LlamaIndex - Nito

# pip install llama-index-llms-openai-like
from llama_index.llms.openai_like import OpenAILike

llm = OpenAILike(
    model="moonshotai/kimi-k3",                              # a Nito catalog ID, fetch from GET /v1/models
    api_key="z_sk_your_key_here",                  # your Nito API key
    api_base="https://app.trynito.ai/v1",  # note: api_base (not base_url)
    is_chat_model=True,                            # else it routes to the legacy /completions path
    is_function_calling_model=True,                # only if the model supports tools
    context_window=128000,                         # default is only 3900, set the model's real window
)

print(llm.complete("Say hello in one short sentence."))

Use OpenAILike, the wrapper LlamaIndex provides for OpenAI-compatible endpoints. Its context_window defaults to 3900 and is_chat_model and is_function_calling_model default to False, so set all three.

model="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.