Qwen3 Coder Next

Provider: Alibaba (Qwen) CN

Input price
$0.12
/ 1M tokens
Output price
$0.80
/ 1M tokens
Cache price
$0.07
/ 1M tokens (read)
Context
262K tokens
Max output 236K tokens

Overview

Alibaba's Qwen3 Coder Next is an 80B open-weight sparse MoE coding specialist (3B active parameters) built for developer workflows. It has no free tier and runs on third-party hosts.

Strengths

  • Sparse MoE architecture activating three billion parameters
  • Large context window spanning two hundred sixty thousand tokens
  • Supports native function calling and JSON mode
  • High output token limit exceeding two hundred thousand

Best use cases

  • Autonomous coding agents and repository analysis
  • Local developer workflow automation scripts
  • Structured data extraction via JSON mode

Pricing position

Input costs $0.12 and output costs $0.80 per million tokens, sitting near DeepSeek V4 Flash at $0.17 output and GPT-5 Mini at $1.00 output.

Caveats

Output pricing exceeds sibling Qwen3.7 Flash and Qwen3 Coder 30B A3B Instruct. Select a 1M context provider if larger windows are mandatory.

Notes drafted by an LLM from the figures on this page (2026-11-10) and rewritten when the price changes.

Key facts

Price basis
Median third-party host price (no first-party API)
Max output
236K tokens
Listed on OpenRouter
2026-02-04
Tracked since
2026-05-08
Last updated
2026-11-10

Features

Function callingJSON output

Monthly cost estimate

Scale Input (M) Output (M) Monthly
0.1M (hobby) 0.1 0.05 $0.05
1M (small app) 1 0.5 $0.52
10M (mid scale) 10 5 $5.20
100M (large) 100 50 $52.00

※ Cache and batch discounts not factored in. Detailed calculator

Official resources

Other models from Alibaba (Qwen)

Similar-priced models

Source: OpenRouter API (qwen/qwen3-coder-next)