LLM answers

An LLM destination generates the answer for a route. When it fires, Dcision sends a chat request to the model you picked — the route's prompt as the system message, the state (or a template of your choice) as the user message — and returns the model's text in the response.

It is how one decision can route and answer: Jev decides that a message is about billing, and the billing prompt writes the reply.

Your key, your providerCopy Anchor Link

LLM answers run on your own provider key — never on Dcision's engine key:

Save the key in Settings → Engine → Provider keys — the same keys used to bring your own key for Jev; Admins and the Owner can add them. Saving a key doesn't change the engine: decisions can keep running on Dcision's engine key while their LLM destinations use yours. The provider bills the tokens to your account; Dcision doesn't charge for them, and the decision itself is billed as usual.

Configure itCopy Anchor Link

{
  "key": "sales_llm",
  "type": "llm",
  "when": { "conditions": [{ "field": "route", "on": "output", "operator": "eq", "value": "sales" }] },
  "llm": {
    "provider": "openrouter",
    "model": "openai/gpt-5-mini",
    "instructions": "You are Acme's sales team. Answer the lead in two sentences, say that a person will follow up today and never quote prices.",
    "input": "{{state.message}}",
    "maxTokens": 300,
    "temperature": 0.3,
    "timeoutMs": 15000
  }
}

Prompts and inputs use the text encoding; secrets can't be used in them.

In the responseCopy Anchor Link

{
  "key": "sales_llm",
  "type": "llm",
  "status": "completed",
  "text": "Thanks for reaching out! Someone from our sales team will contact you today to talk about your 500 users.",
  "model": "openai/gpt-5-mini",
  "usage": { "input_tokens": 61, "output_tokens": 27 }
}

model is the model the provider reports, and usage the tokens it counted — the provider's numbers, separate from the decision's own metrics.

When the call can't be made or fails, the entry says so and the decision still answers:

{ "key": "sales_llm", "type": "llm", "status": "failed", "error": "Add your OpenRouter key in Settings → Engine to use LLM replies." }

LLM calls are made once — they aren't retried — and failures appear in the decision's Overview as failed destinations.

LatencyCopy Anchor Link

The caller waits for LLM answers: they run after the decision, in parallel with the other destinations that wait (agents in sync mode), so the response arrives after the slowest of them. A decision can make at most 3 such calls per execution; more are skipped with "reason": "limit".

Give your HTTP client a timeout that covers the decision's timeoutMs plus the longest destination timeoutMs — for example 5 s + 15 s + a margin. The SDKs wait 30 seconds per attempt by default. The response's metrics.latency_ms measures the decision only: it doesn't include the time spent on these calls.

In the PlaygroundCopy Anchor Link

Previews show the prompt — provider, model, the rendered instructions and message — without calling the model. Switch on Run destinations for real to get a real answer; see Testing destinations.

DataCopy Anchor Link

The input — the whole state unless you set input — is sent to the provider you chose, under your account and its terms. Send only what the answer needs: "input": "{{state.message}}" instead of the whole state.