Using Phi-3 Vision on Fireworks AI
Implementation guide · Phi-3 · Microsoft Research
Fireworks AI exposes Phi-3 Vision through model ID phi-3-vision. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.
Last refreshed 2026-09-21. Next refresh: weekly.
Quick Start
- 1
- 2Use the Fireworks AI SDK or REST API to call
phi-3-vision— see the documentation for request format. - 3
Code Examples
pip install openaiFIREWORKS_API_KEYphi-3-visionFireworks 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-3-vision",
messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)Pricing on Fireworks AI
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.20 |
| Output tokens | $0.20 |
Capabilities
About Phi-3 Vision
Phi-3 Vision is a sophisticated multimodal AI model from Microsoft, designed to adeptly integrate language and vision capabilities. Unlike traditional language models, it processes both text and images and can perform tasks such as optical character recognition, chart analysis, and image interpretation. Its architecture features an image encoder, a text-image connector, a projector for mapping image features, and the Phi-3 Mini language model. Despite its relatively small size of 4.2 billion parameters, it competes with larger models and suits devices with limited computational power. Phi-3 Vision's ability to handle up to 128K tokens supports complex multimodal reasoning.