---
title: "Phi-3.5-MoE-instruct Cost Calculator - Azure"
description: "Calculate the cost of using Phi-3.5-MoE-instruct from Azure. Input costs $0.16 and output $0.64 per 1M tokens."
url: "https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/azure/model/phi-3.5-moe-instruct"
markdown: "https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/azure/model/phi-3.5-moe-instruct.md"
---

# Phi-3.5-MoE-instruct Cost Calculator - Azure

> Calculate the cost of using Phi-3.5-MoE-instruct from Azure. Input costs $0.16 and output $0.64 per 1M tokens.

## Important Links

- [View MCP Gateway](https://www.getmaxim.ai/bifrost/resources/mcp-gateway.md)
- [Features](https://www.getmaxim.ai/bifrost/#features)
- [Enterprise](https://www.getmaxim.ai/bifrost/enterprise)
- [Pricing](https://www.getmaxim.ai/bifrost/pricing.md)
- [Docs](https://docs.getbifrost.ai)
- [GitHub](https://github.com/maximhq/bifrost)
- [Book a Demo](https://www.getmaxim.ai/bifrost/book-a-demo)

## About Phi-3.5-MoE-instruct

Phi-3.5-MoE-instruct is a chat model from Azure, one of 221 chat models they offer. It is priced at $0.16 per 1M input tokens and $0.64 per 1M output tokens, ranking 651 out of 2912 chat models by cost and cheaper than 78% of models in this category. It accepts up to 128K input tokens.

## Pricing

Published Azure pricing for Phi-3.5-MoE-instruct.

- **$0.16 / 1M tokens Input.**
- **$0.64 / 1M tokens Output.**

## Technical Specifications

- **Chat Mode.**
- **128,000 Max Input Tokens.**
- **4,096 Max Output Tokens.**
- **4,096 Max Tokens.**

## Model Capabilities

Phi-3.5-MoE-instruct supports: Tool Choice.

## How Pricing Compares

At $0.16 per 1M input tokens and $0.64 per 1M output tokens, Phi-3.5-MoE-instruct ranks 651 out of 2912 chat models by input cost. It is more affordable compared to the median of $0.55 for chat models, and is cheaper than 78% of models in this category.

| Model | Provider | Input $/1M | Output $/1M | vs Phi-3.5-MoE-instruct |
| --- | --- | --- | --- | --- |
| ai21.jamba-1-5-mini-v1:0 | AWS Bedrock | $0.20 | $0.40 | +25% |
| zephyr-7b-beta | Anyscale | $0.15 | $0.15 | -6% |
| gemma-7b-it | Anyscale | $0.15 | $0.15 | -6% |
| Llama-2-7b-chat-hf | Anyscale | $0.15 | $0.15 | -6% |
| Meta-Llama-3-8B-Instruct | Anyscale | $0.15 | $0.15 | -6% |

## More from Azure

- [gpt-4o-mini-2024-07-18 ($0.17/1M input)](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/azure/model/gpt-4o-mini-2024-07-18.md)
- [gpt-4o-mini-2024-07-18 ($0.15/1M input)](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/azure/model/gpt-4o-mini-2024-07-18.md)
- [Phi-3-medium-128k-instruct ($0.17/1M input)](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/azure/model/phi-3-medium-128k-instruct.md)

## Related Resources

- [Azure AI status](https://www.getmaxim.ai/bifrost/provider-status/azure.md)
- [Phi-3.5-MoE-instruct specifications](https://www.getmaxim.ai/bifrost/model-library/compare/azure/phi-3.5-moe-instruct.md)
- [All Azure pricing](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/azure.md)

## FAQ

### Is Phi-3.5-MoE-instruct cheaper than ai21.jamba-1-5-mini-v1:0?

Yes. Phi-3.5-MoE-instruct costs $0.16 per 1M input tokens compared to ai21.jamba-1-5-mini-v1:0's $0.20 per 1M input tokens, making it 25% more affordable. Both are chat models.

### How does Phi-3.5-MoE-instruct pricing compare to the average chat model?

Phi-3.5-MoE-instruct input pricing is $0.16 per 1M tokens, which is 71% below the median of $0.55 for chat models. It ranks 651 out of 2912 chat models by input cost, making it cheaper than 78% of models in this category. For output, it costs $0.64 per 1M tokens compared to the median of $1.50.

### What makes Phi-3.5-MoE-instruct different from other Azure models?

Among Azure's 221 chat models, Phi-3.5-MoE-instruct ranks 28 by input cost.

### What are the best alternatives to Phi-3.5-MoE-instruct?

The most comparable chat models to Phi-3.5-MoE-instruct are: ai21.jamba-1-5-mini-v1:0 from AWS Bedrock ($0.20/1M input tokens); zephyr-7b-beta from Anyscale ($0.15/1M input tokens); gemma-7b-it from Anyscale ($0.15/1M input tokens); Llama-2-7b-chat-hf from Anyscale ($0.15/1M input tokens). These alternatives were selected based on similar capabilities, pricing, and provider diversity. You can compare any of these models in detail using the Bifrost Model Library.

### How do I check if Azure AI is down?

You can monitor Azure AI service health in real time on the Bifrost Azure AI Status page. It tracks current component status, active incidents, and historical reliability data pulled from the official status page every 60 seconds.

### How do I calculate Phi-3.5-MoE-instruct costs?

Phi-3.5-MoE-instruct is priced based on input and output tokens. Use the interactive calculator at the top of this page to estimate costs for your specific workload. Enter your expected input and output tokens volume and the calculator will show the total cost breakdown. For reference, processing 1M input tokens costs $0.16 and generating 1M output tokens costs $0.64.

## Related Resources

- [All Azure pricing](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/azure.md)
- [LLM cost calculator](https://www.getmaxim.ai/bifrost/llm-cost-calculator.md)
- [Model library](https://www.getmaxim.ai/bifrost/model-library.md)
- [Docs: Bifrost docs](https://docs.getbifrost.ai)
- [GitHub: maximhq/bifrost](https://github.com/maximhq/bifrost)
- [Pricing: Bifrost pricing](https://www.getmaxim.ai/bifrost/pricing.md)
- [Enterprise: Bifrost enterprise](https://www.getmaxim.ai/bifrost/enterprise)
- [Book a Demo: Bifrost demo](https://www.getmaxim.ai/bifrost/book-a-demo)
- [Resources: Bifrost resources](https://www.getmaxim.ai/bifrost/resources.md)

---

*This is a markdown version of [https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/azure/model/phi-3.5-moe-instruct](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/azure/model/phi-3.5-moe-instruct) for AI/LLM consumption.*