Choose the model HeroUI Agent runs and let end users switch between hosted models.
HeroUI Agent runs only models in its hosted catalog. Use composer.defaultModel
to choose the initial model and composer.modelPicker to let end users change it.
Each turn is charged to the workspace's AI credits based on the model's actual usage.
<HeroUIAgent
getAuthToken={getAuthToken}
composer={{defaultModel: "google/gemini-3.8-flash", modelPicker: true}}
agentId={process.env.HEROUI_AGENT_ID!}
/>| ID | Label | Provider | Tier |
|---|---|---|---|
moonshotai/Kimi-K3 | Kimi K3 | Moonshot AI | Light |
openai/gpt-5.6-luna | GPT-5.6 Luna | OpenAI | Light |
openai/gpt-5.6-terra | GPT-5.6 Terra | OpenAI | Codegen |
openai/gpt-5.6-sol | GPT-5.6 Sol | OpenAI | Complex |
google/gemini-3.8-flash | Gemini 3.8 Flash | Light | |
x-ai/grok-4.6 | Grok 4.6 | xAI | Codegen |
anthropic/claude-sonnet-5 | Claude Sonnet 5 | Anthropic | Codegen |
anthropic/claude-opus-4.8 | Claude Opus 4.8 | Anthropic | Complex |
Retired Gemini 3.5 Flash, Gemini 3.6 Flash, and Gemini 3.7 Flash ids resolve to Gemini 3.8 Flash.