Qwen3-Coder Models, Coder-Next & API Guide

Qwen3-Coder is a family of text-based coding language models developed by the Qwen team. It includes large mixture-of-experts Instruct checkpoints, the separate Qwen3-Coder-Next architecture, downloadable model variants, and hosted Alibaba Cloud Model Studio IDs.

Last verified: July 21, 2026.

The open Qwen3-Coder Instruct checkpoints are non-thinking models and do not generate <think> blocks. Hosted Model Studio services must be treated as separate interfaces.

Official open Qwen3-Coder checkpoints

Exact Hugging Face ID	Type	Parameters	Context	Thinking behavior	License
`Qwen/Qwen3-Coder-Next`	Instruct	80B total / 3B active	262,144 native	Non-thinking only	Apache 2.0
`Qwen/Qwen3-Coder-Next-Base`	Base	80B total / 3B active	262,144 native	Base checkpoint	Apache 2.0
`Qwen/Qwen3-Coder-480B-A35B-Instruct`	Instruct	480B total / 35B active	262,144 native; documented 1M extension with YaRN	Non-thinking only	Apache 2.0
`Qwen/Qwen3-Coder-30B-A3B-Instruct`	Instruct	30.5B total / 3.3B active	262,144 native; documented 1M extension with YaRN	Non-thinking only	Apache 2.0

FP8 and GGUF variants are also published for selected checkpoints. Their precision, runtime support, memory use, and performance should be evaluated separately from the original BF16 repositories.

Active-parameter labels describe mixture-of-experts computation. An 80B-total model does not become a 3B download merely because about 3B parameters are activated during token processing.

What is Qwen3-Coder-Next?

Qwen3-Coder-Next is not a renamed 30B or 480B checkpoint. It is built on Qwen3-Next-80B-A3B-Base and uses a hybrid architecture combining Gated DeltaNet layers, attention layers, and a mixture-of-experts design.

80B total parameters.
Approximately 3B active parameters.
262,144-token native context.
Text input and text output.
Non-thinking Instruct behavior.
Separate Base and Instruct repositories.

The specific Qwen3-Coder-Next card documents 262,144 tokens natively. This page does not assign a local 1M guarantee to Coder-Next because its model-specific card and deployment commands focus on the native 256K range.

Does open Qwen3-Coder use Thinking mode?

The open Instruct checkpoints listed above support non-thinking mode only. They do not generate <think></think> blocks, and adding enable_thinking=False is unnecessary.

This rule applies to the downloadable open checkpoints. A hosted service with a similar lowercase model ID can expose a different service-level interface and must not be used as evidence that the local checkpoint has hybrid Thinking behavior.

The documented 358-language claim

The official Qwen3-Coder repository lists support for 358 coding-language and syntax labels. The published list contains programming languages as well as markup, data, configuration, and file formats such as JSON, YAML, Markdown, CSV, and Dockerfile.

Therefore, “358 coding languages and formats in the official list” is more accurate than claiming equal proficiency across 358 programming languages. The number describes published coverage, not guaranteed performance on every syntax or toolchain.

Fill-in-the-middle support

The official repository states that fill-in-the-middle is supported across Qwen3-Coder versions. The documented prompt structure is:

<|fim_prefix|>existing code before the gap
<|fim_suffix|>existing code after the gap
<|fim_middle|>

Applications should use the tokenizer associated with the exact checkpoint because special-token IDs and chat templates are part of the model interface.

Tool calling and the qwen3_coder parser

Qwen3-Coder can propose structured tool calls, but the surrounding application must validate and execute them. The model does not independently edit files, run commands, browse websites, or deploy software.

Official vLLM and SGLang deployments use the qwen3_coder tool-call parser.

pip install "vllm>=0.15.0"

vllm serve Qwen/Qwen3-Coder-Next \
  --port 8000 \
  --max-model-len 32768 \
  --enable-auto-tool-choice \
  --tool-call-parser qwen3_coder

The model card documents a 262,144-token default maximum for Coder-Next but also advises reducing the configured context if the server cannot start. The example above uses 32,768 to avoid presenting the largest context as a low-memory default.

Call the local endpoint with Node.js

npm install openai

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "EMPTY",
  baseURL: "http://localhost:8000/v1",
});

const completion = await client.chat.completions.create({
  model: "Qwen/Qwen3-Coder-Next",
  messages: [
    {
      role: "user",
      content: (
        "Write a TypeScript function that validates an email-like "
        + "identifier. Explain its limitations after the code."
      )
    }
  ],
  max_tokens: 1024,
});

console.log(completion.choices[0].message.content);

Open checkpoints versus Model Studio IDs

Hugging Face repository IDs and Alibaba Cloud Model Studio IDs are different interfaces. Lowercase hosted names must not be presented as downloadable checkpoints.

Model Studio ID	Documented service context	Service Thinking status	Notes
`qwen3-coder-plus`	1M	Supported	Floating hosted alias
`qwen3-coder-plus-2025-09-23`	1M	Supported	Dated hosted version
`qwen3-coder-flash`	1M	Supported	Floating hosted alias
`qwen3-coder-flash-2025-07-28`	1M	Supported	Dated hosted version
`qwen3-coder-next`	256K	Marked supported by the service matrix	Hosted interface; do not transfer this behavior to the open checkpoint
`qwen3-coder-480b-a35b-instruct`	256K	Unsupported	Hosted ID corresponding by name to the open model line
`qwen3-coder-30b-a3b-instruct`	256K	Unsupported	Hosted ID corresponding by name to the open model line

As verified on the date above, the floating hosted aliases map to:

qwen3-coder-plus → qwen3-coder-plus-2025-09-23
qwen3-coder-flash → qwen3-coder-flash-2025-07-28

Alias mappings and regional availability can change. Applications that require reproducibility should use a documented dated ID where the required region provides it.

Call Model Studio with Node.js

Set DASHSCOPE_BASE_URL to the OpenAI-compatible endpoint for your Model Studio region and workspace.

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.DASHSCOPE_API_KEY,
  baseURL: process.env.DASHSCOPE_BASE_URL,
});

const completion = await client.chat.completions.create({
  model: "qwen3-coder-next",
  messages: [
    {
      role: "system",
      content: "You are a careful coding assistant."
    },
    {
      role: "user",
      content: (
        "Write a JavaScript function that groups objects by a selected key. "
        + "Return code without Markdown fences."
      )
    }
  ],
});

console.log(completion.choices[0].message.content);

Do not hard-code API credentials in source files. Model IDs, endpoints, and availability should be checked for the selected Alibaba Cloud region.

Is Qwen3-Coder multimodal?

The Qwen3-Coder models covered here are text models. They do not natively accept screenshots or other image inputs. A coding agent can use an external vision model or screenshot-analysis tool, but that does not make Qwen3-Coder itself multimodal.

Deployment limitations

Generated code can contain functional or security defects.
Tool calls must be authorized, validated, and executed by the application.
Native 256K context can require substantial KV-cache memory.
A MoE active-parameter figure is not the full checkpoint size.
The official max_new_tokens=65536 examples do not establish a universal output guarantee for every runtime.
Quantization can change quality, memory use, throughput, and supported context.
Repository-wide benchmark claims should be read with their evaluation date and configuration.

Frequently asked questions

Does Qwen3-Coder-Next generate Thinking blocks?

The open Qwen/Qwen3-Coder-Next checkpoint is explicitly non-thinking and does not generate <think> blocks.

Does Qwen3-Coder-Next support 1M context locally?

Its specific open model card documents 262,144 tokens natively. This guide does not promise a local 1M range for Coder-Next without checkpoint-specific deployment documentation.

Are qwen3-coder-plus and qwen3-coder-flash downloadable weights?

They are hosted Model Studio IDs. They should not be described as Hugging Face checkpoint names or treated as identical to the 30B, 80B, or 480B open repositories.

Does Qwen3-Coder support exactly 358 programming languages equally?

The official repository publishes a list of 358 coding-language and syntax labels, including file and configuration formats. The list does not guarantee equal proficiency across every entry.

Official sources

For the preceding generation, see Qwen2.5-Coder. For general Qwen models, review the Qwen3 guide.

This independent technical reference is not operated by Alibaba Cloud or the Qwen team. Test generated code and tool calls in a controlled environment.

Qwen3-Coder: Open Models, Coder-Next, API, and Setup