +3 | | 07/28/2026 | |||||
| 1M | 2.3 s | 77 tps | $0.40/M+1 more | $1.60/M+1 more | Read$0.08/M Write$0.50/M | — | +3 | | 06/02/2026 |
Copy link to headingAbout Qwen 3.5 Plus
Qwen 3.5 Plus sits at the top of the production-hosted Qwen3.5 lineup, offering deeper reasoning and stronger performance on scientific problem-solving, visual question answering, and frontend code generation from specifications. Like the Flash variant it is built on the Qwen3.5 hybrid linear-attention MoE backbone, but it is tuned for accuracy-first workloads where additional computation per token is warranted.
The model was highlighted for converting complex visual or textual specifications, such as design mockups, mathematical notation, or multi-document briefs, into functional code or structured analysis. Its context window of 1M tokens enables practitioners to pass entire repositories, research papers, or legal documents without chunking, while the adaptive tool use system lets the model decide when to invoke external APIs or search tools during a single agentic session.
Supported modalities include text, images, and video, all processed natively through the same architecture. Structured outputs, tool calling, and configurable reasoning depth are available, allowing teams to tune the model's behavior from rapid instruction-following to deep deliberate reasoning depending on the use case.
Copy link to headingWhat To Consider When Choosing a Provider
- Configuration: The Plus tier carries a higher per-token cost than Flash; use the AI Gateway cost monitoring dashboard to track spending and set budget alerts before deploying at scale.
- 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 3.5 Plus
Best for
- Scientific and analytical reasoning: Multi-step deliberation tasks including mathematical derivations and structured analysis
- Frontend code generation: Producing production-quality code from UI specifications, screenshots, or design assets
- Full-document analysis: Long-form workloads where the window of 1M tokens eliminates chunking and preserves full context
- Complex agentic pipelines: Multi-turn sessions where the model must autonomously plan, search, and use tools
- Visual reasoning: Comparing multiple images or interpreting data-dense charts within a single prompt
Consider alternatives when
- Throughput and cost first: Use Qwen3.5-Flash when deep analytical reasoning isn't required
- Text-only workloads: A lower-cost text model may suffice when no multimodal inputs are involved
- Video or image generation: This model handles multimodal understanding, not generation
Copy link to headingConclusion
Qwen 3.5 Plus brings Alibaba Cloud's reasoning and vision capabilities to AI Gateway, serving teams that need a capable, long-context model for analytical, code-generation, and agentic tasks. It pairs naturally with the Flash variant in tiered architectures where routine requests route to the lower-cost model and complex queries escalate to Plus.
Copy link to headingFrequently Asked Questions
How does Qwen 3.5 Plus differ from Qwen3.5-Flash on AI Gateway?
Plus is tuned for maximum accuracy and deeper reasoning on complex tasks, while Flash prioritizes low latency and cost efficiency. Both share the context window of 1M tokens and multimodal inputs. Per-token rates differ by tier.
What kind of visual reasoning can Qwen 3.5 Plus perform?
The model can analyze images, video frames, and interleaved visual-text content natively, making it suited for interpreting UI screenshots, scientific diagrams, data visualizations, and video-based question answering.
Can Qwen 3.5 Plus generate code from images or design files?
Yes. A primary use case highlighted is converting visual specifications, such as wireframes, mockups, or screenshots, into functional frontend code.
Does the model support autonomous tool use during a session?
Yes. Qwen 3.5 Plus includes adaptive tool-calling capabilities that let it decide when to invoke registered external tools, APIs, or search functions during a multi-turn agentic session.
What is the maximum context the model can handle in a single request?
The hosted Plus tier supports input of up to 1M tokens by default, enabling entire codebases, books, or large document collections to be passed without retrieval preprocessing.
How is the configurable reasoning depth useful?
Teams can increase reasoning depth for tasks like mathematical proofs or multi-document synthesis, or reduce it for simpler extraction tasks to lower latency and token spend.
Is Qwen 3.5 Plus available without a separate Alibaba Cloud account?
Yes. No separate Alibaba Cloud or Model Studio account is required. AI Gateway handles authentication through its API key or OIDC token system.