# Phi 3 Mini 128K Instruct API Pricing

As of October 10, 2026, Phi 3 Mini 128K Instruct costs $0.10 per 1M input tokens and $0.10 per 1M output tokens from Fireworks AI, the lowest of 2 providers. It has a 131,072-token context window and returns up to 131,072 tokens per response.

- Page: https://models.litellm.ai/models/phi-3-mini-128k-instruct
- Lab: Microsoft
- LiteLLM model name: `fireworks_ai/accounts/fireworks/models/phi-3-mini-128k-instruct`
- Context window: 131,072 tokens
- Max output: 131,072 tokens
- Added to LiteLLM: November 2024
- Prices updated: October 10, 2026

## Pricing by provider

Token prices in USD per 1M tokens.

| Provider | Model name | Input | Output | Cache read | Per image | Per second | Context |
|---|---|---|---|---|---|---|---|
| Fireworks AI | `fireworks_ai/accounts/fireworks/models/phi-3-mini-128k-instruct` | $0.10 | $0.10 | – | – | – | 128K |
| Azure AI Foundry | `azure_ai/Phi-3-mini-128k-instruct` | $0.13 | $0.52 | – | – | – | 128K |

## Cost examples

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

- Fireworks AI: $0.25
- Azure AI Foundry: $0.52

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

- Fireworks AI: $1.02
- Azure AI Foundry: $1.404

## Use it with LiteLLM

```python
from litellm import completion

response = completion(
    model="fireworks_ai/accounts/fireworks/models/phi-3-mini-128k-instruct",
    messages=[{"role": "user", "content": "Hello!"}],
)
```

## FAQ

### How much does Phi 3 Mini 128K Instruct cost?

Phi 3 Mini 128K Instruct costs $0.10 per 1M input tokens and $0.10 per 1M output tokens from Fireworks AI, the lowest of 2 providers.

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

Phi 3 Mini 128K Instruct has a 131,072-token context window and returns up to 131,072 tokens per response.

### Which providers offer Phi 3 Mini 128K Instruct?

Phi 3 Mini 128K Instruct is available from 2 providers through LiteLLM: Fireworks AI and Azure AI Foundry. The lowest price is on Fireworks AI.

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

Use the LiteLLM Python SDK with model="fireworks_ai/accounts/fireworks/models/phi-3-mini-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.

### When did LiteLLM add Phi 3 Mini 128K Instruct?

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

Source: LiteLLM model price file, https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json