Question 1

What is the cost of Phi-3.5-MoE-instruct by Azure Cognitive Services?

Accepted Answer

Phi-3.5-MoE-instruct by Azure Cognitive Services costs $0.16 per 1M input tokens and $0.64 per 1M output tokens.

Question 2

What is the context window of Phi-3.5-MoE-instruct by Azure Cognitive Services?

Accepted Answer

Phi-3.5-MoE-instruct by Azure Cognitive Services has a context window of 128K tokens. It supports up to 128K input tokens and can generate up to 4K output tokens.

Question 3

What are the capabilities of Phi-3.5-MoE-instruct by Azure Cognitive Services?

Accepted Answer

Phi-3.5-MoE-instruct by Azure Cognitive Services supports adjustable temperature. It has open weights.

Question 4

What input and output types does Phi-3.5-MoE-instruct support?

Accepted Answer

Phi-3.5-MoE-instruct by Azure Cognitive Services accepts text as input and can generate text as output.

Question 5

Is Phi-3.5-MoE-instruct by Azure Cognitive Services open source?

Accepted Answer

Yes, Phi-3.5-MoE-instruct by Azure Cognitive Services has open weights, meaning the model weights are publicly available for download and self-hosting.

Question 6

What is the knowledge cutoff date for Phi-3.5-MoE-instruct?

Accepted Answer

Phi-3.5-MoE-instruct by Azure Cognitive Services has a knowledge cutoff date of 2023-10. This means the model was trained on data available up until that date.

Phi-3.5-MoE-instruct API

Input Modalities

Output Modalities

Standard (per 1M tokens)

Phi-3.5-MoE-instruct API

Input Modalities

Output Modalities

Standard (per 1M tokens)