LiteLLMModels

Phi 3 Medium 128K Instruct API Pricing

As of October 10, 2026, Phi 3 Medium 128K Instruct costs $0.17 per 1M input tokens and $0.68 per 1M output tokens on Azure AI Foundry. It has a 128,000-token context window and returns up to 4,096 tokens per response.

By MicrosoftModel ID azure_ai/Phi-3-medium-128k-instructPrices updated Checked
Deprecated: Azure AI Foundry lists August 30, 2025 as the deprecation date for azure_ai/Phi-3-medium-128k-instruct.
Input
$0.17 / 1M tokens
Output
$0.68 / 1M tokens
Context window
128,000 tokens
Max output
4,096 tokens
Providers
1
Added to LiteLLM
November 2024

Phi 3 Medium 128K Instruct 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.

ProviderModel name in LiteLLMInputOutputContext
Azure AI Foundryazure_ai/Phi-3-medium-128k-instruct$0.17$0.68128K

What Phi 3 Medium 128K Instruct costs in practice

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

Azure AI Foundry$0.68

100 long-document requests with 100,000 input and 2,000 output tokens each

Azure AI Foundry$1.836

Phi 3 Medium 128K Instruct features

Use Phi 3 Medium 128K Instruct with LiteLLM

Call Phi 3 Medium 128K Instruct 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.

Python SDK
from litellm import completion

response = completion(
    model="azure_ai/Phi-3-medium-128k-instruct",
    messages=[{"role": "user", "content": "Hello!"}],
)
Proxy config.yaml
model_list:
  - model_name: phi-3-medium-128k-instruct
    litellm_params:
      model: azure_ai/Phi-3-medium-128k-instruct
      # credentials: see the provider's LiteLLM docs page
Call the proxy
curl http://0.0.0.0:4000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-1234" \
  -d '{
    "model": "phi-3-medium-128k-instruct",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Phi 3 Medium 128K Instruct FAQ

How much does Phi 3 Medium 128K Instruct cost?

Phi 3 Medium 128K Instruct costs $0.17 per 1M input tokens and $0.68 per 1M output tokens on Azure AI Foundry.

What is the context window of Phi 3 Medium 128K Instruct?

Phi 3 Medium 128K Instruct has a 128,000-token context window and returns up to 4,096 tokens per response.

Which providers offer Phi 3 Medium 128K Instruct?

Phi 3 Medium 128K Instruct is available from Azure AI Foundry through LiteLLM, using the model name azure_ai/Phi-3-medium-128k-instruct.

How do I call Phi 3 Medium 128K Instruct with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="azure_ai/Phi-3-medium-128k-instruct", 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 3 Medium 128K Instruct support?

It does not support image input.

When did LiteLLM add Phi 3 Medium 128K Instruct?

Phi 3 Medium 128K Instruct was added to LiteLLM's model price file in November 2024.

Is Phi 3 Medium 128K Instruct being deprecated?

Azure AI Foundry deprecated azure_ai/Phi-3-medium-128k-instruct on August 30, 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: Azure AI Foundry.

Provider pages: Azure AI Foundry.