qwen

Qwen: Qwen-Plus

Qwen-Plus is a text-in, text-out model from Alibaba's Qwen team, offering a 1,000,000-token context window and up to 32,768 tokens of output per response. It supports tool use, which makes it usable in agentic pipelines, but it does not support reasoning modes and has no confirmed structured output capability. Input is limited to text; no image or audio modalities are available. At $0.26 per million input tokens and $0.78 per million output tokens, the pricing sits in the budget-to-mid range, making it worth considering for high-volume or long-context text tasks where cost control matters. The significant caveat is that no independent benchmark coverage exists yet, so there is no verified performance data to set expectations. Buyers willing to run their own evals on specific tasks may find the price-to-context ratio attractive, but anyone needing third-party validation before committing should treat it as unproven for now.

Quality Score
94/100
price + capability + benchmarks
Input Price
$0.26
per 1M tokens
Output Price
$0.78
per 1M tokens
Context Window
1,000,000
tokens
Model ID
qwen/qwen-plus
Vendor
qwen
Released
February 2025
Tokenizer
Qwen
Input Modalities
text
Output Modalities
text
Max Output
32,768 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 $0.26/M input and $0.78/M output rates. Run your own numbers →

JobTokensCost
Summarize a 50-page report 30k in / 1.5k out under $0.01
Classify 1,000 customer emails 500k in / 50k out $0.17
A month of a busy support chatbot 5M in / 2M out $2.86

Similar models

Quick answers

How much does Qwen: Qwen-Plus cost?
$0.26 per million input tokens and $0.78 per million output tokens.
What is Qwen: Qwen-Plus's context window?
1,000,000 tokens, roughly 1,500 pages of text in a single request.
Does Qwen: Qwen-Plus support tool calling?
It supports tool calling, structured output.
Can Qwen: Qwen-Plus process images?
No, it is text-only on the input side.