Qwen3 Coder Plus

Provider: Alibaba (Qwen) CN

No longer listed on OpenRouter since 2026-10-09. The figures below are the last recorded values.
Input price
$0.65
/ 1M tokens
Output price
$3.25
/ 1M tokens
Cache price
$0.13
/ 1M tokens (read)
Context
1M tokens
Max output 66K tokens

Overview

Qwen3 Coder Plus is Alibaba's flagship reasoning specialist model, designed primarily for complex coding workloads. It offers an exceptionally large context window and advanced capabilities for structured interactions, positioning it as a high-tier option for developers.

Strengths

  • Exceptional 1,000,000 token context window, ideal for processing extensive codebases.
  • Robust support for function-calling, enabling complex tool use and agentic workflows.
  • Reliable JSON mode for generating structured and parseable output directly.
  • Large maximum output of 65,536 tokens, suitable for generating significant code blocks.

Best use cases

  • Analyzing and refactoring entire code repositories or large software projects.
  • Generating complex multi-file applications or comprehensive API documentation.
  • Automated code review, vulnerability detection, and intelligent suggestion systems.
  • Building sophisticated agents that interact with external tools via function-calling.
  • Extracting structured information from vast technical documentation in JSON format.

Pricing position

At $0.65 per million input tokens and $3.25 per million output tokens, Qwen3 Coder Plus is Alibaba's most premium offering, priced significantly higher than general-purpose Qwen models like Qwen3.5-Flash (input $0.065/M, output $0.26/M) which also offers a 1M context. Its input price is comparable to Gemma 2 27B ($0.65/M) and R1 ($0.7/M), but its output price is considerably higher than most similarly-priced peers.

Caveats

This model does not offer a free tier, unlike some competitors, and its high pricing may be prohibitive for casual or low-volume general text generation tasks. For non-coding applications or shorter contexts, significantly cheaper Qwen models or smaller alternatives from other providers would be more cost-effective. The model does not list vision capabilities, so it is not suitable for multimodal tasks involving images.

Notes drafted by an LLM from the figures on this page (2026-05-21) and rewritten when the price changes.

Key facts

Max output
66K tokens
Tracked since
2026-05-08
Last updated
2026-10-09

Features

Function callingJSON output

Price history

  • 2026-10-09 No longer listed

Monthly cost estimate

Scale Input (M) Output (M) Monthly
0.1M (hobby) 0.1 0.05 $0.23
1M (small app) 1 0.5 $2.27
10M (mid scale) 10 5 $22.75
100M (large) 100 50 $227.50

※ Cache and batch discounts not factored in. Detailed calculator

Official resources

Other models from Alibaba (Qwen)

Similar-priced models

Source: OpenRouter API