Nebius Token Factory - Agno

Nebius Token Factory provides OpenAI-compatible inference for hosted models. Browse the model catalog, query the model-list API, and check function-calling support before selecting a model.

Authentication

Create an API key in the Nebius Token Factory console, then export the key and a current text-generation model ID.

export NEBIUS_API_KEY="your_nebius_api_key"
export NEBIUS_MODEL_ID="your_current_text_model_id"

$Env:NEBIUS_API_KEY="your_nebius_api_key"
$Env:NEBIUS_MODEL_ID="your_current_text_model_id"

Example

Use Nebius with your Agent:

import os

from agno.agent import Agent
from agno.models.nebius import Nebius

agent = Agent(
    model=Nebius(
        id=os.environ["NEBIUS_MODEL_ID"],
    ),
    markdown=True
)

# Print the response in the terminal
agent.print_response("Share a 2 sentence horror story.")

See the Nebius usage examples.

The pinned Agno 2.7.2 default, openai/gpt-oss-20b, is retired from serverless inference. Set id to an explicit current text-generation model ID from the Nebius model-list API.

Params

Parameter	Type	Default	Description
`id`	`str`	`"openai/gpt-oss-20b"`	The id of the Nebius model to use
`name`	`str`	`"Nebius"`	The name of the model
`provider`	`str`	`"Nebius"`	The provider of the model
`api_key`	`Optional[str]`	`None`	The API key for Nebius (defaults to NEBIUS_API_KEY env var)
`base_url`	`str`	`"https://api.tokenfactory.nebius.com/v1/"`	The base URL for the Nebius API