Back to Models
qwen logoQwen
qwen/qwen-plus
Not Available

Qwen-Plus

Qwen-Plus, based on the Qwen2.5 foundation model, is a 131K context model with a balanced performance, speed, and cost combination.

2/1/2025
1,000,000 tokens
#185 Text (Japanese)

Specifications

Modalities

Input
text
Output
text

Supported Parameters

max_tokens
presence_penalty
response_format
seed
temperature
tool_choice
tools
top_p

Max Output Tokens

32,768

Data policy

Prompt retention
Unknown — we could not confirm
Training
Unknown — not declared

"Unknown" does not mean "safe". It means we could not confirm it.

Whether a provider trains on prompts is a declared value from our terms with them. Retention is determined from the upstream listing for every host this model can reach. Neither is guessed.

Frequently asked questions

Is Qwen-Plus available on FastMetal?
Not at the moment. Qwen3 VL 235B A22B Instruct, from the same lab, is available on the FastMetal API today.
What is the context window of Qwen-Plus?
1,000,000 tokens, shared between the prompt and the response.
How does Qwen-Plus rank?
#185 on the public arena's Japanese board (ELO 1,278). Ranks move as the leaderboard is updated.

Leaderboard

Text
russianELO: 1,354
#202
CodingELO: 1,378
#239
MathELO: 1,322
#232
Creative WritingELO: 1,316
#219
Instruction FollowingELO: 1,332
#227
Hard PromptsELO: 1,352
#235
Multi-TurnELO: 1,353
#210
OverallELO: 1,346
#228
JapaneseELO: 1,278
#185
ChineseELO: 1,375
#216
EnglishELO: 1,356
#240

Rankings: LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset), CC BY 4.0, snapshot 2026-10-22; category names mapped and ratings rounded by FastMetal.