recommend_model
Selects the cheapest model from a provider-locked ladder that can handle a user message, using complexity classification to reduce costs in multi-step workflows.
Instructions
Given a ladder of models (cheap → flagship) and a user message, return the cheapest model on the ladder that can plausibly handle it, plus reasoning. The ladder should be brand-locked (all-Anthropic, all-OpenAI, etc.) to honor your user's BYOK provider.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"userMessage": "<userMessage>",
"ladder": "<ladder>"
},
"name": "recommend_model"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| ladder | Yes | Ordered model ids, index 0 = cheapest. Example: ['openai/gpt-5.4-mini', 'openai/gpt-5.4', 'openai/gpt-5.5'] | |
| userMessage | Yes | The user's request. | |
| recentHistory | No | Optional context. Last 1-2 assistant turns. |