Available now
Microsoft
phi-4
Microsoft Research Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed. At 14 billion...
TextOpen Weights128K
InputFree
OutputFree
Context128K
Endpointsopenai
Capabilities
Structured
Modalities
Input
text
Output
text
Quick stats
Context window128K
Max output16.4K
Modechat
TokenizerOther
Knowledge cutoff2024
Quantizationbf16
Hugging Facemicrosoft/phi-4
Performance
Loading performance data...
Supported parameters
| Parameter | Always | Default |
|---|---|---|
| frequency_penalty | - | |
| logit_bias | - | - |
| logprobs | - | - |
| max_tokens | - | |
| min_p | - | - |
| presence_penalty | - | |
| repetition_penalty | - | |
| response_format | - | |
| seed | - | |
| stop | - | |
| structured_outputs | - | |
| temperature | - | |
| top_k | - | - |
| top_logprobs | - | - |
| top_p | - |
§ 01
Pricing
| Input price | $0.00 · 1M tokens |
| Output price | $0.00 · 1M tokens |
| Context window | 128K tokens |
| Compatible endpoints | openai |
| Vendor | Microsoft |
§ 02
Call phi-4 from your code
Point any OpenAI-compatible SDK at UnoRouter and request the model by name. Replace YOUR_API_KEY with a real key from your dashboard.
bash
curl https://api.unorouter.com/v1/chat/completions \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "phi-4",
"messages": [{"role": "user", "content": "Hello!"}]
}'§ 03
Frequently asked questions
How much does phi-4 cost per 1M tokens?
Input is priced at $0.00 per 1M tokens, output at $0.00 per 1M tokens. Billing is per token, no rounding to batch sizes.
How do I access phi-4 via API?
Send requests to the UnoRouter /v1/chat/completions endpoint with model=phi-4. Any OpenAI-compatible client library works. Authentication uses a standard Bearer token.
What is the context window of phi-4?
phi-4 supports a context window of 128K tokens, shared between your prompt and the model's response.
§ 04