daisyrose-27b - API for Egypt, billed in EGP
LiveDaisyRose-27B is RadixArk's multimodal reasoning model, trained from Qwen3.8-27B with reinforcement learning only on long-horizon agent tasks. It improves on the base model in agentic coding, reasoning and instruction following, with thinking that can be enabled or disabled, image understanding and a 256K-token context.
Modality
Chat
Context window
262K tokens
Max output
16K tokens
Region
US
Weights
Open weights
Published
21 Nov 2026
Pricing
Input
8.81
EGP per 1M tokens
Output
110.17
EGP per 1M tokens
Cache read
2.20
EGP per 1M cached input tokens
Monthly cost example
2,093.2 EGP
Illustrative estimate: 50M input + 15M output tokens per month at this model’s catalog rates.
Use it via the API
daisyrose-27b works with any OpenAI-compatible SDK — point the base URL at https://backend.sovereigneg.com/v1 and use your SovereignEG API key.
Run inference
POST /v1/chat/completions — OpenAI-compatible: SovereignEG's own seg-sdk, or a drop-in for any OpenAI SDK.
from seg import SEG # pip install seg-sdk
client = SEG(api_key="YOUR_API_KEY")
response = client.chat.completions.create(
model="daisyrose-27b",
messages=[
{"role": "user", "content": "What are some fun things to do in Cairo?"}
],
)
print(response.choices[0].message.content)from openai import OpenAI
client = OpenAI(
base_url="https://backend.sovereigneg.com/v1",
api_key="YOUR_API_KEY",
)
response = client.chat.completions.create(
model="daisyrose-27b",
messages=[
{"role": "user", "content": "What are some fun things to do in Cairo?"}
],
)
print(response.choices[0].message.content)import OpenAI from "openai"
const client = new OpenAI({
baseURL: "https://backend.sovereigneg.com/v1",
apiKey: "YOUR_API_KEY",
})
const response = await client.chat.completions.create({
model: "daisyrose-27b",
messages: [
{ role: "user", content: "What are some fun things to do in Cairo?" },
],
})
console.log(response.choices[0].message.content)curl https://backend.sovereigneg.com/v1/chat/completions \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "daisyrose-27b",
"messages": [
{"role": "user", "content": "What are some fun things to do in Cairo?"}
]
}'Frequently asked questions
How much does daisyrose-27b cost?
8.81 EGP per 1M input tokens; 110.17 EGP per 1M output tokens. Billing is metered per token in Egyptian pounds (EGP), with no minimum commitment.
What is the context window of daisyrose-27b?
daisyrose-27b supports a context window of 262,144 tokens (262K), with up to 16,384 output tokens per response.
Where is daisyrose-27b hosted?
daisyrose-27b is served from US (US-hosted inference).
Is daisyrose-27b an open-weights model?
Yes — daisyrose-27b is an open-weights model. You call it through the SovereignEG API like any other catalog model, with per-token EGP billing.
How do I use daisyrose-27b via the API?
daisyrose-27b is available through the OpenAI-compatible SovereignEG API: point your SDK's base URL at https://backend.sovereigneg.com/v1 and call /v1/chat/completions with model "daisyrose-27b" and your API key.
Related models
View all models →Arize AI Qwen 2 1.5B Instruct
arize-ai · Chat · 33K context
5.88 EGP / 1M input tokens
Beam 1.0 501B A23B
reflection · Chat · 1M context
23.50 EGP / 1M input tokens
Claude Fable 5.1
Anthropic · Chat · 1M context
587.57 EGP / 1M input tokens
Claude Fable 5.2
Anthropic · Chat · 1M context
470.05 EGP / 1M input tokens