FrameworkPydantic AI with DEVUP AI
Build type-safe agents with Pydantic AI on DEVUP AI models. Connect OpenAIChatModel to DEVUP AI with OpenAIProvider, and get validated, typed answers.
System Architecture
How Pydantic AI Connects to DEVUP AI
1. Client
Pydantic AI
Your Python agent
2. Gateway
DEVUP OpenAI-compatible API
POST /v1/chat/completions
3. Inference
Model
DeepSeek-V4-Pro
4. Response
Response
Text, tool calls and validated objects
Configuration
Quick Setup
bash
pip install "pydantic-ai-slim[openai]"python
import os
from pydantic_ai import Agent
from pydantic_ai.models.openai import OpenAIChatModel
from pydantic_ai.providers.openai import OpenAIProvider
model = OpenAIChatModel(
"deepseek-ai/DeepSeek-V4-Pro",
provider=OpenAIProvider(
base_url="https://api.devupai.com/v1",
api_key=os.environ["DEVUP_API_KEY"],
),
)
agent = Agent(model, instructions="Be concise.")
result = agent.run_sync("Reply with exactly: Salam DEVUP")
print(result.output)Structured Output
Typed Answers with Pydantic
python
from pydantic import BaseModel
class City(BaseModel):
name: str
country: str
city_agent = Agent(model, output_type=City)
result = city_agent.run_sync("Which city is the capital of Algeria?")
print(result.output)Capabilities
Supported Capabilities
Agents and streaming
Run agents synchronously, or stream text as it is generated with run_stream_sync.
Tool calling
Decorate a Python function with @agent.tool_plain and the model calls it when needed.
Structured output
Set output_type to a Pydantic model and the agent returns validated, typed data.
Local DZD billing
Metered billing in Algerian Dinar with BaridiMob, Edahabia, and CIB local payment support.
