Skip to content

Nebius Token Factory

The Nebius Token Factory provider uses provider key nebius and the HPD-Agent.Providers.Nebius package. It is backed by HPD's shared OpenAI-compatible chat-completions client, so ModelName is a Nebius Token Factory chat model id.

Set an API key:

bash
export NEBIUS_API_KEY="..."

The default endpoint is https://api.tokenfactory.nebius.com/v1/, which sends chat requests to chat/completions. Pass endpoint to WithNebius(...), set Endpoint in ClientProviderConfig, or use NEBIUS_ENDPOINT / NEBIUS_BASE_URL when you need a compatible proxy or custom base URL.

Use fluent chat setup first:

csharp
using HPD.Agent;
using HPD.Agent.Providers.Nebius;

var agent = await new AgentBuilder()
    .WithNebius(model: "meta-llama/Meta-Llama-3.1-70B-Instruct")
    .BuildAsync();

var result = await agent.RunAsync("Write one sentence about Nebius Token Factory setup.");
Console.WriteLine(result.Text);

The equivalent Clients.Chat shape is:

json
{
  "Clients": {
    "Chat": {
      "ProviderKey": "nebius",
      "ModelName": "meta-llama/Meta-Llama-3.1-70B-Instruct"
    }
  }
}

Runtime Chat Options

Use ChatRunConfig for shared model-call behavior such as temperature, top-p, max output tokens, stop sequences, response format, tools, tool mode, seed, and generic reasoning options. Put agent-level defaults in ClientProviderConfig.ChatDefaults or .WithChatDefaults(...); use AgentRunConfig.Chat for per-run or per-session overrides.

Caveats

The default endpoint targets Nebius Token Factory. Use the endpoint override aliases if you need the older Nebius AI Studio base URL or a dedicated endpoint.

This provider currently registers the chat family only. Other endpoint families, if the upstream service exposes them, are deferred until HPD has dedicated provider-family support for that surface.

Chat uses HPD's shared OpenAI-compatible chat-completions client. It supports token streaming, function tools, response format and tool mode, seed, max output tokens, top-p, temperature, and stop sequences where the selected model supports them.

Validation checks model and endpoint configuration. Runtime chat options are applied through ChatDefaults and AgentRunConfig.Chat. Missing credentials fail at BuildAsync() before a live provider call.

Built for production .NET agent applications.