Alibaba Cloud: Qwen Plus
qwen-plus- Input / Output
- $0.40 / $1.20
- Context
- 998K
- Max output
- 32K
- Modalities
- Chat
- Capabilities
- Prompt Cache
About Qwen Plus
Qwen Plus is Alibaba's balanced general-purpose Qwen model for writing, analysis and dialogue, sitting between the lighter Qwen Flash and the stronger Qwen Max. It combines one of the largest context windows in the Qwen line with optional thinking mode. Alibaba lists it among legacy Qwen names and recommends newer generations such as Qwen3.7 Plus for new work.
Where it works well
- Answers with reference to a very large body of supplied text, such as manuals, transcripts or knowledge bases.
- Thinking mode can be enabled for questions that need step-by-step reasoning.
- Writing and analysis quality sits above Qwen Flash at moderate cost.
- Prompt caching reduces repeat work when the same reference material accompanies many requests.
When to choose another model
- Qwen Plus works on text alone, so screenshots, charts and scans need a vision-capable model.
- On the hardest coding and reasoning tasks Qwen Max or Qwen3.8 Max does better.
- Alibaba flags it as legacy, so a newer Qwen3.7 Plus may be a better default for new builds.
Getting started
Create API key
Create a key in Console, then use it with every model on the platform.
Send your first request
Copy the example for your language and run it against the endpoint.
Text to textResponses APIPOST/v1/responsesAPI format:curl https://api.tokenlab.sh/v1/responses \ -H "Content-Type: application/json" \ -H "Authorization: Bearer sk-xxx" \ -d '{ "model": "qwen-plus", "input": "Hello!" }'
Pricing
The Verified price applies to Verified, which costs less on most models. The Official price is the model maker's published price and applies to the more reliable Official route. Auto bills the route that completes the request.
Input tokens <= 256K · Mode · non-thinking · cacheMode · implicit
per 1M tokens- Official price
- Input $0.40 / Output $1.20 / Cache read $0.08 / Text Input $0.40 / Text Input · Cache read $0.08 / Text Output $1.20
- Verified price
- —
- Discount
- —
Input tokens <= 256K · Mode · non-thinking · cacheMode · explicit
per 1M tokens- Official price
- Input $0.40 / Output $1.20 / Cache read $0.04 / Cache write $0.50 / Text Input $0.40 / Text Input · Cache read $0.04 / Text Output $1.20
- Verified price
- —
- Discount
- —
Input tokens <= 256K · Mode · thinking · cacheMode · implicit
per 1M tokens- Official price
- Input $0.40 / Output $4.00 / Cache read $0.08 / Text Input $0.40 / Text Input · Cache read $0.08 / Text Output $4.00
- Verified price
- —
- Discount
- —
Input tokens <= 256K · Mode · thinking · cacheMode · explicit
per 1M tokens- Official price
- Input $0.40 / Output $4.00 / Cache read $0.04 / Cache write $0.50 / Text Input $0.40 / Text Input · Cache read $0.04 / Text Output $4.00
- Verified price
- —
- Discount
- —
Input tokens 256K-1M · Mode · non-thinking · cacheMode · implicit
per 1M tokens- Official price
- Input $1.20 / Output $3.60 / Cache read $0.24 / Text Input $1.20 / Text Input · Cache read $0.24 / Text Output $3.60
- Verified price
- —
- Discount
- —
Input tokens 256K-1M · Mode · non-thinking · cacheMode · explicit
per 1M tokens- Official price
- Input $1.20 / Output $3.60 / Cache read $0.12 / Cache write $1.50 / Text Input $1.20 / Text Input · Cache read $0.12 / Text Output $3.60
- Verified price
- —
- Discount
- —
Input tokens 256K-1M · Mode · thinking · cacheMode · implicit
per 1M tokens- Official price
- Input $1.20 / Output $12.00 / Cache read $0.24 / Text Input $1.20 / Text Input · Cache read $0.24 / Text Output $12.00
- Verified price
- —
- Discount
- —
Input tokens 256K-1M · Mode · thinking · cacheMode · explicit
per 1M tokens- Official price
- Input $1.20 / Output $12.00 / Cache read $0.12 / Cache write $1.50 / Text Input $1.20 / Text Input · Cache read $0.12 / Text Output $12.00
- Verified price
- —
- Discount
- —
| Official priceper 1M tokens | Verified priceper 1M tokens | Discount | |
|---|---|---|---|
| Input tokens <= 256K · Mode · non-thinking · cacheMode · implicit | Input $0.40 / Output $1.20 / Cache read $0.08 / Text Input $0.40 / Text Input · Cache read $0.08 / Text Output $1.20 | — | — |
| Input tokens <= 256K · Mode · non-thinking · cacheMode · explicit | Input $0.40 / Output $1.20 / Cache read $0.04 / Cache write $0.50 / Text Input $0.40 / Text Input · Cache read $0.04 / Text Output $1.20 | — | — |
| Input tokens <= 256K · Mode · thinking · cacheMode · implicit | Input $0.40 / Output $4.00 / Cache read $0.08 / Text Input $0.40 / Text Input · Cache read $0.08 / Text Output $4.00 | — | — |
| Input tokens <= 256K · Mode · thinking · cacheMode · explicit | Input $0.40 / Output $4.00 / Cache read $0.04 / Cache write $0.50 / Text Input $0.40 / Text Input · Cache read $0.04 / Text Output $4.00 | — | — |
| Input tokens 256K-1M · Mode · non-thinking · cacheMode · implicit | Input $1.20 / Output $3.60 / Cache read $0.24 / Text Input $1.20 / Text Input · Cache read $0.24 / Text Output $3.60 | — | — |
| Input tokens 256K-1M · Mode · non-thinking · cacheMode · explicit | Input $1.20 / Output $3.60 / Cache read $0.12 / Cache write $1.50 / Text Input $1.20 / Text Input · Cache read $0.12 / Text Output $3.60 | — | — |
| Input tokens 256K-1M · Mode · thinking · cacheMode · implicit | Input $1.20 / Output $12.00 / Cache read $0.24 / Text Input $1.20 / Text Input · Cache read $0.24 / Text Output $12.00 | — | — |
| Input tokens 256K-1M · Mode · thinking · cacheMode · explicit | Input $1.20 / Output $12.00 / Cache read $0.12 / Cache write $1.50 / Text Input $1.20 / Text Input · Cache read $0.12 / Text Output $12.00 | — | — |
Usage & activity
Success rate is the share of requests that completed. Latency is how long a full response takes; P95 means 95% of requests finished within that time.
Usage & availability
Last 24 hours- Requests
- Success rate
- P95 latency
- Total tokens
Data is based on aggregate user requests, excluding status checks.
Open in Console
Open Qwen Plus in Console with a prompt ready to edit or send.
Help me try qwen-plus with a short message at /v1/responses. Show the reply, latency, and cost.
Use cases
Knowledge-base assistants
Put product docs or policies in the prompt and answer customer questions with reference to them.
Report drafting
Turn raw notes, tables and meeting minutes into a structured report in a consistent tone.
Document analysis
Compare several long contracts or filings in one request and list differences that matter.
General chat backends
Serve as the default model for an app that needs solid answers across many topics.
Prompt examples
Here are three quarterly reports. Compare revenue drivers across them and flag any change in how metrics are defined.
Draft a reply to this customer complaint using the refund policy below, in a calm and brief tone.
Think through this scheduling problem step by step and give the final plan as a table.
This model has conditional pricing. Monthly token totals alone cannot produce a reliable estimate; use the detailed pricing for the request specification, cache, and applicable time window.
FAQ
What is Qwen Plus good at?
Everyday writing, analysis and dialogue, particularly when the answer depends on a lot of supplied text. It is the middle tier of the Qwen line, a sensible default before moving up to Max or down to Flash.
What is the difference between Qwen Plus and Qwen Flash?
Plus produces stronger analysis and more polished writing; Flash is quicker and cheaper for simple jobs. Both carry a large window and support thinking mode, so the choice mostly depends on how demanding the task is.
Does Qwen Plus support thinking mode?
Yes. Alibaba's documentation lists thinking mode as supported for Qwen Plus. Turn it on for multi-step reasoning and leave it off for short answers where latency matters more.
Should I use Qwen Plus or Qwen3.7 Plus?
Alibaba recommends newer Qwen3 models for general new work, so evaluate Qwen3.7 Plus first on a fresh project. Keep Qwen Plus where prompts are already tuned and results are stable.
Does Qwen Plus accept images?
No. Qwen Plus is a text model. For screenshots, charts or scanned documents, choose a Qwen model with image input, or send the extracted text instead.
How much does Qwen Plus cost?
On TokenLab, Qwen Plus costs Input $0.40 / Output $1.20 per 1M tokens. The pricing table above shows the full breakdown. Rates depend on the billing unit, specification, and usage. Compare matching conditions in the model's detailed pricing; a single rate does not determine the total cost.
What are the context window and output limit of Qwen Plus?
Qwen Plus accepts up to 997,952 tokens of context and returns up to 32,768 tokens in one response.
Which endpoint should Qwen Plus use?
Use https://api.tokenlab.sh/v1/responses for Qwen Plus. The request example below shows the matching code shape.
Which operations does Qwen Plus support?
Qwen Plus supports Text to text. Select an operation above to see its endpoint and request example.
Compare Qwen Plus
Sources
Reviewed Oct 2, 2026
