Pydantic AI - Nito

# pip install pydantic-ai
from pydantic_ai import Agent
from pydantic_ai.models.openai import OpenAIChatModel
from pydantic_ai.providers.openai import OpenAIProvider

model = OpenAIChatModel(
    "moonshotai/kimi-k3",                                    # a Nito catalog ID, fetch from GET /v1/models
    provider=OpenAIProvider(
        api_key="z_sk_your_key_here",              # your Nito API key
        base_url="https://app.trynito.ai/v1",  # Nito's OpenAI-compatible base URL
    ),
)

agent = Agent(model)
result = agent.run_sync("Say hello in one short sentence.")
print(result.output)

OpenAIChatModel speaks Chat Completions, which is what every OpenAI-compatible provider in Pydantic AI uses. The OPENAI_BASE_URL and OPENAI_API_KEY environment variables are the alternative to passing base_url and api_key.

"z-ai/glm-5.2:confidential"

Privacy

Use a catalog ID, not an OpenAI name. For attested hardware use a :confidential variant; GET /v1/models lists their :confidential IDs. Encrypted needs client-side encryption and extra headers, which these frameworks do not add. See Privacy Levels.

Framework Integrations

The shared pattern.

OpenAI Compatibility

What differs.

Privacy Levels

The four levels.