3288bbc47e
Video generation was xAI-only. Adds an adapter layer under
open-sse/handlers/videoProviders/ so /v1/videos/* can target OpenRouter or
Google Cloud credentials. A provider with no adapter keeps the exact previous
behaviour (raw body to {baseUrl}/{action}, poll {baseUrl}/{id}, verbatim
passthrough), so the xAI path is unchanged.
- openrouter: async job shape identical to xAI; creation POSTs to the /videos
collection root (no /generations suffix) and the registry HTTP-Referer /
X-Title headers are applied. Bodies pass through verbatim.
- vertex: two-way translation, since Veo does not speak the OpenAI-ish videos
shape. create -> :predictLongRunning { instances[], parameters{} }, poll ->
:fetchPredictOperation (Veo has no REST GET poll). The operation resource
name is base64url-encoded into the job id so GET /v1/videos/{id} stays a
flat path. Access tokens are minted from Service Account JSON via the
existing refreshVertexToken; raw API keys are rejected up front. The
operation response maps back onto the { id, status, video, videos } shape
clients already poll.
- videoCore: the request plan is rebuilt per attempt, so the 401 -> refresh
once -> retry once path picks up the refreshed token. Adapter validation
errors return 400 before any upstream call, so a malformed request can never
create a billable job.
- videoGeneration: GET /v1/videos/{id} resolves the provider from the pinned
x-connection-id connection, then ?provider=, then falls back to the xAI
default.
- registry: openrouter and vertex gain videoConfig, the video serviceKind and
video-kind models (Veo 3.1 / 3 / 2, Sora 2 Pro, Seedance 2.0).
40 lines
1.9 KiB
JavaScript
40 lines
1.9 KiB
JavaScript
export default {
|
|
id: "vertex",
|
|
priority: 40,
|
|
alias: "vertex",
|
|
aliases: [
|
|
"vx",
|
|
],
|
|
uiAlias: "vx",
|
|
display: {
|
|
name: "Vertex AI",
|
|
icon: "cloud",
|
|
color: "#4285F4",
|
|
textIcon: "VX",
|
|
website: "https://cloud.google.com/vertex-ai",
|
|
notice: {
|
|
text: "New Google Cloud accounts get $300 free credits. Requires GCP project + Service Account with Vertex AI API enabled.",
|
|
apiKeyUrl: "https://console.cloud.google.com/iam-admin/serviceaccounts",
|
|
},
|
|
},
|
|
category: "freeTier",
|
|
transport: {
|
|
baseUrl: "https://aiplatform.googleapis.com",
|
|
format: "vertex",
|
|
},
|
|
models: [
|
|
{ id: "gemini-3.1-pro-preview", name: "Gemini 3.1 Pro Preview" },
|
|
{ id: "gemini-3.1-flash-lite-preview", name: "Gemini 3.1 Flash Lite Preview" },
|
|
{ id: "gemini-3-flash-preview", name: "Gemini 3 Flash Preview" },
|
|
{ id: "gemini-2.5-flash", name: "Gemini 2.5 Flash" },
|
|
{ id: "veo-3.1-generate-preview", name: "Veo 3.1 (Preview)", params: ["duration","aspect_ratio","resolution","negative_prompt","seed","storage_uri","generate_audio"], kind: "video" },
|
|
{ id: "veo-3.1-fast-generate-preview", name: "Veo 3.1 Fast (Preview)", params: ["duration","aspect_ratio","resolution","negative_prompt","seed","storage_uri","generate_audio"], kind: "video" },
|
|
{ id: "veo-3.0-generate-001", name: "Veo 3", params: ["duration","aspect_ratio","resolution","negative_prompt","seed","storage_uri","generate_audio"], kind: "video" },
|
|
{ id: "veo-2.0-generate-001", name: "Veo 2", params: ["duration","aspect_ratio","negative_prompt","seed","storage_uri"], kind: "video" },
|
|
],
|
|
serviceKinds: ["llm","imageToText","video"],
|
|
// Veo via predictLongRunning + fetchPredictOperation (adapter: handlers/videoProviders/vertex.js).
|
|
// Docs: https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/veo-video-generation
|
|
videoConfig: { baseUrl: "https://aiplatform.googleapis.com" },
|
|
};
|