Phi-3.5 Mini — Microsoft | Modeldex

Phi-3.5 Mini

Active

3.8B instruction-following model targeting mobile and edge deployment.

Updated 3 days agoStructured data from Modeldex catalog

Open source

Not enough benchmark coverage yet for an Intelligence Index — needs at least 3 results across 2 categories.

Overview

Phi-3.5 Mini is Microsoft's lightweight 3.8B model optimized for edge and on-device inference with strong instruction following and multilingual support.

History

Phi-3.5 Mini was released on 2024-08-20.

Training & availability

Weights are publicly available under the MIT license, making this an open-weight model suitable for on-prem deployment and fine-tuning.

Capabilities

Context window: 128K tokens.
Max output: 4K tokens.
Input modalities: text.

Recommended for: open-source.

Limitations

Text-only — cannot process images, audio, or video inputs.

Quick start

Minimal example using the OpenRouter API. Copy, paste, replace the key.

from openai import OpenAI

client = OpenAI(
    base_url="https://openrouter.ai/api/v1",
    api_key="sk-or-...",
)
resp = client.chat.completions.create(
    model="microsoft/phi-3-5-mini",
    messages=[{"role": "user", "content": "Explain quantum computing in one sentence."}],
)
print(resp.choices[0].message.content)

Cost calculator

Estimate your monthly bill. Presets are typical workload sizes.

Input tokens / month5.0M

@ $0.13/1M

Output tokens / month2.0M

@ $0.52/1M

Input cost

$0.65

5.0M × $0.13/1M

Output cost

$1.04

2.0M × $0.52/1M

Total / month

$1.69

$20.28 / year

Integrations & tooling support

Tool calling: Not supported
Structured outputs: Not supported

Price vs quality

Budget pricing

Priced low — good for high-volume tasks. Quality tier pending more benchmark coverage.