Phi 4 API Pricing
As of October 10, 2026, Phi 4 costs $0.07 per 1M input tokens and $0.14 per 1M output tokens from DeepInfra, the lowest of 2 providers. It has a 16,384-token context window and returns up to 16,384 tokens per response.
- Input
- $0.07 / 1M tokens
- Output
- $0.14 / 1M tokens
- Context window
- 16,384 tokens
- Max output
- 16,384 tokens
- Providers
- 2
- Added to LiteLLM
- February 2025
Phi 4 pricing by provider
2 listings across 2 providers. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.
| Provider | Model name in LiteLLM | Input | Output | Context |
|---|---|---|---|---|
| DeepInfra | deepinfra/microsoft/phi-4 | $0.07 | $0.14 | 16K |
| Azure AI Foundry | azure_ai/Phi-4 | $0.125 | $0.50 | 16K |
What Phi 4 costs in practice
1,000 requests with 2,000 input and 500 output tokens each
| DeepInfra | $0.21 |
| Azure AI Foundry | $0.50 |
Phi 4 features
- Function calling
Use Phi 4 with LiteLLM
Call Phi 4 through the LiteLLM Python SDK, or put it behind the LiteLLM proxy and send OpenAI-format requests to /v1/chat/completions. LiteLLM tracks the cost of every request at these prices.
from litellm import completion
response = completion(
model="deepinfra/microsoft/phi-4",
messages=[{"role": "user", "content": "Hello!"}],
)model_list:
- model_name: phi-4
litellm_params:
model: deepinfra/microsoft/phi-4
api_key: os.environ/DEEPINFRA_API_KEYcurl http://0.0.0.0:4000/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer sk-1234" \
-d '{
"model": "phi-4",
"messages": [{"role": "user", "content": "Hello!"}]
}'Phi 4 FAQ
How much does Phi 4 cost?
Phi 4 costs $0.07 per 1M input tokens and $0.14 per 1M output tokens from DeepInfra, the lowest of 2 providers.
What is the context window of Phi 4?
Phi 4 has a 16,384-token context window and returns up to 16,384 tokens per response.
Which providers offer Phi 4?
Phi 4 is available from 2 providers through LiteLLM: DeepInfra and Azure AI Foundry. The lowest price is on DeepInfra.
How do I call Phi 4 with an OpenAI-compatible API?
Use the LiteLLM Python SDK with model="deepinfra/microsoft/phi-4", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/chat/completions from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.
What features does Phi 4 support?
Phi 4 supports function calling.
When did LiteLLM add Phi 4?
Phi 4 was added to LiteLLM's model price file in February 2025.
Sources
Prices come from LiteLLM's open-source model_prices_and_context_window.json, which LiteLLM uses to calculate the cost of every request. Provider pricing pages:
LiteLLM docs: DeepInfra, Azure AI Foundry.
Provider pages: DeepInfra, Azure AI Foundry.
