Phi 4 Reasoning API Pricing

Phi 4 Reasoning pricing by provider

1 listing across 1 provider. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.

What Phi 4 Reasoning costs in practice

1,000 requests with 2,000 input and 500 output tokens each

Phi 4 Reasoning features

• Function calling
• Reasoning

Use Phi 4 Reasoning with LiteLLM

Call Phi 4 Reasoning 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="azure_ai/Phi-4-reasoning",
    messages=[{"role": "user", "content": "Hello!"}],
)

model_list:
  - model_name: phi-4-reasoning
    litellm_params:
      model: azure_ai/Phi-4-reasoning
      # credentials: see the provider's LiteLLM docs page

curl http://0.0.0.0:4000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-1234" \
  -d '{
    "model": "phi-4-reasoning",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Phi 4 Reasoning FAQ

More Microsoft models

• Phi 4 Mini Reasoning$0.075 / $0.30 per 1M tokens
• Phi 4 Mini Instruct$0.075 / $0.30 per 1M tokens
• Phi 4 Multimodal Instruct$0.08 / $0.32 per 1M tokens
• Phi 4$0.07 / $0.14 per 1M tokens
• Phi 2 3B$0.10 / $0.10 per 1M tokens
• Phi 3 Vision 128K Instruct$0.20 / $0.20 per 1M tokens
• Phi 3 Medium 128K Instruct$0.17 / $0.68 per 1M tokens
• Phi 3 Medium 4K Instruct$0.17 / $0.68 per 1M tokens