Eden AI
for LuumenAI
One API key for model access across providers, with stored responses held for approval
Eden AI puts text, image, audio, document, and multimodal models from many providers behind one API. Connect it with an API key and Luumen can check which models are current, count tokens before a call, run moderation or embeddings, and read your credit balance and consumption. Stored response objects can be created and retrieved later.
The Eden AI toolbox
10 tools: 9 read, 1 write. Reads answer instantly. Writes require approval by default. Everything is logged.
- ReadCount Anthropic TokensCount input tokens for an Anthropic-format message request before generation, including system content and tool definitions.
- ReadCreate Anthropic MessageGenerate a non-streaming Anthropic-compatible message with content blocks, stop reason, token usage, provider metadata, and Eden AI cost.
- ReadCreate Chat CompletionGenerate a non-streaming OpenAI-compatible chat completion with a current Eden AI model and return its choices, token usage, provider, and cost.
- ReadCreate EmbeddingsCreate embeddings for one text or a batch of texts and return vectors with model, usage, provider, and cost metadata.
- ReadDiscover AI CapabilitiesFind current Eden AI models or inspect Universal AI feature schemas, providers, pricing, and regions before an execution call.
- ReadGet Cost OverviewReturn current account credits and, when a date range is supplied, aggregated consumption filtered by provider or subfeature.
- ReadGet ResponseRetrieve a previously stored Responses API object by ID, including its status, text output, structured output, usage, and canonical model.
- ReadModerate TextClassify one text or a batch of texts for safety categories and return flags, category scores, applied input types, provider, and cost.
- ReadRun Universal AIRun one synchronous Eden AI Universal AI feature using a current model and feature-specific input.
- WriteCreate ResponseCreate or continue a synchronous OpenAI Responses-compatible text response, stored by default for later retrieval, and return its ID, structured output, text, usage, provider, and cost. Approval by default
One prompt, start to finish
What a governed Eden AI run looks like inside Luumen.
Questions
Authorize once with API token. Luumen lists the scopes each action needs before you approve the connection, and credentials never appear in the chat.
Read actions answer immediately. Anything that writes — create response — is shown as a plan and requires approval by default. Administrators configure that per tool, so you decide exactly which actions can ever run unattended.
You decide. Actions are granted per agent, skill, and team, and per environment — production is not staging. Read access can be broad while writes stay narrow.
Every call to Eden AI — read or write, approved or declined — is recorded with the actor, the input, and the result, and can be linked to the ticket or change record.
Often connected alongside
All integrations
Adobe Marketing Agent MCPAdobe Experience Platform context, sandbox switches, and async task status
AffindaRead parsed documents, collections, and annotations — change them with approval
Agent MailGive the agent its own mailbox for reading threads and sending updates
AI/ML APIInspect assistants, threads, and runs — and change them as approved stepsPut Eden AI to work with Luumen
Connect in minutes. Every action scoped, approved, and audited from day one.