Alibaba Cloud: Qwen Plus Character
qwen-plus-character- Input / Output
- $0.50 / $1.40
- Context
- 32K
- Max output
- 4K
- Modalities
- Chat
- Capabilities
- Prompt Cache
About Qwen Plus Character
Qwen Plus Character is Alibaba's role-play model for extended conversations around a defined persona. Alibaba tuned it to follow a character profile, move topics forward and listen with empathy, and describes it as able to restore personalized characters in depth. It is the richer sibling of Qwen Flash Character, and it does not offer thinking mode.
Where it works well
- Follows detailed character profiles including backstory, relationships and speech habits.
- Keeps the character's voice while referring back to events from earlier turns.
- Supports group-chat style scenes where several characters speak in one conversation.
- Gives more polished persona replies than Qwen Flash Character when quality outweighs speed.
When to choose another model
- Its window is moderate, so very long campaigns need your own running summary.
- It has no thinking mode, so it is a poor fit for puzzle-solving or analytic work.
- For fast, cheap dialogue at scale, Qwen Flash Character responds quicker.
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-character", "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.
Default
per 1M tokens- Official price
- Input $0.50 / Output $1.40 / Cache read $0.10 / Text Input $0.50 / Text Output $1.40
- Verified price
- —
- Discount
- —
Cache read
- Official price
- $0.10
- Verified price
- —
- Discount
- —
| Official priceper 1M tokens | Verified priceper 1M tokens | Discount | |
|---|---|---|---|
| Default | Input $0.50 / Output $1.40 / Cache read $0.10 / Text Input $0.50 / Text Output $1.40 | — | — |
| Prompt cache pricing | |||
| Cache read | $0.10 | — | — |
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 Character in Console with a prompt ready to edit or send.
Help me try qwen-plus-character with a short message at /v1/responses. Show the reply, latency, and cost.
Use cases
Story-driven games
Voice a main character or companion whose personality must hold steady across a long play session.
IP character chat
Let fans talk to a licensed character in an app, using a profile written from the source material.
Virtual companions
Run a persistent persona that recalls details the user shared earlier in the chat.
Multi-character scenes
Simulate a table of characters reacting to each other and the player in one thread.
Prompt examples
Stay in character as Captain Ines Varga, a weary starship commander. I am a new recruit reporting for duty. Remember what I tell you.
You are three characters at a tavern: the barkeep, a bard, and a thief. Respond to my entrance with one line from each.
Continue the story as the lighthouse keeper, referring back to the storm I mentioned earlier, and end with a question for me.
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 Character used for?
Persona-based conversation for games, companion apps, character IP and similar products. You supply the character profile and the model keeps its voice across turns. It is not designed for factual Q&A or code.
How is Qwen Plus Character different from Qwen Plus?
Plus is a general assistant; Plus Character is tuned to sustain a persona, advance the topic and respond with empathy. Use the character model for role-play and the standard model for analysis, writing and answers from documents.
Plus Character or Flash Character?
Choose Plus Character when persona depth and polish matter most, as in a story-led game. Choose Flash Character when you need quick replies and many iterations. Compare both on the same character profile.
Does Qwen Plus Character support thinking mode?
No. The catalog lists thinking as off for this model, which suits natural in-character replies but not step-by-step reasoning or puzzle solving. Pick a reasoning-capable model for those jobs.
Can Qwen Plus Character handle group chats?
Alibaba's role-play guide describes group-chat simulation with several characters across the character models. Name each speaker in the system prompt and tell the model who speaks when.
How much does Qwen Plus Character cost?
On TokenLab, Qwen Plus Character costs Input $0.50 / Output $1.40 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 Character?
Qwen Plus Character accepts up to 32,768 tokens of context and returns up to 4,096 tokens in one response.
Which endpoint should Qwen Plus Character use?
Use https://api.tokenlab.sh/v1/responses for Qwen Plus Character. The request example below shows the matching code shape.
Which operations does Qwen Plus Character support?
Qwen Plus Character supports Text to text. Select an operation above to see its endpoint and request example.
Compare Qwen Plus Character
Sources
Reviewed Oct 2, 2026
