Skip to main content
Providers

Nebius Token Factory

Use nebius/<model> with VoltAgent's model router.

Quick start​

import { Agent } from "@voltagent/core";

const agent = new Agent({
  name: "nebius-agent",
  instructions: "You are a helpful assistant",
  model: "nebius/NousResearch/hermes-4-405b",
});

Environment variables​

  • NEBIUS_API_KEY

Provider package​

@ai-sdk/openai-compatible

This provider uses the OpenAI-compatible adapter.

Default base URL​

https://api.tokenfactory.nebius.com/v1

You can override the base URL by setting NEBIUS_BASE_URL.

Provider docs​

Models​

Show models (15)
  • NousResearch/hermes-4-405b
  • NousResearch/hermes-4-70b
  • deepseek-ai/deepseek-v3
  • meta-llama/llama-3.3-70b-instruct-base
  • meta-llama/llama-3.3-70b-instruct-fast
  • meta-llama/llama-3_1-405b-instruct
  • moonshotai/kimi-k2-instruct
  • nvidia/llama-3_1-nemotron-ultra-253b-v1
  • openai/gpt-oss-120b
  • openai/gpt-oss-20b
  • qwen/qwen3-235b-a22b-instruct-2507
  • qwen/qwen3-235b-a22b-thinking-2507
  • qwen/qwen3-coder-480b-a35b-instruct
  • zai-org/glm-4.5
  • zai-org/glm-4.5-air

Table of Contents