radixark logo
radixark

RadixArk: DaisyRose 27B

Source description (English)

DaisyRose 27B is an open-weight multimodal reasoning model from RadixArk, trained from Qwen3.8 27B using reinforcement learning only on long-horizon agent tasks, with no supervised fine-tuning or distillation. It is...

Overview

Model specifications

Context
262,144 tokens
Maximum output
235,929 tokens
Architecture
text+image->text
Tokenizer
Qwen
Knowledge cutoff
Not provided
Moderated
No
OPENROUTER

Complete pricing

Synchronized OpenRouter rates. Token prices are shown per one million tokens.

Input
$0.15
per 1M tokens
Output
$1.875
per 1M tokens
Cache read
$0.0375
per 1M tokens
API

Model configuration

Default parameters

temperature
1
top_p
0.95
top_k
20

Reasoning

Reasoning required
No
Default parameters
xhigh
Capabilities
xhigh, medium, low, none
API

Quick start

Set OPENROUTER_API_KEY locally. Python requires requests; JavaScript runs in Node.js. Keep the key on the server.

API documentation

curl --fail-with-body https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"radixark/daisyrose-27b","messages":[{"role":"user","content":"Hello!"}]}'
Capabilities

Input → Output

Input
textimage
Output
text
Reasoning

Yes · xhigh · medium · low · none

API

Supported API parameters

frequency_penaltyinclude_reasoninglogit_biasmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_p
Available providers

1 Provider

Checked: November 21, 2026

Live providers on OpenRouter

Provider availability, latency, throughput and routing can change continuously. Open the source page for current operational data.

OpenRouter

DeepInfra

bf16
Context
262K
Maximum output
236K
Input
$0.15
Output
$1.875
Cache read
$0.0375
Cache write
Not provided