Phi-4 is a modern open-source language model with 14 billion parameters. Although the architectural changes compared to previous versions are minimal, the model demonstrates significant progress in tasks requiring logical thinking and analytical skills, made possible by an innovative training approach. Unlike traditional language model training methods, Phi-4 focuses not on the quantity of data but on its quality. The training of Phi-4 utilized diverse sources, including synthetic data specifically designed to develop reasoning skills, filtered documents from public sources, as well as acquired academic books and question-answer knowledge bases. This allows the model to achieve high performance even with a relatively small size.
Phi-4 works exclusively with textual data. Its context window is relatively small at 16K tokens, but it supports more than 50 languages, including Russian.
Overall, Phi-4 is a versatile lightweight model, but according to its developers, it is particularly effective in environments with limited memory and computational resources, as well as for tasks requiring instant response.
| Model Name | Context | Type | GPU | TPS | Status | Link |
|---|---|---|---|---|---|---|
| phi-4 | 16,000.0 | Public | RTX3090 | 31.50 | AVAILABLE | chat |
curl https://chat.immers.cloud/v1/endpoints/phi-4/generate/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer USER_API_KEY" \
-d '{"model": "phi-4", "messages": [
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "Say this is a test"}
], "temperature": 0, "max_tokens": 150}'
$response = Invoke-WebRequest https://chat.immers.cloud/v1/endpoints/phi-4/generate/chat/completions `
-Method POST `
-Headers @{
"Authorization" = "Bearer USER_API_KEY"
"Content-Type" = "application/json"
} `
-Body (@{
model = "phi-4"
messages = @(
@{ role = "system"; content = "You are a helpful assistant." },
@{ role = "user"; content = "Say this is a test" }
)
} | ConvertTo-Json)
($response.Content | ConvertFrom-Json).choices[0].message.content
#!pip install OpenAI --upgrade
from openai import OpenAI
client = OpenAI(
api_key="USER_API_KEY",
base_url="https://chat.immers.cloud/v1/endpoints/phi-4/generate/",
)
chat_response = client.chat.completions.create(
model="phi-4",
messages=[
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "Say this is a test"},
]
)
print(chat_response.choices[0].message.content)
Rent your own physically dedicated instance with hourly or long-term monthly billing.
We recommend deploying private instances in the following scenarios:
| Name | GPU | TPS | Max Concurrency | |||
|---|---|---|---|---|---|---|
16,384.0 |
1 | $0.53 | 32.100 | 2.787 | Launch | |
16,384.0 tensor |
2 | $0.54 | 4.291 | Launch | ||
16,384.0 tensor |
2 | $0.57 | 9.150 | 4.291 | Launch | |
16,384.0 tensor |
2 | $0.69 | 1.411 | Launch | ||
16,384.0 |
1 | $0.83 | 50.090 | 2.787 | Launch | |
16,384.0 |
1 | $1.02 | 69.850 | 2.787 | Launch | |
16,384.0 |
1 | $1.20 | 5.091 | Launch | ||
16,384.0 tensor |
2 | $1.23 | 8.899 | Launch | ||
16,384.0 pipeline |
3 | $1.43 | 2.915 | Launch | ||
16,384.0 |
1 | $1.59 | 83.030 | 5.091 | Launch | |
16,384.0 tensor |
4 | $1.82 | 4.995 | Launch | ||
16,384.0 |
1 | $2.37 | 53.030 | 18.915 | Launch | |
16,384.0 |
1 | $3.83 | 63.450 | 18.915 | Launch | |
16,384.0 |
1 | $4.11 | 22.947 | Launch | ||
16,384.0 |
1 | $4.74 | 36.483 | Launch | ||
| Name | GPU | TPS | Max Concurrency | |||
|---|---|---|---|---|---|---|
16,384.0 |
1 | $0.53 | 1.731 | Launch | ||
16,384.0 tensor |
2 | $0.54 | 3.235 | Launch | ||
16,384.0 tensor |
2 | $0.57 | 3.235 | Launch | ||
16,384.0 |
1 | $0.83 | 1.731 | Launch | ||
16,384.0 pipeline |
3 | $0.84 | 2.723 | Launch | ||
16,384.0 |
1 | $1.02 | 1.731 | Launch | ||
16,384.0 tensor |
4 | $1.12 | 5.091 | Launch | ||
16,384.0 |
1 | $1.20 | 4.035 | Launch | ||
16,384.0 tensor |
2 | $1.23 | 7.843 | Launch | ||
16,384.0 pipeline |
3 | $1.43 | 1.859 | Launch | ||
16,384.0 |
1 | $1.59 | 4.035 | Launch | ||
16,384.0 tensor |
4 | $1.82 | 3.939 | Launch | ||
16,384.0 |
1 | $2.37 | 17.859 | Launch | ||
16,384.0 |
1 | $3.83 | 17.859 | Launch | ||
16,384.0 |
1 | $4.11 | 21.891 | Launch | ||
16,384.0 |
1 | $4.74 | 35.427 | Launch | ||
| Name | GPU | TPS | Max Concurrency | |||
|---|---|---|---|---|---|---|
16,384.0 pipeline |
3 | $0.88 | 2.045 | Launch | ||
16,384.0 tensor |
2 | $0.93 | 29.000 | 2.845 | Launch | |
16,384.0 tensor |
4 | $0.96 | 5.853 | Launch | ||
16,384.0 pipeline |
3 | $1.06 | 2.045 | Launch | ||
16,384.0 tensor |
2 | $1.23 | 2.845 | Launch | ||
16,384.0 tensor |
4 | $1.26 | 5.853 | Launch | ||
16,384.0 tensor |
2 | $1.56 | 46.560 | 2.845 | Launch | |
16,384.0 tensor |
2 | $1.92 | 55.000 | 2.845 | Launch | |
16,384.0 tensor |
2 | $2.22 | 7.453 | Launch | ||
16,384.0 |
1 | $2.37 | 45.550 | 12.861 | Launch | |
16,384.0 tensor |
2 | $2.93 | 73.390 | 7.453 | Launch | |
16,384.0 |
1 | $3.83 | 53.090 | 12.861 | Launch | |
16,384.0 |
1 | $4.11 | 87.210 | 16.893 | Launch | |
16,384.0 |
1 | $4.74 | 30.429 | Launch | ||
Contact our dedicated neural networks support team at nn@immers.cloud or send your request to the sales department at sale@immers.cloud.