per 1M tokens
microsoft/phi-4
deepinfra/microsoft/phi-4
Phi-4 is a model built upon a blend of synthetic datasets, data from filtered public domain websites, and acquired academic books and Q&A datasets. The goal of this approach was to ensure that small capable models were trained with data focused on high quality and advanced reasoning.
Price
per 1M tokens
Providers
Each row is one seller. Prices are the published rate from that source. A dash means that source did not publish the amount. Sorted by a 3:1 blend of input and output.
No provider prices yet.
Monthly bill
Token models use the token counts. Image, video, and audio models use units times the flat rate.
$0.21 at list price for this workload
Every rate
| Unit | Input | Output | Flat | Confidence |
|---|---|---|---|---|
| token | $0.07/1M | $0.14/1M | Not published— | official |
Price history
input or flat output
Daily snapshots
| UTC date | Unit | Input | Output | Flat |
|---|---|---|---|---|
| 2026-10-08 | token | $0.07 | $0.14 | Not published— |
| 2026-10-09 | token | $0.07 | $0.14 | Not published— |
| 2026-10-10 | token | $0.07 | $0.14 | Not published— |
| 2026-10-11 | token | $0.07 | $0.14 | Not published— |
| 2026-10-12 | token | $0.07 | $0.14 | Not published— |
| 2026-10-13 | token | $0.07 | $0.14 | Not published— |
| 2026-10-14 | token | $0.07 | $0.14 | Not published— |
| 2026-10-15 | token | $0.07 | $0.14 | Not published— |
| 2026-10-16 | token | $0.07 | $0.14 | Not published— |
| 2026-10-17 | token | $0.07 | $0.14 | Not published— |
| 2026-10-18 | token | $0.07 | $0.14 | Not published— |
| 2026-10-19 | token | $0.07 | $0.14 | Not published— |
| 2026-10-20 | token | $0.07 | $0.14 | Not published— |
| 2026-10-21 | token | $0.07 | $0.14 | Not published— |
| 2026-10-22 | token | $0.07 | $0.14 | Not published— |
| 2026-10-23 | token | $0.07 | $0.14 | Not published— |
| 2026-10-24 | token | $0.07 | $0.14 | Not published— |
| 2026-10-25 | token | $0.07 | $0.14 | Not published— |
| 2026-10-26 | token | $0.07 | $0.14 | Not published— |
| 2026-10-27 | token | $0.07 | $0.14 | Not published— |
| 2026-10-28 | token | $0.07 | $0.14 | Not published— |
| 2026-10-29 | token | $0.07 | $0.14 | Not published— |
| 2026-10-30 | token | $0.07 | $0.14 | Not published— |
Alternatives
- Baichuan M2 32B$0.07/1M · Compare
- GLM 4.7 Flash$0.07/1M · Compare
- GLM 4.7 Flash$0.07/1M · Compare
- google/gemma-4-26B-A4B-it$0.07/1M · Compare
- GPT OSS Safeguard 20B$0.07/1M · Compare
- GPT OSS Safeguard 20B$0.07/1M · Compare
Parameters (1)
chat
Call this model
OpenRouter id deepinfra/microsoft/phi-4. InferenceList does not send the request.
curl
curl https://openrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"deepinfra/microsoft/phi-4","messages":[{"role":"user","content":"Hello"}]}'
JavaScript
await fetch("https://openrouter.ai/api/v1/chat/completions", {
method: "POST",
headers: {
Authorization: "Bearer " + process.env.OPENROUTER_API_KEY,
"Content-Type": "application/json",
},
body: JSON.stringify({
model: "deepinfra/microsoft/phi-4",
messages: [{ role: "user", content: "Hello" }],
}),
});
Python
import os, json, urllib.request
req = urllib.request.Request(
"https://openrouter.ai/api/v1/chat/completions",
data=json.dumps({"model": "deepinfra/microsoft/phi-4", "messages": [{"role": "user", "content": "Hello"}]}).encode(),
headers={"Authorization": "Bearer " + os.environ["OPENROUTER_API_KEY"], "Content-Type": "application/json"},
)
print(urllib.request.urlopen(req).read().decode())