EphemeraAdmin: Import: Help:Ephemera Agent/LLM Providers

2026-04-01T04:29:33Z

Import: Help:Ephemera Agent/LLM Providers

New page

{{DISPLAYTITLE:Ephemera Agent — LLM Providers}}
__TOC__

== Supported Providers ==

{| class="wikitable" style="width:100%"
! Provider !! Available Models !! API Key Location
|-
| Claude (Anthropic) || claude-sonnet-4-20250514, claude-opus-4-20250514, claude-haiku-4-5-20251001 || [https://console.anthropic.com console.anthropic.com]
|-
| GPT (OpenAI) || gpt-4o, gpt-4o-mini, gpt-4-turbo || [https://platform.openai.com/api-keys platform.openai.com/api-keys]
|-
| Gemini (Google) || gemini-2.5-pro, gemini-2.5-flash, gemini-2.5-flash-lite, gemini-3.1-pro-preview, gemini-3-flash-preview, gemini-3.1-flash-lite-preview || [https://aistudio.google.com/apikey aistudio.google.com/apikey]
|-
| Custom endpoint || Any model name || Varies by provider
|}

== Custom / OpenAI-Compatible Endpoints ==

Select '''Custom (OpenAI-compatible)''' from the provider dropdown, then enter:
* '''API Endpoint URL''' — the full URL of the <code>/chat/completions</code> endpoint (e.g. <code>https://api.groq.com/openai/v1/chat/completions</code>)
* '''Model name''' — exact model string the endpoint expects (e.g. <code>llama-3.3-70b-versatile</code>)
* '''API key''' — the provider's API key

Compatible with: Groq, Mistral, Together AI, Fireworks, Perplexity, and others. Also compatible with locally-hosted models via Ollama or LM Studio — expose them with a tunnel (e.g. ngrok) to make them reachable from the server.

== Tiered Model Routing ==

The system uses two separate LLM calls per generative task:

; Planner tier
: Handles task classification and entity extraction. Should be a fast, cheap model. The input is small and the output is structured JSON — no creativity needed. Recommended: Haiku, Flash-Lite, GPT-4o-mini.

; Generator tier
: Handles actual content creation. Receives the full assembled context. Use the best model available for the quality of output you need.

Configure each tier independently in the '''SETTINGS''' tab. Settings persist via localStorage.

== Recommendations ==

* Use a fast, low-cost model for the Planner tier.
* Use the strongest available model for the Generator tier.
* If tool calling behaves unexpectedly, try switching providers before assuming the prompts or backend are at fault.

== Key Storage ==

API keys entered manually are stored in browser memory only for the duration of the session. Loading a [[Help:Ephemera Agent/Configuration#Keys File|keys file]] provides the same memory-only storage with one-click convenience.

Keys are '''never''' written to disk, stored in cookies, or sent to any server other than the relevant AI provider's own API.

[[Category:Help]]
[[Category:EphemeraAgent]]

Help:Ephemera Agent/LLM Providers - Revision history

EphemeraAdmin: Import: Help:Ephemera Agent/LLM Providers