qwen

Qwen: Qwen3 Coder Plus

Qwen3 Coder Plus is a text-in, text-out model from Qwen with a 1,000,000-token context window and a 65,536-token output ceiling. It supports tool use, which makes it suited for agentic coding workflows, but it does not support reasoning mode and has no confirmed structured output capability. There is no information on open weights, so deployment flexibility beyond the API is unclear. The case for shortlisting it rests largely on its coding-focused positioning and generous context length, which can accommodate large codebases in a single pass. At $0.65 per million input tokens and $3.25 per million output tokens, it sits in a mid-range price band for coding-oriented models. The honest caveat is that there is no independent benchmark coverage yet, so performance relative to competitors is unverified; buyers prioritizing proven, measurable quality should wait for third-party evaluations before committing.

Quality Score
93/100
price + capability + benchmarks
Input Price
$0.65
per 1M tokens
Output Price
$3.25
per 1M tokens
Context Window
1,000,000
tokens
Model ID
qwen/qwen3-coder-plus
Vendor
qwen
Released
September 2025
Tokenizer
Qwen3
Input Modalities
text
Output Modalities
text
Max Output
65,536 tokens
Tool Calling
✓ supported
Structured Output
✓ supported
Reasoning Mode
not supported
Vision
text only
Audio
no
Moderated
no

What it costs in practice

Computed from the current $0.65/M input and $3.25/M output rates. Run your own numbers →

JobTokensCost
Summarize a 50-page report 30k in / 1.5k out $0.02
Classify 1,000 customer emails 500k in / 50k out $0.49
A month of a busy support chatbot 5M in / 2M out $9.75

Similar models

Quick answers

How much does Qwen: Qwen3 Coder Plus cost?
$0.65 per million input tokens and $3.25 per million output tokens.
What is Qwen: Qwen3 Coder Plus's context window?
1,000,000 tokens, roughly 1,500 pages of text in a single request.
Does Qwen: Qwen3 Coder Plus support tool calling?
It supports tool calling, structured output.
Can Qwen: Qwen3 Coder Plus process images?
No, it is text-only on the input side.