Models

Model-agnostic design, ModelProvider interface, factory functions, and ModelConfig options in RadarOS.

Models

Model Agnosticism

RadarOS is model-agnostic. You can use OpenAI, Anthropic, Google Gemini, Vertex AI, Ollama, or any custom provider through a unified ModelProvider interface. Switch models with a single line change—no refactoring required.

Unified Interface

All providers implement the same generate() and stream() methods. Your agent code stays identical.

Easy Switching

Swap openai("gpt-4o") for anthropic("claude-sonnet-4-20250514") without touching the rest of your app.

---

ModelProvider Interface

Every model in RadarOS implements the ModelProvider interface:

interface ModelProvider {
  readonly providerId: string;
  readonly modelId: string;
  generate(messages: ChatMessage[], options?: ModelConfig & { tools?: ToolDefinition[] }): Promise<ModelResponse>;
  stream(messages: ChatMessage[], options?: ModelConfig & { tools?: ToolDefinition[] }): AsyncGenerator<StreamChunk>;
}

providerId · string

Unique identifier for the provider (e.g., "openai", "anthropic").

modelId · string

The specific model identifier (e.g., "gpt-4o", "claude-sonnet-4-20250514").

generate · (messages, options?) => Promise<ModelResponse>

Non-streaming completion. Returns the full response with message, usage, and finish reason.

stream · (messages, options?) => AsyncGenerator<StreamChunk>

Streaming completion. Yields text deltas, tool call chunks, and finish events.

---

Factory Functions

Use factory functions to create model instances. Each returns a ModelProvider ready for agents, teams, and workflows.

Factory	Provider	Returns	Config
openai(modelId, config?)	OpenAI	ModelProvider	{ apiKey?, baseURL? }
anthropic(modelId, config?)	Anthropic	ModelProvider	{ apiKey? }
google(modelId, config?)	Google Gemini	ModelProvider	{ apiKey? }
vertex(modelId, config?)	Google Vertex AI	ModelProvider	{ project?, location?, credentials? }
ollama(modelId, config?)	Ollama (local)	ModelProvider	{ host? } (default: http://localhost:11434)
openaiRealtime(modelId?, config?)	OpenAI Realtime	RealtimeProvider	{ apiKey?, baseURL? }
googleLive(modelId?, config?)	Gemini Live	RealtimeProvider	{ apiKey? }

Switching Models in One Line

import { Agent, openai, anthropic, google, vertex, ollama } from "@radaros/core";

// OpenAI
const model = openai("gpt-4o");

// Anthropic
const model = anthropic("claude-sonnet-4-20250514");

// Google Gemini (API key)
const model = google("gemini-2.5-flash");

// Google Vertex AI (GCP auth)
const model = vertex("gemini-2.5-flash", { project: "my-project" });

// Local Ollama (no API key)
const model = ollama("llama3.1");

const agent = new Agent({
  name: "Assistant",
  model,
  instructions: "You are a helpful assistant.",
});

Realtime Providers (Voice)

For voice agents, use the realtime helpers that return a RealtimeProvider:

import { VoiceAgent, openaiRealtime, googleLive } from "@radaros/core";

// OpenAI Realtime
const agent = new VoiceAgent({
  name: "assistant",
  provider: openaiRealtime("gpt-4o-realtime-preview"),
});

// Google Gemini Live
const agent = new VoiceAgent({
  name: "assistant",
  provider: googleLive("gemini-2.5-flash-native-audio-preview-12-2025"),
});

---

ModelConfig Options

Pass these options to generate() or stream() (or set them on agents):

temperature · number

Sampling temperature (0–2). Lower = more deterministic. Typical: 0.7.

maxTokens · number

Maximum tokens in the completion. Provider-specific limits apply.

topP · number

Nucleus sampling. Alternative to temperature for some providers.

stop · string[]

Stop sequences. Generation stops when any of these strings are produced.

responseFormat · 'text' | 'json' | object

Output format: "text" (default), "json" (JSON object), or { type: "json_schema", schema, name? } for structured output.

apiKey · string

Per-request API key override. Use when you need to override the key set at construction (e.g., multi-tenant).

Example: ModelConfig Usage

const response = await model.generate(messages, {
  temperature: 0.3,
  maxTokens: 1024,
  responseFormat: "json",
});

---

Next Steps

OpenAI

GPT-4o, GPT-4o-mini, GPT-4-turbo, o1-preview.

Anthropic

Claude Sonnet, Claude Haiku.

Google Gemini

Gemini 2.5 Flash, Gemini 2.5 Pro. Multi-modal support.

Vertex AI

Enterprise Gemini via Google Cloud. IAM auth, VPC, compliance.

Ollama

Local models: Llama, CodeLlama, Mistral.

Custom Provider

Implement your own ModelProvider.