Kilo Gateway
RadixArk: DaisyRose 27B
DaisyRose 27B is an open-weight multimodal reasoning model from RadixArk, trained from [Qwen3.8 27B](https://openrouter.ai/qwen/qwen3.8-27b) using reinforcement learning only on long-horizon agent tasks, with no supervised fine-tuning or distillation. It is...
radixark/daisyrose-27bContext
262.1K
Max output
235.9K
Input $/M
$0.20
Output $/M
$2.50
Cache read $/M
$0.05
Cache write $/M
—
Against the catalogue
Context window262.1K
Larger than 44% of the 10,022 models listed
Input price$0.20
Cheaper than 69% of priced models
Capabilities
Reasoningsupported
Tool callingsupported
Structured outputsupported
Attachmentssupported
Temperaturesupported
Open weightsnot supported
Interleaved thinkingnot supported
Modalities
Input
TextImage
Output
Text
Reasoning controls
effortnone, low, medium, xhighPricing detail
| Rate | Base $/M |
|---|---|
| Input | $0.20 |
| Output | $2.50 |
| Cache read | $0.05 |