Using Phi-4 Mini on Fireworks AI
Implementation guide · Phi-4 · Microsoft Research
ServerlessOpen Source
Fireworks AI exposes Phi-4 Mini through model ID phi-4-mini. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.
Last refreshed 2026-05-19. Next refresh: weekly.
Quick Start
- 1
- 2
- 3
Code Examples
Install
pip install openaiAPI key
FIREWORKS_API_KEYModel ID
phi-4-miniFireworks model IDs use "accounts/fireworks/models/{model-name}" format, e.g. "accounts/fireworks/models/llama4-scout-instruct-basic" or "accounts/fireworks/models/deepseek-r1".
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["FIREWORKS_API_KEY"],
base_url="https://api.fireworks.ai/inference/v1"
)
response = client.chat.completions.create(
model="phi-4-mini",
messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)Pricing on Fireworks AI
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.90 |
| Output tokens | $0.90 |
Capabilities
No model capability flags are currently sourced.
About Phi-4 Mini
Phi-4 family model from Microsoft Research. Mini variant with efficient performance.
Model Specs
Released2024-12-13
Parameters3.8B
Context128k
Knowledge cutoff2024-06