Qwen3 Coder Plus
1862°
Run this model
Offers / Ads
Qwen | 1,000,000 token context | $0.65/M input, $3.25/M output. Qwen3 Coder Plus is Alibaba's proprietary version of the Open Source Qwen3 Coder 480B A35B. It is a powerful coding agent model specializing in autonomous programming via tool calling and...
Guides for this model
Open weights vs open source vs API-only: what you are actually allowed to do
How to choose an AI model in October 2026: the closed source news, then the open weights worth downloading
The 10 cheapest ChatGPT alternatives in 2026: free local models, free tiers and flat-rate plans
Captain's notes
Notes from 2026-10-13
Qwen3 Coder Plus is Alibaba's proprietary API version of the Qwen3 Coder 480B A35B architecture, tuned specifically for autonomous coding work via tool calling. The one-million-token context window sets it apart from most coding models, making it practical for large codebases in a single pass. It suits developers who want an agentic coding model they can drop into a pipeline without managing weights.
Known for
- Autonomous programming via tool calling and agentic workflows
- One-million-token context — fit for large, multi-file codebases
- Backed by the 480B A35B architecture, a serious parameter count
- Proprietary build on an otherwise open-weight model family
Watch out for
- Weights are not released; you are API-only, no local deployment.
- Output tokens cost five times the input rate — agentic loops with heavy generation add up fast.
- Licence and usage terms are Alibaba's; the maker has not published them prominently.
Prompts to try
Refactor a large module
Here is a Python module that handles user authentication. It mixes database calls, business logic and HTTP responses in the same functions. Refactor it into three clearly separated layers — data access, service and controller — without changing the external behaviour. Explain each structural decision you make.
Build a CLI tool end-to-end
Write a self-contained Node.js CLI tool that watches a directory for new JSON files, validates each against a schema I will describe, and moves valid files to a processed folder and invalid ones to a rejected folder with a reason log. Use only Node built-ins, no npm packages. Include error handling and a usage message.
Debug a failing test suite
I have a Go test suite where three tests pass locally but fail in CI with a race condition error. The tests share a global map that multiple goroutines write to. Identify the problem, explain why it surfaces in CI but not locally, and rewrite the relevant code to be safe without using a global mutex.
Compare with
- Qwen3.8 FlashOpen-weights model1,000,000 token context · $0.15/M input, $0.47/M output
- Qwen3 Coder NextOpen-weights model262,144 token context · $0.12/M input, $0.80/M output
- Qwen3 Coder 480B A35BOpen-weights model262,144 token context · $0.30/M input, $1.00/M output
- Qwen3 Next 80B A3B InstructOpen-weights model262,144 token context · $0.09/M input, $1.10/M output
More text models from qwen
Questions people ask
- Can I run Qwen3 Coder Plus locally?
- No. Qwen3 Coder Plus is a proprietary API model; Alibaba has not released the weights. The open-weight sibling, Qwen3 Coder 480B A35B, is a separate model you can download and run yourself.
- What does it cost and how long is the context?
- Pricing is $0.65 per million input tokens and $3.25 per million output tokens, with a one-million-token context window.
- How does this differ from the open-weight Qwen3 Coder?
- Qwen3 Coder Plus is Alibaba's hosted, proprietary build on the same underlying architecture — you get it via API only, while the open-weight version can be downloaded and self-hosted.
Captain's verdictA serious agentic coding model with a genuinely useful million-token window, but the output pricing means you should watch your loop costs.
Captain writes these notes from the model's own description and model card. Prices and context sizes are the provider's at the time of writing and can change.
Ranking badge
Updated Oct 22, 2026
Made this model? Show this badge on your page.
Paste it into your Hugging Face card or Civitai description.
How this score adds up
This model has no popularity data from any source yet, so it carries a stand-in number below 7,000° that keeps the lists complete. It never ranks above a model with data. The breakdown appears here as soon as a source reports it.
Glossary: the terms used here
- Heat score
- One number for how much a model is used and wanted right now, from 0° to 9,999°. Every list on this site that says hottest is sorted by it and nothing else.
- Floor
- The 7,000° every model with real data starts from. The scale runs from 0° to 9,999°; the part below the floor is reserved for stand-ins (models without data), so that a model with data always ranks above one without. The floor is the same for everyone and decides nothing; the degrees above it are the measurement.
- Download-equivalents
- Everything the score treats as a download, added up: downloads themselves, each torrent seeder as 1,000, each AI Horde image and each run on a generation site as one.
- Log scale
- Counting by tens, not by ones: going from 1,000 to 10,000 downloads adds the same degrees as going from 10,000 to 100,000. It keeps giants from crowding out everything else.
- Likes
- Thumbs up and likes from every source, worth half a download each on the log scale.
- Adoption rate
- How many downloads a day a model gets right now, from the difference between two readings of a source. A quarter of the weight of the download term.
- Measured and estimated
- Measured means two readings of a source exist and the difference is real. Estimated means only today's total is known and the past is spread over the model's life; the site says which one it is showing.
- Seeder
- Someone who keeps a copy of the weights online for others to download over a torrent, or a hosted mirror doing the same. Each one counts as 1,000 downloads.
- AI Horde
- A volunteer network that generates images for free on donated computers. The number of images it has made with a model is public, and each counts as one download.
- Generation sites
- Sites that host their own copies of a model and let people generate with it, such as PixAI, SeaArt and Yodayo. Their downloads count like Civitai's and each generation run as one download.
- OpenRouter tokens
- A text model served through an API, such as Claude or GPT, has no weights to download, so its usage is measured in tokens: the pieces of text it read and wrote through OpenRouter, a gateway many apps use, over the last 30 days. Every 10,000,000 tokens count as one download. Source: OpenRouter (openrouter.ai/rankings), CC BY 4.0.
- Full model (checkpoint)
- The weights themselves, the file that generates on its own. It gets a bonus because add-ons depend on it.
- LoRA and embedding
- Small add-on files that steer someone else's weights toward a style, a character or a concept. They cannot run alone.
- Family and weights
- The base a model is built on, such as SD 1.5, SDXL, Flux or Wan. Every model inherits the release date of its family's weights.
- Age
- Degrees taken off for how long ago the family's weights came out: 150° a year, up to 750°. It keeps old downloads that had years to pile up from freezing the top of the list.
- Family boost
- A small, bounded nudge for LoRAs of a family this site is pushing forward right now, always listed in the breakdown.
- Stand-in score
- A stable number below the floor given to a model no source reports on yet, so lists stay complete. It never ranks above a model with data.
- New! (grace period)
- A model less than 7 days old shows New! instead of a score and holds no place in the rankings. Its score is computed from day one, but a model one day old grows faster than anything, so without the wait the week's #1 would always be whatever came out yesterday rather than what held up for a week.
- Trend
- How a model's growth over a period compares with the typical model's growth over the same period. Faster than typical reads as a rise, slower as a fall.
- Typical model
- The middle of the catalog: half the models with a figure grew faster over the period, half slower.
Qwen3 Coder Plus is a text model for the Text / LLM family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Text / LLM models and check its heat score to see how it is trending.
Browse by Model Family
Text / LLM Models
434
Anima Models
528
Chroma Models
19
Fibo Models
2
Flux Models
1,496
Flux 2 / Klein Models
1,239
Flux 3 Models
3
Moss Models
3
Iris Models
1
MiniMax H3 Models
364
Hunyuan Models
204
Ideogram Models
20
Krea2 Models
717
Qwen Models
20
Qwen2 Models
47
Ltx2 Models
153