Qwen3 Coder Plus
Qwen3 Coder Plus is an enhanced tier in Alibaba Cloud's agentic coding model family, offering a step up in capability over the base variant for development teams with demanding software engineering workloads.
View API reference- Input and output price
- Input $1, Output $5, Per 1M tokens
- 24h uptime
- Loading AI Gateway uptime
import { streamText } from 'ai'
const result = streamText({ model: 'alibaba/qwen3-coder-plus', prompt: 'Why is the sky blue?'})Copy link to headingPlayground
Try out Qwen3 Coder 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.
Qwen3 Coder Plus
Qwen3 Coder 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 Qwen3 Coder 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-coder-plus', prompt: 'Why is the sky blue?', });
console.log(result.text);}
main().catch(console.error);Top-level parameters
The same Qwen3 Coder 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-coder-plus', system: 'You are a concise technical assistant.', prompt: 'Summarize the tradeoffs between static generation and SSR.', maxOutputTokens: 1024, temperature: 0.5, });
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-coder-plus. AI Gateway routes the request to an available provider. |
maxOutputTokens | number | No | Hard cap on generated tokens. Qwen3 Coder Plus supports up to 65,536 output tokens. |
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 |
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-coder-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.
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-coder-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 | 4.0 s | 50 tps | $2/M | $6/M | Read$0.25/M Write$2.50/M | — | +2 | | 09/01/2026 | |||||
| 991K | 1.1 s | 96 tps | $0.16/M | $0.47/M | Read$0.02/M Write$0.20/M | — | +2 | | 08/26/2026 | |||||
| 1M | 0.6 s | 133 tps | $0.10/M | $0.40/M | Read$0.01/M Write$0.63/M | — | +1 |   +3 | 08/14/2026 | |||||
| 1M | 2.5 s | 160 tps | $2/M | $6/M | Read$0.25/M Write$2.50/M | — | +1 |  | 08/02/2026 | |||||
| 991K | 2.5 s | 140 tps | $0.03/M+2 more | $0.13/M+2 more | Read$0.006/M Write$0.04/M | — | +2 | | 07/28/2026 | |||||
| 1M | 2.0 s | 58 tps | $0.40/M+1 more | $1.60/M+1 more | Read$0.08/M Write$0.50/M | — | +2 | | 06/02/2026 |
Copy link to headingAbout Qwen3 Coder Plus
Qwen3 Coder Plus sits above the base Qwen3-Coder in Alibaba Cloud's model hierarchy and is listed alongside the 480B-A35B variant in DashScope API configurations. The "Plus" designation in Alibaba Cloud's naming convention typically indicates a model that has been enhanced beyond the base offering, with more capability, higher quality output, or a larger underlying architecture, while the Qwen3-Coder lineage keeps coding and agentic capabilities at the center.
The Qwen3-Coder line emphasizes practical coding ability across the full range of programming languages and software engineering contexts. Its orientation toward code that actually runs, rather than code that only looks plausible, shows up in multi-step coding tasks where a single mistake early in the sequence compounds.
The practical result is a model that understands code at the level of real software engineering, not benchmark optimization. Repository-level tasks, debugging sessions that require reading error output and revising approach, and tool-calling workflows that interact with shells, file systems, and APIs are the scenarios the Qwen3-Coder family is built around.
For teams that found the base Qwen3-Coder variant adequate for simpler tasks but want additional headroom for complex feature development, architectural refactoring, or cross-file dependency analysis, the Plus tier offers that step up without going to the full 480B-A35B model.
Copy link to headingWhat To Consider When Choosing a Provider
- Configuration: Provider selection can affect sustained throughput for code-heavy workloads. For batch processing of large code review jobs, test latency and throughput against your expected load pattern before committing to a deployment configuration.
- 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 Qwen3 Coder Plus
Best for
- Mid-complexity software engineering tasks: Repository-level tasks that go beyond single-file edits, refactoring across multiple files, resolving import dependencies, updating APIs across a codebase, benefit from the enhanced capability the Plus tier offers over the base variant
- Code review and explanation at depth: Explaining complex code, identifying non-obvious bugs, and producing detailed inline documentation on unfamiliar codebases require a model with enough capacity to follow intricate logic chains
- Automated developer tool backends: AI-powered PR review, automated ticket-to-code workflows, or code migration tools that need reliable, high-quality output benefit from the Plus tier's improved consistency on harder tasks
- Test generation for complex code paths: Generating meaningful unit and integration tests for code with many branching paths or subtle invariants requires the model to reason carefully about what the code actually does, not just what it looks like
- Technical interview preparation and code challenge solving: Multi-step algorithmic problems, system design questions involving code sketches, and debugging exercises with embedded errors are well-suited to a capable coding model
Consider alternatives when
- Cost per query is the primary concern at high volume: The 30B-A3B variant activates fewer parameters and will be cheaper per token for workloads where its capability level is sufficient. For very high request volumes, the cost difference accumulates
- The task is simple code formatting, linting, or templating: Simple transformations don't need Plus-level capability. Smaller or base-tier models handle these efficiently
- You need the absolute ceiling of open coding capability: The Qwen3-Coder 480B-A35B model provides the highest ceiling for the most demanding problems. The Plus tier sits between the base and 480B-A35B in capability
Copy link to headingConclusion
Qwen3 Coder Plus addresses the gap between entry-level coding models and the full 480B-A35B tier, capable enough for complex real-world engineering tasks, without the serving requirements of the 480B-A35B variant. Teams who have outgrown simpler models but don't need the absolute ceiling will find it a practical fit. AI Gateway brings Alibaba Cloud access under one integration with reliable failover.
Copy link to headingFrequently Asked Questions
How does Qwen3 Coder Plus differ from the base Qwen3-Coder?
The Plus tier represents an enhanced capability level within the Qwen3-Coder family. Based on Alibaba Cloud's DashScope API configuration, it's positioned as a step up from the base model, offering stronger performance on more demanding coding tasks. Specific architectural details distinguish it from the base variant in the provider API documentation.
What kinds of coding tasks does Qwen3 Coder Plus handle best?
Qwen3 Coder Plus emphasizes agentic coding scenarios: multi-step tasks, tool use, and real-world software engineering problems rather than isolated algorithmic puzzles. It handles repository-level tasks, debugging requiring iterative refinement, and cross-file coordination particularly well.
What is the context window and how does it affect long coding sessions?
The context window is 1M tokens. For extended agentic sessions where the model accumulates file contents, tool outputs, and conversation history, a larger context window reduces the need for truncation strategies that can discard useful information.
Does Qwen3 Coder Plus support MCP and tool-calling for agentic workflows?
Yes. The Qwen3-Coder family supports agentic tool use including MCP (Model Context Protocol) integration, making it compatible with tool-calling frameworks used in developer toolchains like Cline and Claude Code.
How does AI Gateway handle high-throughput coding workloads for this model?
AI Gateway distributes requests across Alibaba Cloud, which provides aggregate throughput capacity beyond any single provider. Live metrics are displayed on this page and update based on real traffic.
Can I switch between Qwen3 Coder Plus and the base or 30B-A3B variants through the same gateway?
Yes. All Qwen3-Coder variants are available through AI Gateway with separate model identifiers. You can route different request types to different tiers, for example, simple completion tasks to a smaller variant and complex multi-step tasks to the Plus tier, using the same API key and endpoint configuration.
Your use is subject to Alibaba Cloud's Terms & Privacy Policies.