per 1M tokens
Microsoft: Phi 4
microsoft/phi-4
[Microsoft Research](/microsoft) 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...
Price
per 1M tokens
Cheaper on DeepInfra (−20%) versus the OpenRouter list price
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.
| Provider | Tag | Quant | Input | Output | Context | Uptime | Status | Source |
|---|---|---|---|---|---|---|---|---|
| DeepInfra Price differs from the host list |
deepinfra/bf16/flex | bf16 | $0.056/1M | $0.112/1M | 16K | — | Live | openrouter-endpoints |
| DeepInfra | — | — | $0.07/1M | $0.14/1M | 16K | — | Listed | deepinfra |
| DeepInfra | deepinfra/bf16 | bf16 | $0.07/1M | $0.14/1M | 16K | 100% | Live | openrouter-endpoints |
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 |
|---|---|---|---|---|
| 2026-09-15 | token | $0.07 | $0.14 | Not published— |
| 2026-09-16 | token | $0.07 | $0.14 | Not published— |
| 2026-09-17 | token | $0.07 | $0.14 | Not published— |
| 2026-09-18 | token | $0.07 | $0.14 | Not published— |
| 2026-09-19 | token | $0.07 | $0.14 | Not published— |
| 2026-09-20 | token | $0.07 | $0.14 | Not published— |
| 2026-09-21 | token | $0.07 | $0.14 | Not published— |
| 2026-09-22 | token | $0.07 | $0.14 | Not published— |
| 2026-09-23 | token | $0.07 | $0.14 | Not published— |
| 2026-09-24 | token | $0.07 | $0.14 | Not published— |
| 2026-09-25 | token | $0.07 | $0.14 | Not published— |
| 2026-09-26 | token | $0.07 | $0.14 | Not published— |
| 2026-09-27 | token | $0.07 | $0.14 | Not published— |
| 2026-09-28 | token | $0.07 | $0.14 | Not published— |
| 2026-09-29 | token | $0.07 | $0.14 | Not published— |
| 2026-09-30 | token | $0.07 | $0.14 | Not published— |
| 2026-10-01 | token | $0.07 | $0.14 | Not published— |
| 2026-10-02 | token | $0.07 | $0.14 | Not published— |
| 2026-10-03 | token | $0.07 | $0.14 | Not published— |
| 2026-10-04 | token | $0.07 | $0.14 | Not published— |
| 2026-10-05 | token | $0.07 | $0.14 | Not published— |
| 2026-10-06 | token | $0.07 | $0.14 | Not published— |
| 2026-10-07 | token | $0.07 | $0.14 | Not published— |
| 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 (13)
frequency_penaltylogit_biasmax_tokensmin_ppresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetop_ktop_p
Call this model
OpenRouter id 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":"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: "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": "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())