Phi 3.5 MoE Instruct API Pricing
As of October 10, 2026, Phi 3.5 MoE Instruct costs $0.16 per 1M input tokens and $0.64 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.
azure_ai/Phi-3.5-MoE-instruct.- Input
- $0.16 / 1M tokens
- Output
- $0.64 / 1M tokens
- Context window
- 128,000 tokens
- Max output
- 4,096 tokens
- Providers
- 1
- Added to LiteLLM
- November 2024
Phi 3.5 MoE 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.
| Provider | Model name in LiteLLM | Input | Output | Context |
|---|---|---|---|---|
| Azure AI Foundry | azure_ai/Phi-3.5-MoE-instruct | $0.16 | $0.64 | 128K |
What Phi 3.5 MoE Instruct costs in practice
1,000 requests with 2,000 input and 500 output tokens each
| Azure AI Foundry | $0.64 |
100 long-document requests with 100,000 input and 2,000 output tokens each
| Azure AI Foundry | $1.728 |
Phi 3.5 MoE Instruct features
- Image input
Use Phi 3.5 MoE Instruct with LiteLLM
Call Phi 3.5 MoE 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.
from litellm import completion
response = completion(
model="azure_ai/Phi-3.5-MoE-instruct",
messages=[{"role": "user", "content": "Hello!"}],
)model_list:
- model_name: phi-3.5-moe-instruct
litellm_params:
model: azure_ai/Phi-3.5-MoE-instruct
# credentials: see the provider's LiteLLM docs pagecurl http://0.0.0.0:4000/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer sk-1234" \
-d '{
"model": "phi-3.5-moe-instruct",
"messages": [{"role": "user", "content": "Hello!"}]
}'Phi 3.5 MoE Instruct FAQ
How much does Phi 3.5 MoE Instruct cost?
Phi 3.5 MoE Instruct costs $0.16 per 1M input tokens and $0.64 per 1M output tokens on Azure AI Foundry.
What is the context window of Phi 3.5 MoE Instruct?
Phi 3.5 MoE Instruct has a 128,000-token context window and returns up to 4,096 tokens per response.
Which providers offer Phi 3.5 MoE Instruct?
Phi 3.5 MoE Instruct is available from Azure AI Foundry through LiteLLM, using the model name azure_ai/Phi-3.5-MoE-instruct.
How do I call Phi 3.5 MoE Instruct with an OpenAI-compatible API?
Use the LiteLLM Python SDK with model="azure_ai/Phi-3.5-MoE-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 3.5 MoE Instruct support?
It does not support image input.
When did LiteLLM add Phi 3.5 MoE Instruct?
Phi 3.5 MoE Instruct was added to LiteLLM's model price file in November 2024.
Is Phi 3.5 MoE Instruct being deprecated?
Azure AI Foundry deprecated azure_ai/Phi-3.5-MoE-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.
