Phi-3 Medium 4K on DeepInfra

Phi-3 · Microsoft Research

ServerlessOpen Source

Last refreshed 2026-06-15. Next refresh: weekly.

Why use Phi-3 Medium 4K on DeepInfra?

DeepInfra offers Phi-3 Medium 4K with pay-as-you-go pricing at $0.14/1M input tokens. DeepInfra is a cloud inference platform offering cost-effective access to open-source AI models.

Compare Phi-3 Medium 4K across 3 providers to find the best fit for your use case
Input / 1M
$0.14
Output / 1M
$0.41
Cache
Not sourced
Batch
Not sourced

Setup recipe

Python + curl
Install
pip install openai
Auth
export DEEPINFRA_API_KEY=...
Call
import os
from openai import OpenAI
client = OpenAI(
    api_key=os.environ["DEEPINFRA_API_KEY"],
Model ID
phi-3-medium-4k

Request example

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["DEEPINFRA_API_KEY"],
    base_url="https://api.deepinfra.com/v1/openai"
)
response = client.chat.completions.create(
    model="phi-3-medium-4k",
    messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)

Gotchas

  • DeepInfra uses "organization/model-name" format, e.g. "meta-llama/Meta-Llama-3-8B-Instruct" or "mistralai/Mistral-7B-Instruct-v0.3". See the DeepInfra model catalog for exact IDs.
  • The examples expect DEEPINFRA_API_KEY; rename it only if your application config maps the new variable.

Compare Phi-3 Medium 4K Across Providers

ProviderInput (per 1M)Output (per 1M)
Microsoft Foundry$0.45$1.35
NVIDIA NIM——
DeepInfra$0.14$0.41

Pricing

TypePrice (per 1M)
Input tokens$0.14
Output tokens$0.41

Capabilities

Structured Outputs

About Phi-3 Medium 4K

The Phi-3 Medium 4K, developed by Microsoft, is a state-of-the-art large language model with 14 billion parameters. It is engineered for efficiency across various tasks, particularly excelling in reasoning capabilities. This model is designed to handle 4,096 token context lengths, allowing for the processing of longer input sequences. Leveraging a dense, decoder-only Transformer architecture, it incorporates techniques like supervised fine-tuning and direct preference optimization to align with human preferences and safety standards. The model supports multilingual data, although it is primarily trained in English.

Get Started

Model Specs

Released2024-05-21
Parameters14B
Context4k
ArchitectureDecoder Only
Knowledge cutoff2023-10