Compact
Phi-4
Microsoft's compact reasoning model. Surprisingly capable for its size, ideal for edge deployments and cost-sensitive faith-tech apps.
Parameters
14B
Context
16K
Input Price
$0.01/1M tok
Output Price
$0.02/1M tok
Latency
~100ms
Key Strengths
- ✓ Very compact
- ✓ Strong reasoning for size
- ✓ Extremely low cost
- ✓ Fast inference
- ✓ Good for edge
Use Cases
Edge/mobile deployments
Cost-sensitive apps
Simple Q&A
Classification tasks
Quick Start
import OpenAI from 'openai';
const client = new OpenAI({
baseURL: 'https://api.xalen.io/v1',
apiKey: 'your-xalen-api-key'
});
const response = await client.chat.completions.create({
model: 'phi-4',
messages: [
{ role: 'system', content: 'You are a Vedic astrology expert.' },
{ role: 'user', content: 'Analyze the effects of Jupiter in the 7th house.' }
],
max_tokens: 1024
});
console.log(response.choices[0].message.content);Frequently Asked Questions
What is Phi-4?
Microsoft's compact reasoning model. Surprisingly capable for its size, ideal for edge deployments and cost-sensitive faith-tech apps.
How much does Phi-4 cost?
Pricing starts at $0.01 per 1M input tokens and $0.02 per 1M output tokens. Batch processing gets a 50% discount. No monthly minimums.
What languages does Phi-4 support?
14 Indian languages including Hindi, Tamil, Telugu, Kannada, Malayalam, Bengali, Marathi, Gujarati, Odia, Punjabi, Assamese, Sinhala, Nepali, and Sanskrit. Plus English.
How do I access Phi-4?
Use any OpenAI-compatible SDK. Set base URL to api.xalen.io/v1 and use your XALEN API key. Python, JavaScript, and Go SDKs also available.