Skip to model information

Qwen3-Coder-Next

Deprecated

A Qwen model with a 256K-token context window and tool calling. On the Alibaba Cloud Model Studio API since February 20, 2026, now deprecated.

Access details: Alibaba Cloud Model Studio API

The model ID to use in API requests.

qwen3-coder-next

Open weights on Hugging Face: Qwen/Qwen3-Coder-Next

Updated Oct 1, 2026

Capabilities & limits

Context window
256K
Maximum output
64K
Image input
Unsupported
Tool calling
Supported
Structured output
Supported

Pricing

USD / 1M tokens
Input
$0.30
Output
$1.50

Standard rates per million tokens. Discounts and long-context rates, where offered, are on Qwen's pricing page.

Full rate card 6 rates

All prices in USD.

Input tokens

$0.30 per 1M tokens
  • input 0 to 32K tokens per request

Output tokens

$1.50 per 1M tokens
  • input 0 to 32K tokens per request
  • non-thinking mode only

Input tokens

$0.50 per 1M tokens
  • input 32K to 128K tokens per request

Output tokens

$2.50 per 1M tokens
  • input 32K to 128K tokens per request
  • non-thinking mode only

Input tokens

$0.80 per 1M tokens
  • input 128K to 256K tokens per request

Output tokens

$4.00 per 1M tokens
  • input 128K to 256K tokens per request
  • non-thinking mode only

USD, International deployment scope (Singapore region) on the international pricing page. Standard prices; the page notes limited-time promotions are excluded. Context-cache and explicit-cache rates are described on a separate page and were not captured; where the page flags a 50% batch discount it is noted here. Rates for other regions (China, Germany, US, Japan, Hong Kong) are not captured.

Price history
Oct 1, 2026

Input $0.30 per million tokens

Oct 1, 2026

Output $1.50 per million tokens

Technical details

Active parameters
3B
Architecture
Hybrid attention and MoE, built on Qwen3-Next-80B-A3B-Base
Input modalities
Text
Output modalities
Text

How they describe it

an open-weight language model designed specifically for coding agents and local development

Release & lifecycle

First available
Feb 20, 2026
deprecated
As of Oct 1, 2026

Considering a switch?

Specs only go so far. Try both on your own tasks and compare quality, speed and cost.

Compare with Gemini 3.5 Flash-Lite →

Prices and availability as of October 20, 2026. Qwen's own pages have the latest.