An AI Model is an LLM (or transcription model) that Frontline exposes to agents and workflows. Models are managed by Frontline — you cannot create or modify them via the Public API. You only discover them and reference them by id from elsewhere.
| Field | Type | Notes |
|---|---|---|
id | number | Use as aiModelId when configuring an agent setting. |
name | string | Display name (e.g. GPT-4o, Claude 3.5 Sonnet). |
description | string? | Marketing-style summary. |
type | enum | TEXT · TRANSCRIPTION. |
aiVendor | string? | E.g. openai, anthropic, google. |
reasoningModel | boolean? | true for thinking-tier models. |
creditsPerMessage | number? | Cost in Frontline credits per message generated. |
isDefault | boolean? | Whether this is the default model for its type. |
order | number? | Display order in the UI. |
analyticsColor | string? | Hex color used in dashboards. |
externalId | string? | Provider-side identifier. |
- Agent settings — set
aiModelIdinPUT /agents/{agentId}/agent-settingto change the model an agent uses for conversation. Frontline validates the ID before saving. - Workflow nodes — AI-flavored nodes (
TOOLS_AI,AI_CAPTURE,DATA_TRANSFORMER, …) inherit the agent's model when used inside flows; standalone automation nodes use account defaults. - Transcription nodes — automation
TRANSCRIPTIONnodes pick a model withtype: TRANSCRIPTION.
Frontline ships defaults per model type:
GET /public/v1/ai-models/default?type=TEXT
GET /public/v1/ai-models/default?type=TRANSCRIPTIONIf you don't pin a specific aiModelId, Frontline falls back to these.
| Verb | Path | Purpose |
|---|---|---|
GET | /public/v1/ai-models | List (optional type filter) |
GET | /public/v1/ai-models/default | Get default for a type |
GET | /public/v1/ai-models/{aiModelId} | Detail |
Read-only. Listing accepts type=TEXT or type=TRANSCRIPTION to filter.
frontline ai-models list --type TEXT --table
frontline ai-models default --type TEXT
frontline ai-models describe 1Use the returned id as aiModelId in frontline agents agent-setting update.