Qwen
Qwen: Qwen3.8 27B
qwen/qwen3.8-27b
Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks, with flexible thinking that can be enabled or disabled.
Input
$0.24
/ 1M tokens
Output
$2.2
/ 1M tokens
Context window
1M
tokens
Limits
Context
1,000,000
tokens
Max output
235,929
24% of the context window
Parameters
27,781,427,952
Model facts
Author
Qwen
Tokenizer
Qwen
Modality
Text + Image + Video -> Text
License
Apache-2.0
Created
Aug 14, 2026
Hugging Face
Qwen/Qwen3.8-27B
Default generation parameters
temperature
1
top_k
20
top_p
0.95
Reasoning
Default XhighXhighMediumLowNone
Publication status
Hugging Face: verifiedLicense: publishedParameter count: published
Modalities
Input · TextInput · ImageInput · VideoOutput · Text
Generation controls
Frequency penaltyInclude reasoningLogit biasLogprobsMax tokensMin pPresence penaltyReasoningReasoning effortRepetition penaltyResponse formatSeedStopStructured outputsTemperatureTool choiceToolsTop aTop kTop logprobsTop p
Capability scores
45.8
Agentic index
Better than 82% of models compared
68.1
Coding index
Better than 69% of models compared
33.7
Intelligence index
Better than 75% of models compared