OpenAI
Call OpenAI's REST API — chat completions, images, audio, files, embeddings, moderations.
About
OpenAI ships in the w6w first-party pack. It declares 13 actions, 2 health checks, and the host runs its code in a sandbox that never sees the credential.
- App id
io.w6w.openai- Version
- 0.3.1
- Author
- w6w
- Licence
- MIT
- Categories
- AI & Machine Learning · Developer Tools
Overview
OpenAI covers most of what a workflow would reach for across the API — chat completions, generating embeddings for search or similarity, and moderating content before it’s shown to anyone else in a process.
Audio and images are both first-class: audio can be transcribed or translated to English, and images can be generated from a prompt, edited, or used to produce variations — three distinct image actions rather than one that tries to cover every case. Files can be uploaded, listed, fetched and deleted for use as inputs elsewhere in the API, and models can be listed to keep a workflow’s choice explicit.
A fit for adding an AI step almost anywhere in a workflow — summarizing or classifying text, moderating user-submitted content, transcribing audio, or generating an image from data produced earlier in the process.
Build with OpenAI
Three routes to the same 13 actions. The Workflow tab is generated from OpenAI's own manifest and carries its real ids, so it is copy-pasteable; the Code and CLI examples are the same call for any action on any app, so every app-specific value in them is a blank you fill in.
A workflow step names the app and the action, and the editor fills in the
connection when you pick one. This is the Step shape from the
workflow spec, carrying OpenAI's real ids.
{
"manifestVersion": "2",
"name": "openai-example",
"steps": [
{
"id": "audio-transcribe",
"uses": {
"app": "io.w6w.openai",
"action": "audio-transcribe",
"connection": "conn_YOUR_CONNECTION_ID"
},
"with": {
"file": "<file>"
}
}
]
}Here are some of the things you can do
-
Transcribe Audio
performaudio-transcribe -
Translate Audio
performaudio-translate -
Create Chat Completion
performchat-complete -
Create Embeddings
performembeddings-create -
List Files
readfiles-list
+8 more actions available
Every app-specific value here is a blank you have to fill in. An
app action is reached through the connection that authenticates it, so the
address is a connection id, not the app id — and connections belong to your account,
so a public page cannot know yours. Create one for OpenAI, then fill in
the three blanks: conn_YOUR_CONNECTION_ID, the action key, and the
parameters that action declares. The call itself is real — the shape is transcribed
from the studio's own snippet builder, which prints the same kind of blanks — but
nothing in it is specific to OpenAI. The Workflow tab is where this app's
real ids are.
npm install @w6w/sdkyarn add @w6w/sdkpnpm add @w6w/sdkdeno add npm:@w6w/sdkimport { W6wClient, isActionRun } from "@w6w/sdk";
// Reads W6W_BASE_URL and W6W_TOKEN from the environment when omitted.
const client = new W6wClient();
const envelope = await client.run({
urn: "conn_YOUR_CONNECTION_ID",
action: "chat-complete",
payload: {
model: "<value>",
messages: "<value>",
// temperature: "<value>",
// topP: "<value>",
// n: "<value>",
// maxTokens: "<value>",
// frequencyPenalty: "<value>",
// presencePenalty: "<value>",
// stop: "<value>",
// user: "<value>",
// responseFormat: "<value>",
// jsonSchema: "<value>",
// seed: "<value>",
// tools: "<value>",
// toolChoice: "<value>",
// parallelToolCalls: "<value>",
},
});
if (isActionRun(envelope)) console.log(envelope.value);npm install -g @w6w/cliw6w run conn_YOUR_CONNECTION_ID --action chat-complete --payload '{"model":"<value>","messages":"<value>"}'Give an AI agent OpenAI — without giving it OpenAI's credentials. One MCP endpoint exposes every app, function and workflow the caller is entitled to, as tools it can discover and run. Access is granted per team while we onboard.
One tool call{
"name": "w6w_invoke",
"arguments": {
"ref": "app:io.w6w.openai#audio-transcribe",
"input": {
"file": "<file>"
}
}
}
Every tool names its target with a single ref. The
app: form above doesn't name a connection at all — the
host resolves which of the caller's OpenAI connections to sign
with, and refuses rather than guesses when the answer is ambiguous.
What the agent gets
Credentials it can't read
The token is attached host-side, at the moment of the call. It is never a tool argument, never in the model's context, and never in a transcript — so a prompt injection has nothing to exfiltrate.
A tool surface scoped to the caller
Tools are derived per end user from what that person has actually connected and is entitled to — not one shared bot identity carrying the union of everyone's access.
A durable workflow in one call
Multi-step work runs on the workflow engine and returns a run handle the agent can poll — retries, branching and state survive the conversation that started them.
Health-aware discovery
OpenAI's declared health checks are on the surface too, so an agent can tell "the vendor is down" from "your credential expired" before it burns a retry on either.
The MCP surface is part of the hosted platform. OpenAI itself is MIT, and the runtime that executes it is source-available (FSL).
Health checks
OpenAI declares its own checks, so its health is a property of the app rather than something the host guesses at.
OpenAI platform status
Atlassian Statuspage rollup for status.openai.com, with per-component detail. Unauthenticated and unsigned.
API rate-limit headroom
Requests-per-minute and tokens-per-minute remaining, read off the `x-ratelimit-*` headers.